diff --git a/README.md b/README.md index 2fc6b44..a626929 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ Soil is an extensible and user-friendly Agent-based Social Simulator for Social Networks. Learn how to run your own simulations with our [documentation](http://soilsim.readthedocs.io). -Follow our [tutorial](notebooks/soil_tutorial.ipynb) to develop your own agent models. +Follow our [tutorial](examples/tutorial/soil_tutorial.ipynb) to develop your own agent models. If you use Soil in your research, don't forget to cite this paper: diff --git a/docs/Tutorial - Spreading news.rst b/docs/Tutorial - Spreading news.rst deleted file mode 100644 index 8eaf7cd..0000000 --- a/docs/Tutorial - Spreading news.rst +++ /dev/null @@ -1,1284 +0,0 @@ -Developing new models ---------------------- - -Introduction -============ - -This notebook is an introduction to the soil agent-based social network -simulation framework. In particular, we will focus on a specific use -case: studying the propagation of news in a social network. - -The steps we will follow are: - -- Modelling the behavior of agents -- Running the simulation using different configurations -- Analysing the results of each simulation - -But before that, let's import the soil module and networkx. - -.. code:: ipython3 - - import soil - import networkx as nx - -.. code:: ipython3 - - %pylab inline - # To display plots in the notebook - - -.. parsed-literal:: - - Populating the interactive namespace from numpy and matplotlib - - -Basic concepts -============== - -There are three main elements in a soil simulation: - -- The network topology. A simulation may use an existing NetworkX - topology, or generate one on the fly -- Agents. There are two types: 1) network agents, which are linked to a - node in the topology, and 2) environment agents, which are freely - assigned to the environment. -- The environment. It assigns agents to nodes in the network, and - stores the environment parameters (shared state for all agents). - -Soil is based on ``simpy``, which is an event-based network simulation -library. Soil provides several abstractions over events to make -developing agents easier. This means you can use events (timeouts, -delays) in soil, but for the most part we will assume your models will -be step-based. - -Modeling behaviour -================== - -Our first step will be to model how every person in the social network -reacts when it comes to news. We will follow a very simple model (a -finite state machine). - -There are two types of people, those who have heard about a newsworthy -event (infected) or those who have not (neutral). A neutral person may -heard about the news either on the TV (with probability -**prob\_tv\_spread**) or through their friends. Once a person has heard -the news, they will spread it to their friends (with a probability -**prob\_neighbor\_spread**). Some users do not have a TV, so they only -rely on their friends. - -The spreading probabilities will change over time due to different -factors. We will represent this variance using an environment agent. - -Network Agents -++++++++++++++ - -A basic network agent in Soil should inherit from -``soil.agents.BaseAgent``, and define its behaviour in every step of the -simulation by implementing a ``run(self)`` method. The most important -attributes of the agent are: - -- ``agent.state``, a dictionary with the state of the agent. - ``agent.state['id']`` reflects the state id of the agent. That state - id can be used to look for other networks in that specific state. The - state can be access via the agent as well. For instance: - - .. code:: py - - a = soil.agents.BaseAgent(env=env) - a['hours_of_sleep'] = 10 - print(a['hours_of_sleep']) - - The state of the agent is stored in every step of the simulation: - ``py print(a['hours_of_sleep', 10]) # hours of sleep before step #10 print(a[None, 0]) # whole state of the agent before step #0`` - -- ``agent.env``, a reference to the environment. Most commonly used to - get access to the environment parameters and the topology: - - .. code:: py - - a.env.G.nodes() # Get all nodes ids in the topology - a.env['minimum_hours_of_sleep'] - -Since our model is a finite state machine, we will be basing it on -``soil.agents.FSM``. - -With ``soil.agents.FSM``, we do not need to specify a ``step`` method. -Instead, we describe every step as a function. To change to another -state, a function may return the new state. If no state is returned, the -state remains unchanged.[ It will consist of two states, ``neutral`` -(default) and ``infected``. - -Here's the code: - -.. code:: ipython3 - - import random - - class NewsSpread(soil.agents.FSM): - @soil.agents.default_state - @soil.agents.state - def neutral(self): - r = random.random() - if self['has_tv'] and r < self.env['prob_tv_spread']: - return self.infected - return - - @soil.agents.state - def infected(self): - prob_infect = self.env['prob_neighbor_spread'] - for neighbor in self.get_neighboring_agents(state_id=self.neutral.id): - r = random.random() - if r < prob_infect: - neighbor.state['id'] = self.infected.id - return - - -Environment agents -++++++++++++++++++ - -Environment agents allow us to control the state of the environment. In -this case, we will use an environment agent to simulate a very viral -event. - -When the event happens, the agent will modify the probability of -spreading the rumor. - -.. code:: ipython3 - - NEIGHBOR_FACTOR = 0.9 - TV_FACTOR = 0.5 - class NewsEnvironmentAgent(soil.agents.BaseAgent): - def step(self): - if self.now == self['event_time']: - self.env['prob_tv_spread'] = 1 - self.env['prob_neighbor_spread'] = 1 - elif self.now > self['event_time']: - self.env['prob_tv_spread'] = self.env['prob_tv_spread'] * TV_FACTOR - self.env['prob_neighbor_spread'] = self.env['prob_neighbor_spread'] * NEIGHBOR_FACTOR - -Testing the agents -++++++++++++++++++ - -Feel free to skip this section if this is your first time with soil. - -Testing agents is not easy, and this is not a thorough testing process -for agents. Rather, this section is aimed to show you how to access -internal pats of soil so you can test your agents. - -First of all, let's check if our network agent has the states we would -expect: - -.. code:: ipython3 - - NewsSpread.states - - - - -.. parsed-literal:: - - {'infected': , - 'neutral': } - - - -Now, let's run a simulation on a simple network. It is comprised of -three nodes: - -.. code:: ipython3 - - G = nx.Graph() - G.add_edge(0, 1) - G.add_edge(0, 2) - G.add_edge(2, 3) - G.add_node(4) - pos = nx.spring_layout(G) - nx.draw_networkx(G, pos, node_color='red') - nx.draw_networkx(G, pos, nodelist=[0], node_color='blue') - - - -.. image:: output_21_0.png - - -Let's run a simple simulation that assigns a NewsSpread agent to all the -nodes in that network. Notice how node 0 is the only one with a TV. - -.. code:: ipython3 - - env_params = {'prob_tv_spread': 0, - 'prob_neighbor_spread': 0} - - MAX_TIME = 100 - EVENT_TIME = 10 - - sim = soil.simulation.SoilSimulation(topology=G, - num_trials=1, - max_time=MAX_TIME, - environment_agents=[{'agent_type': NewsEnvironmentAgent, - 'state': { - 'event_time': EVENT_TIME - }}], - network_agents=[{'agent_type': NewsSpread, - 'weight': 1}], - states={0: {'has_tv': True}}, - default_state={'has_tv': False}, - environment_params=env_params) - env = sim.run_simulation()[0] - - -.. parsed-literal:: - - Trial: 0 - Running - Finished trial in 0.014928102493286133 seconds - Finished simulation in 0.015764951705932617 seconds - - -Now we can access the results of the simulation and compare them to our -expected results - -.. code:: ipython3 - - agents = list(env.network_agents) - - # Until the event, all agents are neutral - for t in range(10): - for a in agents: - assert a['id', t] == a.neutral.id - - # After the event, the node with a TV is infected, the rest are not - assert agents[0]['id', 11] == NewsSpread.infected.id - - for a in agents[1:4]: - assert a['id', 11] == NewsSpread.neutral.id - - # At the end, the agents connected to the infected one will probably be infected, too. - assert agents[1]['id', MAX_TIME] == NewsSpread.infected.id - assert agents[2]['id', MAX_TIME] == NewsSpread.infected.id - - # But the node with no friends should not be affected - assert agents[4]['id', MAX_TIME] == NewsSpread.neutral.id - - -Lastly, let's see if the probabilities have decreased as expected: - -.. code:: ipython3 - - assert abs(env.environment_params['prob_neighbor_spread'] - (NEIGHBOR_FACTOR**(MAX_TIME-1-10))) < 10e-4 - assert abs(env.environment_params['prob_tv_spread'] - (TV_FACTOR**(MAX_TIME-1-10))) < 10e-6 - -Running the simulation -====================== - -To run a simulation, we need a configuration. Soil can load -configurations from python dictionaries as well as JSON and YAML files. -For this demo, we will use a python dictionary: - -.. code:: ipython3 - - config = { - 'name': 'ExampleSimulation', - 'max_time': 20, - 'interval': 1, - 'num_trials': 1, - 'network_params': { - 'generator': 'complete_graph', - 'n': 500, - }, - 'network_agents': [ - { - 'agent_type': NewsSpread, - 'weight': 1, - 'state': { - 'has_tv': False - } - }, - { - 'agent_type': NewsSpread, - 'weight': 2, - 'state': { - 'has_tv': True - } - } - ], - 'states': [ {'has_tv': True} ], - 'environment_params':{ - 'prob_tv_spread': 0.01, - 'prob_neighbor_spread': 0.5 - } - } - -Let's run our simulation: - -.. code:: ipython3 - - soil.simulation.run_from_config(config, dump=False) - - -.. parsed-literal:: - - Using config(s): ExampleSimulation - Trial: 0 - Running - Finished trial in 1.4140360355377197 seconds - Finished simulation in 2.4056642055511475 seconds - - -In real life, you probably want to run several simulations, varying some -of the parameters so that you can compare and answer your research -questions. - -For instance: - -- Does the outcome depend on the structure of our network? We will use - different generation algorithms to compare them (Barabasi-Albert and - Erdos-Renyi) -- How does neighbor spreading probability affect my simulation? We will - try probability values in the range of [0, 0.4], in intervals of 0.1. - -.. code:: ipython3 - - network_1 = { - 'generator': 'erdos_renyi_graph', - 'n': 500, - 'p': 0.1 - } - network_2 = { - 'generator': 'barabasi_albert_graph', - 'n': 500, - 'm': 2 - } - - - for net in [network_1, network_2]: - for i in range(5): - prob = i / 10 - config['environment_params']['prob_neighbor_spread'] = prob - config['network_params'] = net - config['name'] = 'Spread_{}_prob_{}'.format(net['generator'], prob) - s = soil.simulation.run_from_config(config) - - -.. parsed-literal:: - - Using config(s): Spread_erdos_renyi_graph_prob_0.0 - Trial: 0 - Running - Finished trial in 0.2691483497619629 seconds - Finished simulation in 0.3650345802307129 seconds - Using config(s): Spread_erdos_renyi_graph_prob_0.1 - Trial: 0 - Running - Finished trial in 0.34261059761047363 seconds - Finished simulation in 0.44017767906188965 seconds - Using config(s): Spread_erdos_renyi_graph_prob_0.2 - Trial: 0 - Running - Finished trial in 0.34417223930358887 seconds - Finished simulation in 0.4550771713256836 seconds - Using config(s): Spread_erdos_renyi_graph_prob_0.3 - Trial: 0 - Running - Finished trial in 0.3237779140472412 seconds - Finished simulation in 0.42307496070861816 seconds - Using config(s): Spread_erdos_renyi_graph_prob_0.4 - Trial: 0 - Running - Finished trial in 0.3507683277130127 seconds - Finished simulation in 0.45061564445495605 seconds - Using config(s): Spread_barabasi_albert_graph_prob_0.0 - Trial: 0 - Running - Finished trial in 0.19115304946899414 seconds - Finished simulation in 0.20927715301513672 seconds - Using config(s): Spread_barabasi_albert_graph_prob_0.1 - Trial: 0 - Running - Finished trial in 0.22086191177368164 seconds - Finished simulation in 0.2390913963317871 seconds - Using config(s): Spread_barabasi_albert_graph_prob_0.2 - Trial: 0 - Running - Finished trial in 0.21225976943969727 seconds - Finished simulation in 0.23252630233764648 seconds - Using config(s): Spread_barabasi_albert_graph_prob_0.3 - Trial: 0 - Running - Finished trial in 0.2853121757507324 seconds - Finished simulation in 0.30568504333496094 seconds - Using config(s): Spread_barabasi_albert_graph_prob_0.4 - Trial: 0 - Running - Finished trial in 0.21434736251831055 seconds - Finished simulation in 0.23370599746704102 seconds - - -The results are conveniently stored in pickle (simulation), csv (history -of agent and environment state) and gexf format. - -.. code:: ipython3 - - !tree soil_output - !du -xh soil_output/* - - -.. parsed-literal:: - - soil_output - ├── Sim_prob_0 - │   ├── Sim_prob_0.dumped.yml - │   ├── Sim_prob_0.simulation.pickle - │   ├── Sim_prob_0_trial_0.environment.csv - │   └── Sim_prob_0_trial_0.gexf - ├── Spread_barabasi_albert_graph_prob_0.0 - │   ├── Spread_barabasi_albert_graph_prob_0.0.dumped.yml - │   ├── Spread_barabasi_albert_graph_prob_0.0.simulation.pickle - │   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv - │   └── Spread_barabasi_albert_graph_prob_0.0_trial_0.gexf - ├── Spread_barabasi_albert_graph_prob_0.1 - │   ├── Spread_barabasi_albert_graph_prob_0.1.dumped.yml - │   ├── Spread_barabasi_albert_graph_prob_0.1.simulation.pickle - │   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.environment.csv - │   └── Spread_barabasi_albert_graph_prob_0.1_trial_0.gexf - ├── Spread_barabasi_albert_graph_prob_0.2 - │   ├── Spread_barabasi_albert_graph_prob_0.2.dumped.yml - │   ├── Spread_barabasi_albert_graph_prob_0.2.simulation.pickle - │   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.environment.csv - │   └── Spread_barabasi_albert_graph_prob_0.2_trial_0.gexf - ├── Spread_barabasi_albert_graph_prob_0.3 - │   ├── Spread_barabasi_albert_graph_prob_0.3.dumped.yml - │   ├── Spread_barabasi_albert_graph_prob_0.3.simulation.pickle - │   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.environment.csv - │   └── Spread_barabasi_albert_graph_prob_0.3_trial_0.gexf - ├── Spread_barabasi_albert_graph_prob_0.4 - │   ├── Spread_barabasi_albert_graph_prob_0.4.dumped.yml - │   ├── Spread_barabasi_albert_graph_prob_0.4.simulation.pickle - │   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.environment.csv - │   └── Spread_barabasi_albert_graph_prob_0.4_trial_0.gexf - ├── Spread_erdos_renyi_graph_prob_0.0 - │   ├── Spread_erdos_renyi_graph_prob_0.0.dumped.yml - │   ├── Spread_erdos_renyi_graph_prob_0.0.simulation.pickle - │   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.environment.csv - │   └── Spread_erdos_renyi_graph_prob_0.0_trial_0.gexf - ├── Spread_erdos_renyi_graph_prob_0.1 - │   ├── Spread_erdos_renyi_graph_prob_0.1.dumped.yml - │   ├── Spread_erdos_renyi_graph_prob_0.1.simulation.pickle - │   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.environment.csv - │   └── Spread_erdos_renyi_graph_prob_0.1_trial_0.gexf - ├── Spread_erdos_renyi_graph_prob_0.2 - │   ├── Spread_erdos_renyi_graph_prob_0.2.dumped.yml - │   ├── Spread_erdos_renyi_graph_prob_0.2.simulation.pickle - │   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.environment.csv - │   └── Spread_erdos_renyi_graph_prob_0.2_trial_0.gexf - ├── Spread_erdos_renyi_graph_prob_0.3 - │   ├── Spread_erdos_renyi_graph_prob_0.3.dumped.yml - │   ├── Spread_erdos_renyi_graph_prob_0.3.simulation.pickle - │   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.environment.csv - │   └── Spread_erdos_renyi_graph_prob_0.3_trial_0.gexf - └── Spread_erdos_renyi_graph_prob_0.4 - ├── Spread_erdos_renyi_graph_prob_0.4.dumped.yml - ├── Spread_erdos_renyi_graph_prob_0.4.simulation.pickle - ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.environment.csv - └── Spread_erdos_renyi_graph_prob_0.4_trial_0.gexf - - 11 directories, 44 files - 1.8M soil_output/Sim_prob_0 - 652K soil_output/Spread_barabasi_albert_graph_prob_0.0 - 684K soil_output/Spread_barabasi_albert_graph_prob_0.1 - 692K soil_output/Spread_barabasi_albert_graph_prob_0.2 - 692K soil_output/Spread_barabasi_albert_graph_prob_0.3 - 688K soil_output/Spread_barabasi_albert_graph_prob_0.4 - 1.8M soil_output/Spread_erdos_renyi_graph_prob_0.0 - 1.9M soil_output/Spread_erdos_renyi_graph_prob_0.1 - 1.9M soil_output/Spread_erdos_renyi_graph_prob_0.2 - 1.9M soil_output/Spread_erdos_renyi_graph_prob_0.3 - 1.9M soil_output/Spread_erdos_renyi_graph_prob_0.4 - - -Analysing the results -===================== - -Once the simulations are over, we can use soil to analyse the results. - -First, let's load the stored results into a pandas dataframe. - -.. code:: ipython3 - - %pylab inline - from soil import analysis - - -.. parsed-literal:: - - Populating the interactive namespace from numpy and matplotlib - - -.. parsed-literal:: - - /usr/lib/python3.6/site-packages/IPython/core/magics/pylab.py:160: UserWarning: pylab import has clobbered these variables: ['random'] - `%matplotlib` prevents importing * from pylab and numpy - "\n`%matplotlib` prevents importing * from pylab and numpy" - - -.. code:: ipython3 - - config_file, df, config = list(analysis.get_data('soil_output/Spread_barabasi*prob_0.1*', process=False))[0] - df - - - - -.. raw:: html - -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
agent_idtstepattributevalue
0env0prob_tv_spread0.01
1env0prob_neighbor_spread0.1
2env1prob_tv_spread0.01
3env1prob_neighbor_spread0.1
4env2prob_tv_spread0.01
5env2prob_neighbor_spread0.1
6env3prob_tv_spread0.01
7env3prob_neighbor_spread0.1
8env4prob_tv_spread0.01
9env4prob_neighbor_spread0.1
10env5prob_tv_spread0.01
11env5prob_neighbor_spread0.1
12env6prob_tv_spread0.01
13env6prob_neighbor_spread0.1
14env7prob_tv_spread0.01
15env7prob_neighbor_spread0.1
16env8prob_tv_spread0.01
17env8prob_neighbor_spread0.1
18env9prob_tv_spread0.01
19env9prob_neighbor_spread0.1
20env10prob_tv_spread0.01
21env10prob_neighbor_spread0.1
22env11prob_tv_spread0.01
23env11prob_neighbor_spread0.1
24env12prob_tv_spread0.01
25env12prob_neighbor_spread0.1
26env13prob_tv_spread0.01
27env13prob_neighbor_spread0.1
28env14prob_tv_spread0.01
29env14prob_neighbor_spread0.1
...............
210124996has_tvTrue
210134996idneutral
210144997has_tvTrue
210154997idneutral
210164998has_tvTrue
210174998idneutral
210184999has_tvTrue
210194999idneutral
2102049910has_tvTrue
2102149910idneutral
2102249911has_tvTrue
2102349911idneutral
2102449912has_tvTrue
2102549912idneutral
2102649913has_tvTrue
2102749913idneutral
2102849914has_tvTrue
2102949914idneutral
2103049915has_tvTrue
2103149915idneutral
2103249916has_tvTrue
2103349916idneutral
2103449917has_tvTrue
2103549917idneutral
2103649918has_tvTrue
2103749918idneutral
2103849919has_tvTrue
2103949919idneutral
2104049920has_tvTrue
2104149920idinfected
-

21042 rows × 4 columns

-
- - - -.. code:: ipython3 - - list(analysis.get_data('soil_output/Spread_barabasi*prob_0.1*', process=True))[0][1] - - - - -.. raw:: html - -
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
value0.010.1FalseTrueinfectedneutral
tstep
01.01.0163.0337.00.0500.0
11.01.0163.0337.03.0497.0
21.01.0163.0337.06.0494.0
31.01.0163.0337.012.0488.0
41.01.0163.0337.023.0477.0
51.01.0163.0337.036.0464.0
61.01.0163.0337.053.0447.0
71.01.0163.0337.079.0421.0
81.01.0163.0337.0119.0381.0
91.01.0163.0337.0164.0336.0
101.01.0163.0337.0204.0296.0
111.01.0163.0337.0254.0246.0
121.01.0163.0337.0293.0207.0
131.01.0163.0337.0336.0164.0
141.01.0163.0337.0365.0135.0
151.01.0163.0337.0391.0109.0
161.01.0163.0337.0407.093.0
171.01.0163.0337.0424.076.0
181.01.0163.0337.0442.058.0
191.01.0163.0337.0452.048.0
201.01.0163.0337.0464.036.0
-
- - - -If you don't want to work with pandas, you can also use some pre-defined -functions from soil to conveniently plot the results: - -.. code:: ipython3 - - analysis.plot_all('soil_output/Spread_barabasi*', attributes=['id']) - - - -.. image:: output_44_0.png - - - -.. image:: output_44_1.png - - - -.. image:: output_44_2.png - - - -.. image:: output_44_3.png - - - -.. image:: output_44_4.png - - -.. code:: ipython3 - - analysis.plot_all('soil_output/Spread_erdos*', attributes=['id']) - - - -.. image:: output_45_0.png - - - -.. image:: output_45_1.png - - - -.. image:: output_45_2.png - - - -.. image:: output_45_3.png - - - -.. image:: output_45_4.png - diff --git a/docs/index.rst b/docs/index.rst index 24fbf0b..5822204 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -34,13 +34,14 @@ If you use Soil in your research, do not forget to cite this paper: .. toctree:: - :maxdepth: 2 + :maxdepth: 0 :caption: Learn more about soil: installation quickstart - Tutorial - Spreading news + Tutorial +.. .. Indices and tables diff --git a/docs/output_21_0.png b/docs/output_21_0.png index df25782..cce7e07 100644 Binary files a/docs/output_21_0.png and b/docs/output_21_0.png differ diff --git a/docs/output_44_0.png b/docs/output_44_0.png deleted file mode 100644 index 101c22a..0000000 Binary files a/docs/output_44_0.png and /dev/null differ diff --git a/docs/output_44_1.png b/docs/output_44_1.png deleted file mode 100644 index 5973ac6..0000000 Binary files a/docs/output_44_1.png and /dev/null differ diff --git a/docs/output_44_2.png b/docs/output_44_2.png deleted file mode 100644 index 3e55aba..0000000 Binary files a/docs/output_44_2.png and /dev/null differ diff --git a/docs/output_44_3.png b/docs/output_44_3.png deleted file mode 100644 index db7d651..0000000 Binary files a/docs/output_44_3.png and /dev/null differ diff --git a/docs/output_44_4.png b/docs/output_44_4.png deleted file mode 100644 index 226fa72..0000000 Binary files a/docs/output_44_4.png and /dev/null differ diff --git a/docs/output_45_0.png b/docs/output_45_0.png deleted file mode 100644 index 4b3a22b..0000000 Binary files a/docs/output_45_0.png and /dev/null differ diff --git a/docs/output_45_1.png b/docs/output_45_1.png deleted file mode 100644 index bf1b9d2..0000000 Binary files a/docs/output_45_1.png and /dev/null differ diff --git a/docs/output_45_2.png b/docs/output_45_2.png deleted file mode 100644 index db31580..0000000 Binary files a/docs/output_45_2.png and /dev/null differ diff --git a/docs/output_45_3.png b/docs/output_45_3.png deleted file mode 100644 index b3980d6..0000000 Binary files a/docs/output_45_3.png and /dev/null differ diff --git a/docs/output_45_4.png b/docs/output_45_4.png deleted file mode 100644 index 6dffdb5..0000000 Binary files a/docs/output_45_4.png and /dev/null differ diff --git a/docs/output_54_0.png b/docs/output_54_0.png new file mode 100644 index 0000000..1a52819 Binary files /dev/null and b/docs/output_54_0.png differ diff --git a/docs/output_54_1.png b/docs/output_54_1.png new file mode 100644 index 0000000..1a52819 Binary files /dev/null and b/docs/output_54_1.png differ diff --git a/docs/output_55_0.png b/docs/output_55_0.png new file mode 100644 index 0000000..1a52819 Binary files /dev/null and b/docs/output_55_0.png differ diff --git a/docs/output_55_1.png b/docs/output_55_1.png new file mode 100644 index 0000000..1a52819 Binary files /dev/null and b/docs/output_55_1.png differ diff --git a/docs/output_55_2.png b/docs/output_55_2.png new file mode 100644 index 0000000..8c9603c Binary files /dev/null and b/docs/output_55_2.png differ diff --git a/docs/output_55_3.png b/docs/output_55_3.png new file mode 100644 index 0000000..8c9603c Binary files /dev/null and b/docs/output_55_3.png differ diff --git a/docs/output_55_4.png b/docs/output_55_4.png new file mode 100644 index 0000000..57e8811 Binary files /dev/null and b/docs/output_55_4.png differ diff --git a/docs/output_55_5.png b/docs/output_55_5.png new file mode 100644 index 0000000..57e8811 Binary files /dev/null and b/docs/output_55_5.png differ diff --git a/docs/output_55_6.png b/docs/output_55_6.png new file mode 100644 index 0000000..1596132 Binary files /dev/null and b/docs/output_55_6.png differ diff --git a/docs/output_55_7.png b/docs/output_55_7.png new file mode 100644 index 0000000..1596132 Binary files /dev/null and b/docs/output_55_7.png differ diff --git a/docs/output_55_8.png b/docs/output_55_8.png new file mode 100644 index 0000000..b5472f6 Binary files /dev/null and b/docs/output_55_8.png differ diff --git a/docs/output_55_9.png b/docs/output_55_9.png new file mode 100644 index 0000000..b5472f6 Binary files /dev/null and b/docs/output_55_9.png differ diff --git a/docs/output_56_0.png b/docs/output_56_0.png new file mode 100644 index 0000000..193dd2d Binary files /dev/null and b/docs/output_56_0.png differ diff --git a/docs/output_56_1.png b/docs/output_56_1.png new file mode 100644 index 0000000..193dd2d Binary files /dev/null and b/docs/output_56_1.png differ diff --git a/docs/output_56_2.png b/docs/output_56_2.png new file mode 100644 index 0000000..e17e299 Binary files /dev/null and b/docs/output_56_2.png differ diff --git a/docs/output_56_3.png b/docs/output_56_3.png new file mode 100644 index 0000000..e17e299 Binary files /dev/null and b/docs/output_56_3.png differ diff --git a/docs/output_56_4.png b/docs/output_56_4.png new file mode 100644 index 0000000..81d1c91 Binary files /dev/null and b/docs/output_56_4.png differ diff --git a/docs/output_56_5.png b/docs/output_56_5.png new file mode 100644 index 0000000..81d1c91 Binary files /dev/null and b/docs/output_56_5.png differ diff --git a/docs/output_56_6.png b/docs/output_56_6.png new file mode 100644 index 0000000..481775b Binary files /dev/null and b/docs/output_56_6.png differ diff --git a/docs/output_56_7.png b/docs/output_56_7.png new file mode 100644 index 0000000..481775b Binary files /dev/null and b/docs/output_56_7.png differ diff --git a/docs/output_56_8.png b/docs/output_56_8.png new file mode 100644 index 0000000..0c27f83 Binary files /dev/null and b/docs/output_56_8.png differ diff --git a/docs/output_56_9.png b/docs/output_56_9.png new file mode 100644 index 0000000..0c27f83 Binary files /dev/null and b/docs/output_56_9.png differ diff --git a/docs/output_61_0.png b/docs/output_61_0.png new file mode 100644 index 0000000..c94a531 Binary files /dev/null and b/docs/output_61_0.png differ diff --git a/docs/output_63_1.png b/docs/output_63_1.png new file mode 100644 index 0000000..43b9a36 Binary files /dev/null and b/docs/output_63_1.png differ diff --git a/docs/output_66_1.png b/docs/output_66_1.png new file mode 100644 index 0000000..43b9a36 Binary files /dev/null and b/docs/output_66_1.png differ diff --git a/docs/output_67_1.png b/docs/output_67_1.png new file mode 100644 index 0000000..83b7722 Binary files /dev/null and b/docs/output_67_1.png differ diff --git a/docs/output_72_0.png b/docs/output_72_0.png new file mode 100644 index 0000000..21b4f1e Binary files /dev/null and b/docs/output_72_0.png differ diff --git a/docs/output_72_1.png b/docs/output_72_1.png new file mode 100644 index 0000000..21b4f1e Binary files /dev/null and b/docs/output_72_1.png differ diff --git a/docs/output_74_1.png b/docs/output_74_1.png new file mode 100644 index 0000000..1a9312d Binary files /dev/null and b/docs/output_74_1.png differ diff --git a/docs/output_75_1.png b/docs/output_75_1.png new file mode 100644 index 0000000..5c71771 Binary files /dev/null and b/docs/output_75_1.png differ diff --git a/docs/output_76_1.png b/docs/output_76_1.png new file mode 100644 index 0000000..203587f Binary files /dev/null and b/docs/output_76_1.png differ diff --git a/docs/soil_tutorial.rst b/docs/soil_tutorial.rst new file mode 100644 index 0000000..bf85758 --- /dev/null +++ b/docs/soil_tutorial.rst @@ -0,0 +1,2612 @@ + +Soil Tutorial +============= + +Introduction +------------ + +This notebook is an introduction to the soil agent-based social network +simulation framework. In particular, we will focus on a specific use +case: studying the propagation of news in a social network. + +The steps we will follow are: + +- Modelling the behavior of agents +- Running the simulation using different configurations +- Analysing the results of each simulation + +But before that, let's import the soil module and networkx. + +.. code:: ipython3 + + import soil + import networkx as nx + + %load_ext autoreload + %autoreload 2 + + %pylab inline + # To display plots in the notebooed_ + + +.. parsed-literal:: + + Populating the interactive namespace from numpy and matplotlib + + +Basic concepts +-------------- + +There are three main elements in a soil simulation: + +- The network topology. A simulation may use an existing NetworkX + topology, or generate one on the fly +- Agents. There are two types: 1) network agents, which are linked to a + node in the topology, and 2) environment agents, which are freely + assigned to the environment. +- The environment. It assigns agents to nodes in the network, and + stores the environment parameters (shared state for all agents). + +Soil is based on ``simpy``, which is an event-based network simulation +library. Soil provides several abstractions over events to make +developing agents easier. This means you can use events (timeouts, +delays) in soil, but for the most part we will assume your models will +be step-based. + +Modeling behaviour +------------------ + +Our first step will be to model how every person in the social network +reacts when it comes to news. We will follow a very simple model (a +finite state machine). + +There are two types of people, those who have heard about a newsworthy +event (infected) or those who have not (neutral). A neutral person may +heard about the news either on the TV (with probability +**prob\_tv\_spread**) or through their friends. Once a person has heard +the news, they will spread it to their friends (with a probability +**prob\_neighbor\_spread**). Some users do not have a TV, so they only +rely on their friends. + +The spreading probabilities will change over time due to different +factors. We will represent this variance using an environment agent. + +Network Agents +~~~~~~~~~~~~~~ + +A basic network agent in Soil should inherit from +``soil.agents.BaseAgent``, and define its behaviour in every step of the +simulation by implementing a ``run(self)`` method. The most important +attributes of the agent are: + +- ``agent.state``, a dictionary with the state of the agent. + ``agent.state['id']`` reflects the state id of the agent. That state + id can be used to look for other networks in that specific state. The + state can be access via the agent as well. For instance: + + .. code:: py + + a = soil.agents.BaseAgent(env=env) + a['hours_of_sleep'] = 10 + print(a['hours_of_sleep']) + + The state of the agent is stored in every step of the simulation: + ``py print(a['hours_of_sleep', 10]) # hours of sleep before step #10 print(a[None, 0]) # whole state of the agent before step #0`` + +- ``agent.env``, a reference to the environment. Most commonly used to + get access to the environment parameters and the topology: + + .. code:: py + + a.env.G.nodes() # Get all nodes ids in the topology + a.env['minimum_hours_of_sleep'] + +Since our model is a finite state machine, we will be basing it on +``soil.agents.FSM``. + +With ``soil.agents.FSM``, we do not need to specify a ``step`` method. +Instead, we describe every step as a function. To change to another +state, a function may return the new state. If no state is returned, the +state remains unchanged.[ It will consist of two states, ``neutral`` +(default) and ``infected``. + +Here's the code: + +.. code:: ipython3 + + import random + + class NewsSpread(soil.agents.FSM): + @soil.agents.default_state + @soil.agents.state + def neutral(self): + r = random.random() + if self['has_tv'] and r < self.env['prob_tv_spread']: + return self.infected + return + + @soil.agents.state + def infected(self): + prob_infect = self.env['prob_neighbor_spread'] + for neighbor in self.get_neighboring_agents(state_id=self.neutral.id): + r = random.random() + if r < prob_infect: + neighbor.state['id'] = self.infected.id + return + + +Environment agents +~~~~~~~~~~~~~~~~~~ + +Environment agents allow us to control the state of the environment. In +this case, we will use an environment agent to simulate a very viral +event. + +When the event happens, the agent will modify the probability of +spreading the rumor. + +.. code:: ipython3 + + NEIGHBOR_FACTOR = 0.9 + TV_FACTOR = 0.5 + class NewsEnvironmentAgent(soil.agents.BaseAgent): + def step(self): + if self.now == self['event_time']: + self.env['prob_tv_spread'] = 1 + self.env['prob_neighbor_spread'] = 1 + elif self.now > self['event_time']: + self.env['prob_tv_spread'] = self.env['prob_tv_spread'] * TV_FACTOR + self.env['prob_neighbor_spread'] = self.env['prob_neighbor_spread'] * NEIGHBOR_FACTOR + +Testing the agents +~~~~~~~~~~~~~~~~~~ + +Feel free to skip this section if this is your first time with soil. + +Testing agents is not easy, and this is not a thorough testing process +for agents. Rather, this section is aimed to show you how to access +internal pats of soil so you can test your agents. + +First of all, let's check if our network agent has the states we would +expect: + +.. code:: ipython3 + + NewsSpread.states + + + + +.. parsed-literal:: + + {'infected': , + 'neutral': } + + + +Now, let's run a simulation on a simple network. It is comprised of +three nodes: + +.. code:: ipython3 + + G = nx.Graph() + G.add_edge(0, 1) + G.add_edge(0, 2) + G.add_edge(2, 3) + G.add_node(4) + pos = nx.spring_layout(G) + nx.draw_networkx(G, pos, node_color='red') + nx.draw_networkx(G, pos, nodelist=[0], node_color='blue') + + + +.. image:: output_21_0.png + + +Let's run a simple simulation that assigns a NewsSpread agent to all the +nodes in that network. Notice how node 0 is the only one with a TV. + +.. code:: ipython3 + + env_params = {'prob_tv_spread': 0, + 'prob_neighbor_spread': 0} + + MAX_TIME = 100 + EVENT_TIME = 10 + + sim = soil.simulation.SoilSimulation(topology=G, + num_trials=1, + max_time=MAX_TIME, + environment_agents=[{'agent_type': NewsEnvironmentAgent, + 'state': { + 'event_time': EVENT_TIME + }}], + network_agents=[{'agent_type': NewsSpread, + 'weight': 1}], + states={0: {'has_tv': True}}, + default_state={'has_tv': False}, + environment_params=env_params) + env = sim.run_simulation()[0] + + +.. parsed-literal:: + + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.02695441246032715 seconds + INFO:soil.utils:NOT dumping results + INFO:soil.utils:Finished simulation in 0.03360605239868164 seconds + + +Now we can access the results of the simulation and compare them to our +expected results + +.. code:: ipython3 + + agents = list(env.network_agents) + + # Until the event, all agents are neutral + for t in range(10): + for a in agents: + assert a['id', t] == a.neutral.id + + # After the event, the node with a TV is infected, the rest are not + assert agents[0]['id', 11] == NewsSpread.infected.id + + for a in agents[1:4]: + assert a['id', 11] == NewsSpread.neutral.id + + # At the end, the agents connected to the infected one will probably be infected, too. + assert agents[1]['id', MAX_TIME] == NewsSpread.infected.id + assert agents[2]['id', MAX_TIME] == NewsSpread.infected.id + + # But the node with no friends should not be affected + assert agents[4]['id', MAX_TIME] == NewsSpread.neutral.id + + +Lastly, let's see if the probabilities have decreased as expected: + +.. code:: ipython3 + + assert abs(env.environment_params['prob_neighbor_spread'] - (NEIGHBOR_FACTOR**(MAX_TIME-1-10))) < 10e-4 + assert abs(env.environment_params['prob_tv_spread'] - (TV_FACTOR**(MAX_TIME-1-10))) < 10e-6 + +Running the simulation +---------------------- + +To run a simulation, we need a configuration. Soil can load +configurations from python dictionaries as well as JSON and YAML files. +For this demo, we will use a python dictionary: + +.. code:: ipython3 + + config = { + 'name': 'ExampleSimulation', + 'max_time': 20, + 'interval': 1, + 'num_trials': 1, + 'network_params': { + 'generator': 'complete_graph', + 'n': 500, + }, + 'network_agents': [ + { + 'agent_type': NewsSpread, + 'weight': 1, + 'state': { + 'has_tv': False + } + }, + { + 'agent_type': NewsSpread, + 'weight': 2, + 'state': { + 'has_tv': True + } + } + ], + 'environment_agents':[ + {'agent_type': NewsEnvironmentAgent, + 'state': { + 'event_time': 10 + } + } + ], + 'states': [ {'has_tv': True} ], + 'environment_params':{ + 'prob_tv_spread': 0.01, + 'prob_neighbor_spread': 0.5 + } + } + +Let's run our simulation: + +.. code:: ipython3 + + soil.simulation.run_from_config(config, dump=False) + + +.. parsed-literal:: + + INFO:soil.utils:Using config(s): ExampleSimulation + INFO:soil.utils:Dumping results to soil_output/ExampleSimulation : False + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 5.869051456451416 seconds + INFO:soil.utils:NOT dumping results + INFO:soil.utils:Finished simulation in 6.9609293937683105 seconds + + +In real life, you probably want to run several simulations, varying some +of the parameters so that you can compare and answer your research +questions. + +For instance: + +- Does the outcome depend on the structure of our network? We will use + different generation algorithms to compare them (Barabasi-Albert and + Erdos-Renyi) +- How does neighbor spreading probability affect my simulation? We will + try probability values in the range of [0, 0.4], in intervals of 0.1. + +.. code:: ipython3 + + network_1 = { + 'generator': 'erdos_renyi_graph', + 'n': 500, + 'p': 0.1 + } + network_2 = { + 'generator': 'barabasi_albert_graph', + 'n': 500, + 'm': 2 + } + + + for net in [network_1, network_2]: + for i in range(5): + prob = i / 10 + config['environment_params']['prob_neighbor_spread'] = prob + config['network_params'] = net + config['name'] = 'Spread_{}_prob_{}'.format(net['generator'], prob) + s = soil.simulation.run_from_config(config) + + +.. parsed-literal:: + + INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.0 + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 1.2258412837982178 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0 + INFO:soil.utils:Finished simulation in 5.597268104553223 seconds + INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.1 + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 1.3026399612426758 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1 + INFO:soil.utils:Finished simulation in 5.534018278121948 seconds + INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.2 + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 1.4764575958251953 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2 + INFO:soil.utils:Finished simulation in 6.170421123504639 seconds + INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.3 + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 1.5429913997650146 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3 + INFO:soil.utils:Finished simulation in 5.936013221740723 seconds + INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.4 + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 1.4097135066986084 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4 + INFO:soil.utils:Finished simulation in 5.732810974121094 seconds + INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.0 + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.751497745513916 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0 + INFO:soil.utils:Finished simulation in 2.3415369987487793 seconds + INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.1 + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.8503265380859375 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1 + INFO:soil.utils:Finished simulation in 2.5671920776367188 seconds + INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.2 + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.8511502742767334 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2 + INFO:soil.utils:Finished simulation in 2.55816912651062 seconds + INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.3 + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.8982968330383301 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3 + INFO:soil.utils:Finished simulation in 2.6871559619903564 seconds + INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.4 + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4 : True + INFO:soil.utils:Trial: 0 + INFO:soil.utils: Running + INFO:soil.utils:Finished trial in 0.9563727378845215 seconds + INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4 + INFO:soil.utils:Finished simulation in 2.5253307819366455 seconds + + +The results are conveniently stored in pickle (simulation), csv and +sqlite (history of agent and environment state) and gexf (dynamic +network) format. + +.. code:: ipython3 + + !tree soil_output + !du -xh soil_output/* + + +.. parsed-literal:: + + soil_output + ├── Spread_barabasi_albert_graph_prob_0.0 + │   ├── Spread_barabasi_albert_graph_prob_0.0.dumped.yml + │   ├── Spread_barabasi_albert_graph_prob_0.0.simulation.pickle + │   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508409808.7944386.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508428617.9811945.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv + │   └── Spread_barabasi_albert_graph_prob_0.0_trial_0.gexf + ├── Spread_barabasi_albert_graph_prob_0.1 + │   ├── Spread_barabasi_albert_graph_prob_0.1.dumped.yml + │   ├── Spread_barabasi_albert_graph_prob_0.1.simulation.pickle + │   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508409810.9913027.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508428620.3419535.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.db.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.environment.csv + │   └── Spread_barabasi_albert_graph_prob_0.1_trial_0.gexf + ├── Spread_barabasi_albert_graph_prob_0.2 + │   ├── Spread_barabasi_albert_graph_prob_0.2.dumped.yml + │   ├── Spread_barabasi_albert_graph_prob_0.2.simulation.pickle + │   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508409813.2012305.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508428622.91827.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.db.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.environment.csv + │   └── Spread_barabasi_albert_graph_prob_0.2_trial_0.gexf + ├── Spread_barabasi_albert_graph_prob_0.3 + │   ├── Spread_barabasi_albert_graph_prob_0.3.dumped.yml + │   ├── Spread_barabasi_albert_graph_prob_0.3.simulation.pickle + │   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508409815.5177016.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508428625.5117545.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.db.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.environment.csv + │   └── Spread_barabasi_albert_graph_prob_0.3_trial_0.gexf + ├── Spread_barabasi_albert_graph_prob_0.4 + │   ├── Spread_barabasi_albert_graph_prob_0.4.dumped.yml + │   ├── Spread_barabasi_albert_graph_prob_0.4.simulation.pickle + │   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508409818.1516452.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508428628.1986933.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.db.sqlite + │   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.environment.csv + │   └── Spread_barabasi_albert_graph_prob_0.4_trial_0.gexf + ├── Spread_erdos_renyi_graph_prob_0.0 + │   ├── Spread_erdos_renyi_graph_prob_0.0.dumped.yml + │   ├── Spread_erdos_renyi_graph_prob_0.0.simulation.pickle + │   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508409781.0791047.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508428588.625598.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.db.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.environment.csv + │   └── Spread_erdos_renyi_graph_prob_0.0_trial_0.gexf + ├── Spread_erdos_renyi_graph_prob_0.1 + │   ├── Spread_erdos_renyi_graph_prob_0.1.dumped.yml + │   ├── Spread_erdos_renyi_graph_prob_0.1.simulation.pickle + │   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508409786.6177793.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508428594.3783743.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.db.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.environment.csv + │   └── Spread_erdos_renyi_graph_prob_0.1_trial_0.gexf + ├── Spread_erdos_renyi_graph_prob_0.2 + │   ├── Spread_erdos_renyi_graph_prob_0.2.dumped.yml + │   ├── Spread_erdos_renyi_graph_prob_0.2.simulation.pickle + │   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508409791.9751768.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508428600.041021.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.db.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.environment.csv + │   └── Spread_erdos_renyi_graph_prob_0.2_trial_0.gexf + ├── Spread_erdos_renyi_graph_prob_0.3 + │   ├── Spread_erdos_renyi_graph_prob_0.3.dumped.yml + │   ├── Spread_erdos_renyi_graph_prob_0.3.simulation.pickle + │   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508409797.606661.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508428606.2884977.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.db.sqlite + │   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.environment.csv + │   └── Spread_erdos_renyi_graph_prob_0.3_trial_0.gexf + └── Spread_erdos_renyi_graph_prob_0.4 + ├── Spread_erdos_renyi_graph_prob_0.4.dumped.yml + ├── Spread_erdos_renyi_graph_prob_0.4.simulation.pickle + ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508409803.4306188.sqlite + ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508428612.3312593.sqlite + ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.db.sqlite + ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.environment.csv + └── Spread_erdos_renyi_graph_prob_0.4_trial_0.gexf + + 10 directories, 70 files + 2.5M soil_output/Spread_barabasi_albert_graph_prob_0.0 + 2.5M soil_output/Spread_barabasi_albert_graph_prob_0.1 + 2.5M soil_output/Spread_barabasi_albert_graph_prob_0.2 + 2.5M soil_output/Spread_barabasi_albert_graph_prob_0.3 + 2.5M soil_output/Spread_barabasi_albert_graph_prob_0.4 + 3.6M soil_output/Spread_erdos_renyi_graph_prob_0.0 + 3.7M soil_output/Spread_erdos_renyi_graph_prob_0.1 + 3.7M soil_output/Spread_erdos_renyi_graph_prob_0.2 + 3.7M soil_output/Spread_erdos_renyi_graph_prob_0.3 + 3.7M soil_output/Spread_erdos_renyi_graph_prob_0.4 + + +Analysing the results +--------------------- + +Loading data +~~~~~~~~~~~~ + +Once the simulations are over, we can use soil to analyse the results. + +Soil allows you to load results for specific trials, or for a set of +trials if you specify a pattern. The specific methods are: + +- ``analysis.read_data()`` to load all the results + from a directory. e.g. ``read_data('my_simulation/')``. For each + trial it finds in each folder matching the pattern, it will return + the dumped configuration for the simulation, the results of the + trial, and the configuration itself. By default, it will try to load + data from the sqlite database. +- ``analysis.read_csv()`` to load all the results from a CSV + file. e.g. + ``read_csv('my_simulation/my_simulation_trial0.environment.csv')`` +- ``analysis.read_sql()`` to load all the results from a + sqlite database . e.g. + ``read_sql('my_simulation/my_simulation_trial0.db.sqlite')`` + +Let's see it in action by loading the stored results into a pandas +dataframe: + +.. code:: ipython3 + + from soil.analysis import * + +.. code:: ipython3 + + df = read_csv('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv', keys=['id']) + df + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
agent_idt_stepkeyvaluevalue_type
500idneutralstr
710idneutralstr
920idneutralstr
1130idneutralstr
1340idneutralstr
1550idneutralstr
1760idneutralstr
1970idneutralstr
2180idneutralstr
2390idneutralstr
25100idneutralstr
27110idneutralstr
29120idneutralstr
31130idneutralstr
33140idneutralstr
35150idneutralstr
37160idneutralstr
39170idneutralstr
41180idneutralstr
43190idneutralstr
45200idneutralstr
47210idneutralstr
49220idneutralstr
51230idneutralstr
53240idneutralstr
55250idneutralstr
57260idneutralstr
59270idneutralstr
61280idneutralstr
63290idneutralstr
..................
2102547020idinfectedstr
2102747120idinfectedstr
2102947220idinfectedstr
2103147320idinfectedstr
2103347420idinfectedstr
2103547520idinfectedstr
2103747620idinfectedstr
2103947720idinfectedstr
2104147820idinfectedstr
2104347920idinfectedstr
2104548020idinfectedstr
2104748120idinfectedstr
2104948220idinfectedstr
2105148320idinfectedstr
2105348420idinfectedstr
2105548520idinfectedstr
2105748620idinfectedstr
2105948720idinfectedstr
2106148820idinfectedstr
2106348920idinfectedstr
2106549020idinfectedstr
2106749120idinfectedstr
2106949220idinfectedstr
2107149320idinfectedstr
2107349420idinfectedstr
2107549520idinfectedstr
2107749620idinfectedstr
2107949720idinfectedstr
2108149820idinfectedstr
2108349920idinfectedstr
+

10500 rows × 5 columns

+
+ + + +Soil can also process the data for us and return a dataframe with as +many columns as there are attributes in the environment and the agent +states: + +.. code:: ipython3 + + env, agents = process(df) + agents + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
t_stepagent_id
00neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
.........
2072infected
73infected
74infected
75infected
76infected
77infected
78infected
79infected
8infected
80infected
81infected
82infected
83infected
84infected
85infected
86infected
87infected
88infected
89infected
9infected
90infected
91infected
92infected
93infected
94infected
95infected
96infected
97infected
98infected
99infected
+

10500 rows × 1 columns

+
+ + + +The index of the results are the simulation step and the agent\_id. +Hence, we can access the state of the simulation at a given step: + +.. code:: ipython3 + + agents.loc[0] + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
agent_id
0neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
......
72neutral
73neutral
74neutral
75neutral
76neutral
77neutral
78neutral
79neutral
8neutral
80neutral
81neutral
82neutral
83neutral
84neutral
85neutral
86neutral
87neutral
88neutral
89neutral
9neutral
90neutral
91neutral
92neutral
93neutral
94neutral
95neutral
96neutral
97neutral
98neutral
99neutral
+

500 rows × 1 columns

+
+ + + +Or, we can perform more complex tasks such as showing the agents that +have changed their state between two simulation steps: + +.. code:: ipython3 + + changed = agents.loc[1]['id'] != agents.loc[0]['id'] + agents.loc[0][changed] + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
agent_id
140neutral
164neutral
170neutral
310neutral
455neutral
+
+ + + +To focus on specific agents, we can swap the levels of the index: + +.. code:: ipython3 + + agents1 = agents.swaplevel() + +.. code:: ipython3 + + agents1.loc['0'].dropna(axis=1) + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
t_step
0neutral
1neutral
2neutral
3neutral
4neutral
5neutral
6neutral
7neutral
8neutral
9neutral
10neutral
11infected
12infected
13infected
14infected
15infected
16infected
17infected
18infected
19infected
20infected
+
+ + + +Plotting data +~~~~~~~~~~~~~ + +If you don't want to work with pandas, you can also use some pre-defined +functions from soil to conveniently plot the results: + +.. code:: ipython3 + + plot_all('soil_output/Spread_barabasi_albert_graph_prob_0.0/', get_count, 'id'); + + + +.. image:: output_54_0.png + + + +.. image:: output_54_1.png + + +.. code:: ipython3 + + plot_all('soil_output/Spread_barabasi*', get_count, 'id'); + + + +.. image:: output_55_0.png + + + +.. image:: output_55_1.png + + + +.. image:: output_55_2.png + + + +.. image:: output_55_3.png + + + +.. image:: output_55_4.png + + + +.. image:: output_55_5.png + + + +.. image:: output_55_6.png + + + +.. image:: output_55_7.png + + + +.. image:: output_55_8.png + + + +.. image:: output_55_9.png + + +.. code:: ipython3 + + plot_all('soil_output/Spread_erdos*', get_value, 'prob_tv_spread'); + + + +.. image:: output_56_0.png + + + +.. image:: output_56_1.png + + + +.. image:: output_56_2.png + + + +.. image:: output_56_3.png + + + +.. image:: output_56_4.png + + + +.. image:: output_56_5.png + + + +.. image:: output_56_6.png + + + +.. image:: output_56_7.png + + + +.. image:: output_56_8.png + + + +.. image:: output_56_9.png + + +Manually plotting with pandas +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Although the simplest way to visualize the results of a simulation is to +use the built-in methods in the analysis module, sometimes the setup is +more complicated and we need to explore the data a little further. + +For that, we can use native pandas over the results. + +Soil provides some convenience methods to simplify common operations: + +- ``analysis.split_df`` to separate a history dataframe into + environment and agent parameters. +- ``analysis.get_count`` to get a dataframe with the value counts for + different attributes during the simulation. +- ``analysis.get_value`` to get the evolution of the value of an + attribute during the simulation. + +And, as we saw earlier, ``analysis.process`` can turn a dataframe in +canonical form into a dataframe with a column per attribute. + +.. code:: ipython3 + + p = read_sql('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite') + env, agents = split_df(p); + +Let's look at the evolution of agent parameters in the simulation + +.. code:: ipython3 + + res = agents.groupby(by=['t_step', 'key', 'value']).size().unstack(level=[1,2]).fillna(0) + res.plot(); + + + +.. image:: output_61_0.png + + +As we can see, ``event_time`` is cluttering our results, + +.. code:: ipython3 + + del res['event_time'] + res.plot() + + + + +.. parsed-literal:: + + + + + + +.. image:: output_63_1.png + + +.. code:: ipython3 + + processed = process_one(agents); + processed + + + + +.. raw:: html + +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
event_timehas_tvid
t_stepagent_id
000Trueneutral
10Falseneutral
100Trueneutral
1000Trueneutral
1010Trueneutral
1020Falseneutral
1030Trueneutral
1040Trueneutral
1050Falseneutral
1060Falseneutral
1070Trueneutral
1080Trueneutral
1090Falseneutral
110Trueneutral
1100Falseneutral
1110Falseneutral
1120Trueneutral
1130Trueneutral
1140Trueneutral
1150Trueneutral
1160Falseneutral
1170Trueneutral
1180Trueneutral
1190Falseneutral
120Falseneutral
1200Falseneutral
1210Trueneutral
1220Trueneutral
1230Trueneutral
1240Falseneutral
...............
20730Trueinfected
740Trueinfected
750Trueinfected
760Trueinfected
770Trueinfected
780Trueinfected
790Falseinfected
80Falseinfected
800Trueinfected
810Falseinfected
820Falseinfected
830Trueinfected
840Falseinfected
850Trueinfected
860Trueinfected
870Trueinfected
880Falseinfected
890Falseinfected
90Trueinfected
900Trueinfected
910Trueinfected
920Trueinfected
930Falseinfected
940Trueinfected
950Trueinfected
960Trueinfected
970Trueinfected
980Falseinfected
990Trueinfected
NewsEnvironmentAgent10False0
+

10521 rows × 3 columns

+
+ + + +Which is equivalent to: + +.. code:: ipython3 + + get_count(agents, 'id', 'has_tv').plot() + + + + +.. parsed-literal:: + + + + + + +.. image:: output_66_1.png + + +.. code:: ipython3 + + get_value(agents, 'event_time').plot() + + + + +.. parsed-literal:: + + + + + + +.. image:: output_67_1.png + + +Dealing with bigger data +------------------------ + +.. code:: ipython3 + + from soil import analysis + +.. code:: ipython3 + + !du -xsh ../rabbits/soil_output/rabbits_example/ + + +.. parsed-literal:: + + 267M ../rabbits/soil_output/rabbits_example/ + + +If we tried to load the entire history, we would probably run out of +memory. Hence, it is recommended that you also specify the attributes +you are interested in. + +.. code:: ipython3 + + p = analysis.plot_all('../rabbits/soil_output/rabbits_example/', analysis.get_count, 'id') + + + +.. image:: output_72_0.png + + + +.. image:: output_72_1.png + + +.. code:: ipython3 + + df = analysis.read_sql('../rabbits/soil_output/rabbits_example/rabbits_example_trial_0.db.sqlite', keys=['id', 'rabbits_alive']) + +.. code:: ipython3 + + states = analysis.get_count(df, 'id') + states.plot() + + + + +.. parsed-literal:: + + + + + + +.. image:: output_74_1.png + + +.. code:: ipython3 + + alive = analysis.get_value(df, 'rabbits_alive', 'rabbits_alive', aggfunc='sum').apply(pd.to_numeric) + alive.plot() + + + + +.. parsed-literal:: + + + + + + +.. image:: output_75_1.png + + +.. code:: ipython3 + + h = alive.join(states); + h.plot(); + + +.. parsed-literal:: + + /home/jfernando/.local/lib/python3.6/site-packages/pandas/core/reshape/merge.py:551: UserWarning: merging between different levels can give an unintended result (1 levels on the left, 2 on the right) + warnings.warn(msg, UserWarning) + + + +.. image:: output_76_1.png + + +.. code:: ipython3 + + states[[('id','newborn'),('id','fertile'),('id', 'pregnant')]].sum(axis=1).sub(alive['rabbits_alive'], fill_value=0) diff --git a/examples/custom-agents/UnnamedSimulation.dumped.yml b/examples/custom-agents/UnnamedSimulation.dumped.yml deleted file mode 100644 index 34c5534..0000000 --- a/examples/custom-agents/UnnamedSimulation.dumped.yml +++ /dev/null @@ -1,17 +0,0 @@ -default_state: {} -environment_agents: [] -environment_params: {prob_neighbor_spread: 0.0, prob_tv_spread: 0.01} -interval: 1 -max_time: 20 -name: Sim_prob_0 -network_agents: -- agent_type: NewsSpread - state: {has_tv: false} - weight: 1 -- agent_type: NewsSpread - state: {has_tv: true} - weight: 2 -network_params: {generator: erdos_renyi_graph, n: 500, p: 0.1} -num_trials: 1 -states: -- {has_tv: true} diff --git a/examples/custom-agents/agent.py b/examples/custom-agents/agent.py deleted file mode 100644 index 0f4d8a4..0000000 --- a/examples/custom-agents/agent.py +++ /dev/null @@ -1,20 +0,0 @@ -import soil -import random - -class NewsSpread(soil.agents.FSM): - @soil.agents.default_state - @soil.agents.state - def neutral(self): - r = random.random() - if self['has_tv'] and r < self.env['prob_tv_spread']: - return self.infected - return - - @soil.agents.state - def infected(self): - prob_infect = self.env['prob_neighbor_spread'] - for neighbor in self.get_neighboring_agents(state_id=self.neutral.id): - r = random.random() - if r < prob_infect: - neighbor.state['id'] = self.infected.id - return diff --git a/examples/newsspread/NewsSpread.ipynb b/examples/newsspread/NewsSpread.ipynb new file mode 100644 index 0000000..5f2a6b3 --- /dev/null +++ b/examples/newsspread/NewsSpread.ipynb @@ -0,0 +1,460 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:01.378353Z", + "start_time": "2017-10-19T17:54:00.685043+02:00" + }, + "scrolled": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Populating the interactive namespace from numpy and matplotlib\n" + ] + } + ], + "source": [ + "import soil\n", + "import networkx as nx\n", + " \n", + "%load_ext autoreload\n", + "%autoreload 2\n", + "\n", + "# To display plots in the notebook\n", + "%pylab inline\n", + "\n", + "from soil import *" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# News Spreading example with SOIL" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "In this example we three different kinds of models, which we combine in five types of simulation" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:02.678166Z", + "start_time": "2017-10-19T17:54:02.508949+02:00" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "---\r\n", + "default_state: {}\r\n", + "load_module: newsspread\r\n", + "environment_agents: []\r\n", + "environment_params:\r\n", + " prob_neighbor_spread: 0.0\r\n", + " prob_tv_spread: 0.01\r\n", + "interval: 1\r\n", + "max_time: 30\r\n", + "name: Sim_all_dumb\r\n", + "network_agents:\r\n", + "- agent_type: DumbViewer\r\n", + " state:\r\n", + " has_tv: false\r\n", + " weight: 1\r\n", + "- agent_type: DumbViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " weight: 1\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "num_trials: 50\r\n", + "---\r\n", + "default_state: {}\r\n", + "load_module: newsspread\r\n", + "environment_agents: []\r\n", + "environment_params:\r\n", + " prob_neighbor_spread: 0.0\r\n", + " prob_tv_spread: 0.01\r\n", + "interval: 1\r\n", + "max_time: 30\r\n", + "name: Sim_half_herd\r\n", + "network_agents:\r\n", + "- agent_type: DumbViewer\r\n", + " state:\r\n", + " has_tv: false\r\n", + " weight: 1\r\n", + "- agent_type: DumbViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " weight: 1\r\n", + "- agent_type: HerdViewer\r\n", + " state:\r\n", + " has_tv: false\r\n", + " weight: 1\r\n", + "- agent_type: HerdViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " weight: 1\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "num_trials: 50\r\n", + "---\r\n", + "default_state: {}\r\n", + "load_module: newsspread\r\n", + "environment_agents: []\r\n", + "environment_params:\r\n", + " prob_neighbor_spread: 0.0\r\n", + " prob_tv_spread: 0.01\r\n", + "interval: 1\r\n", + "max_time: 30\r\n", + "name: Sim_all_herd\r\n", + "network_agents:\r\n", + "- agent_type: HerdViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " id: infected\r\n", + " weight: 1\r\n", + "- agent_type: HerdViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " id: neutral\r\n", + " weight: 1\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "num_trials: 50\r\n", + "---\r\n", + "default_state: {}\r\n", + "load_module: newsspread\r\n", + "environment_agents: []\r\n", + "environment_params:\r\n", + " prob_neighbor_spread: 0.0\r\n", + " prob_tv_spread: 0.01\r\n", + " prob_neighbor_cure: 0.1\r\n", + "interval: 1\r\n", + "max_time: 30\r\n", + "name: Sim_wise_herd\r\n", + "network_agents:\r\n", + "- agent_type: HerdViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " id: infected\r\n", + " weight: 1\r\n", + "- agent_type: WiseViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " weight: 1\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "num_trials: 50\r\n", + "---\r\n", + "default_state: {}\r\n", + "load_module: newsspread\r\n", + "environment_agents: []\r\n", + "environment_params:\r\n", + " prob_neighbor_spread: 0.0\r\n", + " prob_tv_spread: 0.01\r\n", + " prob_neighbor_cure: 0.1\r\n", + "interval: 1\r\n", + "max_time: 30\r\n", + "name: Sim_all_wise\r\n", + "network_agents:\r\n", + "- agent_type: WiseViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " id: infected\r\n", + " weight: 1\r\n", + "- agent_type: WiseViewer\r\n", + " state:\r\n", + " has_tv: true\r\n", + " weight: 1\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "network_params:\r\n", + " generator: barabasi_albert_graph\r\n", + " n: 500\r\n", + " m: 5\r\n", + "num_trials: 50\r\n" + ] + } + ], + "source": [ + "!cat NewsSpread.yml" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:07.617556Z", + "start_time": "2017-10-19T17:54:03.481983+02:00" + } + }, + "outputs": [], + "source": [ + "evodumb = analysis.read_data('soil_output/Sim_all_dumb/', group=True, process=analysis.get_count, keys=['id']);" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:07.832237Z", + "start_time": "2017-10-19T17:54:07.620220+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "evodumb['mean'].plot(yerr=evodumb['std'])" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:28.017296Z", + "start_time": "2017-10-19T17:54:07.834047+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "evodumb = analysis.read_data('soil_output/Sim_all_dumb/', group=True, process=analysis.get_count, keys=['id']);\n", + "evohalfherd = analysis.read_data('soil_output/Sim_half_herd/', group=True, process=analysis.get_count, keys=['id'])\n", + "evoherd = analysis.read_data('soil_output/Sim_all_herd/', group=True, process=analysis.get_count, keys=['id'])\n", + "evoherdwise = analysis.read_data('soil_output/Sim_wise_herd/', group=True, process=analysis.get_count, keys=['id'])\n", + "evowise = analysis.read_data('soil_output/Sim_all_wise//', group=True, process=analysis.get_count, keys=['id'])" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:28.963822Z", + "start_time": "2017-10-19T17:54:28.020292+02:00" + } + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nocXJrmBn1wAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xt0VPW5//H3QwgXBUQNVAQ0YNEjlBgUqTeUqsBBrdZL\nFS9cRIVSEFS0RT1H0aPowrv1HK0UqrbwQwW0avWIViylesAkhpsUQUULRG5WINxMwvP7YzbjkEyY\nyY2ZZH9ea2Uxs/ez9zybWXyy+c6e7zZ3R0REwqFRqhsQEZEDR6EvIhIiCn0RkRBR6IuIhIhCX0Qk\nRBT6IiIhotAXEQmRhKFvZh3NbK6ZLTezZWY2NmbdjWa2Ilg+KViWbWY7zaww+HmmLg9ARESS1ziJ\nmlJgnLsXmFlLIN/M3gF+AFwE5Lj7bjNrG7PNZ+6eWwf9iohIDSQMfXcvAoqCx9vMbDnQHrgBeNDd\ndwfrNlS3iaysLM/Ozq7u5iIioZSfn7/J3dtUZZtkzvSjzCwb6AEsAB4CepvZ/cAu4FZ3/ygo7WRm\nHwNbgf9w97/tb7/Z2dnk5eVVpRURkdAzsy+ruk3SoW9mLYBZwE3uvtXMGgOHAqcAJwMvmVlnIv8r\nOMrdN5vZScCrZtbN3beW299wYDjAUUcdVdW+RUSkGpK6esfMMokE/jR3nx0sXgPM9oiFwB4gy913\nu/tmAHfPBz4Dji2/T3d/1t17unvPNm2q9L8TERGppmSu3jFgCrDc3R+NWfUqcHZQcyzQBNhkZm3M\nLCNY3hnoAnxe242LiEjVJTO8czowCFhiZoXBsjuAqcBUM1sKfAcMcXc3szOBe82sFCgDfuHu39RB\n7yJSh0pKSlizZg27du1KdSuh16xZMzp06EBmZmaN95XM1TvzAatk9TVx6mcRGQoSkXpszZo1tGzZ\nkuzsbCL/4ZdUcHc2b97MmjVr6NSpU433p2/kikhcu3bt4vDDD1fgp5iZcfjhh9fa/7gU+iJSKQV+\neqjN90GhLyISImkR+p9v3J5U3RW//ZArfvth0vutSn1Drk2XPtKhNl36SIfaqtZ/trGYzzYW10qt\nmTFu3Lho7e0T7mfChAl12kN2djaXXnpp9PnMmTMZOnRolfdb0z5qq7Yq73OstAh9EQmXpk2bMnv2\nbDZt2nRAXzcvL49ly5Yd0NdMNwp9ETngGjduzPDhw3nssccqrPvyyy8555xzyMnJ4ZxzzuGrr74C\nYOjQodx7x238/Lxz6Ny5MzNnzoxu89BDD3HyySeTk5PD3XffXenr3nrrrUycOLHC8m//9Q2/GDyQ\nnJwcTjnlFBYvXgzAhAkTGDZsGH369KFz5848+eST0W1efXkGvXr1Ijc3lxEjRlBWVlbtv48DSaEv\nIikxatQopk2bxratW/ZZPnr0aAYPHszixYu5+uqrGTNmTHTdhvVf8+Ib7/DGG28wfvx4AObMmcPK\nlStZuHAhhYWF5OfnM2/evLivefnll1NQUMCqVav2Wf7EpIl07X4CixcvZuLEiQwePDi67h//+Adv\nv/02Cxcu5J577qGkpIRVn/6DP/9pFn//+98pLCwkIyODadOm1dZfTZ2q0oRrIiK1pVWrVgwePJjn\nJz9Ds2bNoss//PBDZs+OzPYyaNAgfvWrX0XX9R1wAY0aNaJr166sX78eiIT+nDlz6NGjBwDFxcWs\nXLmS9sefWOE1MzIyuO2223jggQcYMGBAdHnegg/576l/BODss89m8+bNbNkS+WV0/vnn07RpU5o2\nbUrbtm1Zv349H/ztryxbVMjJJ58MwM6dO2nbtm2F10tHCn0RSZmbbrqJnNweXDrwGpoeFP/bprGX\nKzZp2jT62N2jf95+++2MGDFin+0q+0B00KBBPPDAA3Tr1u37hcG+4r1u05jXzMjIoLS0FNy5+Iqr\neOaJRxIcYfrR8I6IpMxhhx3GeRdezMvTX4guO+2005gxYwYA06ZN44wzztjvPvr378/UqVMpLo6E\n/Nq1a9mwIXJ7j0GXXsDatWv3qc/MzOTmm2/m8ccfjy47+dTTeW3WSwC8//77ZGVl0apVq0pf89Te\nffjf1/8UfZ1vvvmGL7+s8izHKaHQF5GUum7kGP71zebo8yeffJLf//735OTk8Ic//IEnnnhiv9v3\n69ePq666ilNPPZXu3btz2WWXsW3bNvbs2cOXX3zOYYcdVvE1r7sucsYeGHPb7SxZVEBOTg7jx4/n\n+eef3+9rdjnu37jl9v+kX79+5OTk0LdvX4qKiqp45Kmh4R0ROeD2npUDZLVty9IvN3BMmxZA5Hr6\n9957r8I2zz333D5DNrH7GDt2LGPHjt2n/q15C+l//oU0b94cgNWrV0fXNW3alHXr1kWftz70MH77\nwovRHvYq/92BpUuXApGho/N/diljbhiSzOGmFZ3pi0iDdOzxXbnzvx5MdRtpR6EvIhIiCn0RkRBR\n6IuIhIhCX0QkRBT6IiIhotAXkbS1c+dOzjrrLMrKyli3bh2jhlW4QysAffr0IS8vb7/7uuuuu3j3\n3Xf3W7N7927OPfdccnNzefHFF6vU6+rVq5k+fXqVtoHIRHJ7J48bO3woqz9flWCLmlHoi0jamjp1\nKpdccgkZGRkceeSR0flxquPee+/l3HPP3W/Nxx9/TElJCYWFhVxxxRVV2n91Qz/WVUOv59mnHk9c\nWAP6cpaIJHTP68so+PJfADTLzEhYv6ukLGFt1yNbcfdPu1W6HiLTMOwN0tWrVzNgwHm8NW8hO3fu\n5Nprr+WTTz7h+OOPZ+fOnQl7Gjp0KBdccAGXXXYZ2dnZDBkyhNdff52SkhIe+e1ztG59GNdccw0b\nN24kNzeXWbNm8e2333LLLbdQXFxMVlYWzz33HO3atWP1559x1203UbzlGzIyMnj55ZcZP348y5cv\nJzc3lyFDhjBmzBjGjx/P2+++x3e7d3Pz2BsZMWIE7s6NN97Ie++9R6dOnaJzCAGcfMpp/HrMLygt\nLaVx47qJZ53pi0ha+u677/j888/Jzs6usO7pp5/moIMOYvHixdx5553k5+dXef9ZWVkUFBQwcuRI\nfvc/T3J4mzb87ne/o3fv3hQWFnLUUUdx4403MnPmTPLz8xk2bBh33nknAON+eT3XDLuBRYsW8cEH\nH9CuXTsefPDB6LY333wzU6ZM4ZBDDuGVOX9l9py/MnnyZL744gteeeUVVqxYwZIlS5g8eTIffPBB\ntKdGjRpxdHZnFi1aVO2/t0R0pi8iCd39027RKRDKT1UQT1VqK7Np0yZat24dd928efOi8+zn5OSQ\nk5NT5f1fcsklAJx00klMm/FyhfUrVqxg6dKl9O3bF4CysjLatWvHtm3b+LpoHf3OvxBgn2mhY82Z\nM4fFixczfUZkIred27excuVK5s2bx5VXXhkdsjr77LP32e7wrDasW7eOk046qcrHlAyFvoikpebN\nm7Nr165K18dOuVwde6dMzsjIoLSstMJ6d6dbt258+OG+96LdunVrUvt3d37zm9/wwxNPB77/Bfjm\nm2/ut/fdu3dF5wuqCxreEZG0dOihh1JWVhY3+M8888zonaqWLl0avb0hwODBg1m4cGGNX/+4445j\n48aN0dAvKSlh2bJltGrViiOOPJJ33nwdiFzxs2PHDlq2bMm2bdui2/fv35+nn36akpISAD799FO2\nb9/OmWeeyYwZMygrK6OoqIi5c+fu87pffL5q37n+a5lCX0TSVr9+/Zg/f36F5SNHjqS4uJicnBwm\nTZpEr169ousWL15Mu3btavzaTZo0YebMmfz617/mhBNOIDc3Nzr+/sh/T+b53z1DTk4Op512Gl9/\n/TU5OTk0btyYE044gccee4zrr7+erl27ctG5ZzDgzF6MGDGC0tJSLr74Yrp06UL37t0ZOXIkZ511\nVvQ1N23YQLNmzWul/8poeEdE0tbo0aN59NFHOffcc8nOzuateZEz+ObNm0dvtBJr69atdOnShY4d\nO1a4c9Zzzz0XfRw7zXLPnj2Z/upbQOR6/z59+kTX5ebmxr3fbnbnH/LH2X+u8JnFX/7yl32eT5w4\nketuvgPY9/ONp556Ku7xvjb7JQYOvjbuutqS8EzfzDqa2VwzW25my8xsbMy6G81sRbB8Uszy281s\nVbCuf101LyINW48ePfjJT35CWVlZUvWtWrXi5ZcrfihbX7Q65BAuueLqOn2NZM70S4Fx7l5gZi2B\nfDN7B/gBcBGQ4+67zawtgJl1BQYC3YAjgXfN7Fh3T+5dExGJMWzYsFS3cMBcduWgOn+NhGf67l7k\n7gXB423AcqA9MBJ40N13B+s2BJtcBMxw993u/gWwCuhVcc8iInKgVemDXDPLBnoAC4Bjgd5mtsDM\n/mpmJwdl7YF/xmy2JlhWfl/DzSzPzPL2frotIiJ1K+nQN7MWwCzgJnffSmRo6FDgFOA24CWLXHwa\n7wJUr7DA/Vl37+nuPTMzM6vVvIiIVE1SV++YWSaRwJ/m7rODxWuA2R6ZOGKhme0BsoLlHWM27wCs\nYz/alf5zf6uj7tp8W/Co4iVcNa1vyLXp0kc61KZLH+lQW9X6I0vXBI/+LdS16dLHXZtv46WEVRUl\nc/WOAVOA5e7+aMyqV4Gzg5pjgSbAJuA1YKCZNTWzTkAXoObflBCR0Ck/tfJVN4yNW5fM1Mq16anJ\nz7NjR+JJ3sqLnUZ54MCBrFy5srZbSyiZ4Z3TgUHA2WZWGPycB0wFOpvZUmAGMMQjlgEvAZ8A/wuM\n0pU7IlId5adWnj75iVS3BMBTk19gx874U0Qke3npyJEjmTRpUuLCWpZweMfd5xN/nB4g7h0N3P1+\n4P4a9CUi6eSt8TT5akHkcZODEpY3+W5H4tojusOAB/e7n/JTK5//7z8lb+7r1ZpauU+fPvz4xz9m\n7ty5fPvtt0yZMoXevXtTVlbGHfc+xLwPF1Kyxxg1ahQjRozg/fff5+GHH+aNN94AIl8U69mzJ1u3\nbqVo/UYG/HwIbY5oz9y5c2nRogW33HILb7/9No888gjvvfcer78e6bNXbleemnRPhX569+7N0KFD\n63Qa5Xg0DYOIpKW6mFq5tLSUhQsX8vjjj3PPPZEgnjJlCq1atWD+Wy/z0UcfRadArsyYMWNo94M2\nvPXy89F5c7Zv386PfvQjFixYwBlnnMHo0aP56KOPWLp0Kbt27eLNd96vsJ9GjRrxwx/+sE6nUY5H\n0zCISGIDHuS7on8A0Lxd4g8Zq1JbmbqYWjl2OuW9UzHMmTOHRR/n8cobc2iU2ZQtW7awcuVKmjRp\nknSvGRkZXHrppdHnc+fOZdKkSezYsYPNmzZw/LFd4m7Xtm3bOp1GOR6FvoikpbqYWnmf6ZRLI9Mp\nuzuP3Pcf9O1zxj6/pObPn8+ePXuiz/fXS7NmzcjIyIjW/fKXvyQvL4+OHTty57jR7Nq9O+52u3bV\n7TTK8Wh4R0TS0oGaWrl///5Mfn5GhSmQjz76aD755BN2797Nli1b9plMrWWLgynevj3u/vb2m5WV\nRXFxMa/++e1KX/vTTz+t02mU49GZvoikrb1TK5e/ofnIkSO59tprycnJITc3t5KpleOHcnnXX389\nK5fmc1r/SyGjCW3atOHVV1+lY8eOXH755eTk5NClSxd69OgR3WbY1Zfzs6uHc2THoyvMh9+6dWtu\nuOEGunfvTnZ2Niee0D3u665fv57mzet2GuV4FPoikrbKT62cNzdy45JkplbeGXyusNf7778ffZyV\nlRUd02/UqBH33n4z995+c4XPICZNmhT3ssqR113DyOuuidYXF+87jfN9993HfffdB7BPH7HTO0+f\nPp0RI0Yk+BuofRreEZG01ZCnVm7dujVDhgw54K+rM30RSWsNdWrla6+t25ulVEZn+iJSqcjUWpJq\ntfk+KPRFJK5mzZqxefNmBX+KuTubN2+mWbNmtbI/De+ISFwdOnRgzZo1bNy4EYCSLV8DkPlt4l8C\nDbk2FX00a9aMDh06JNVbIgp9EYkrMzOTTp06RZ8vm3gDAMffkXga5oZcm059VIeGd0REQkShLyIS\nIgp9EZEQUeiLiISIQl9EJEQU+iIiIaLQFxEJEYW+iEiIKPRFREJEoS8iEiIKfRGREFHoi4iEiEJf\nRCREFPoiIiGi0BcRCZGEoW9mHc1srpktN7NlZjY2WD7BzNaaWWHwc16wPNvMdsYsf6auD0JERJKT\nzE1USoFx7l5gZi2BfDN7J1j3mLs/HGebz9w9t9a6FBGRWpEw9N29CCgKHm8zs+VA+7puTEREal+V\nxvTNLBvoASwIFo02s8VmNtXMDo0p7WRmH5vZX82sdyX7Gm5meWaWpxsvi4gcGEmHvpm1AGYBN7n7\nVuBp4Bggl8j/BB4JSouAo9y9B3ALMN3MWpXfn7s/6+493b2nmdXwMEREJBlJhb6ZZRIJ/GnuPhvA\n3de7e5m77wEmA72C5bvdfXPwOB/4DDi2LpoXEZGqSebqHQOmAMvd/dGY5e1iyi4GlgbL25hZRvC4\nM9AF+Lw2mxYRkepJ5uqd04FBwBIzKwyW3QFcaWa5gAOrgRHBujOBe82sFCgDfuHu39Rq1yIiUi3J\nXL0zH4g36P5mJfWziAwFiYhImtE3ckVEQkShLyISIgp9EZEQUeiLiISIQl9EJEQU+iIiIaLQFxEJ\nEYW+iEiIKPRFREJEoS8iEiIKfRGREFHoi4iEiEJfRCREFPoiIiFi6XB/2tbtjvb+E2YkrNvx1ccA\nHHRUj6T2W5X6hlybLn2kQ2269JEOtenSR32rTZc+dnz1MW9MHJXv7j0TFsfQmb6ISIikxZl+t/Yt\nfNna4oR1yyaeEam/Y35S+61KfUOuTZc+0qE2XfpIh9p06aO+1aZLH8smnsGP7vy7zvRFRKRyCn0R\nkRBR6IuIhIhCX0QkRBT6IiIhotAXEQkRhb6ISIgo9EVEQkShLyISIglD38w6mtlcM1tuZsvMbGyw\nfIKZrTWzwuDnvJhtbjezVWa2wsz61+UBiIhI8honUVMKjHP3AjNrCeSb2TvBusfc/eHYYjPrCgwE\nugFHAu+a2bHuXlabjYuISNUlPNN39yJ3LwgebwOWA+33s8lFwAx33+3uXwCrgF610ayIiNRMlcb0\nzSwb6AEsCBaNNrPFZjbVzA4NlrUH/hmz2Rr2/0tCREQOkKRD38xaALOAm9x9K/A0cAyQCxQBj+wt\njbN5hak8zWy4meWZWV46zPQpIhIGSYW+mWUSCfxp7j4bwN3Xu3uZu+8BJvP9EM4aoGPM5h2AdeX3\n6e7PuntPd+9pFu/3hIiI1LZkrt4xYAqw3N0fjVneLqbsYmBp8Pg1YKCZNTWzTkAXYGHttSwiItWV\nzNU7pwODgCVmVhgsuwO40sxyiQzdrAZGALj7MjN7CfiEyJU/o3TljohIekgY+u4+n/jj9G/uZ5v7\ngftr0JeIiNQBfSNXRCREFPoiIiGi0BcRCRGFvohIiCj0RURCRKEvIhIiCn0RkRBR6IuIhIilw2Rn\nJx7ZxAvu75uwbvtXHwNw8FE9ktpvVeobcm269JEOtenSRzrUpksf9a02XfrY/tXHtJhQlO/uPRMW\nx9CZvohIiCQz906d221N4No/J6xbPfEMALolUVvV+oZcmy59pENtuvSRDrXp0kd9q02XPiK1RQnr\nytOZvohIiCj0RURCRKEvIhIiCn0RkRBR6IuIhIhCX0QkRBT6IiIhotAXEQkRhb6ISIgo9EVEQkSh\nLyISIgp9EZEQUeiLiISIQl9EJEQU+iIiIaLQFxEJkYShb2YdzWyumS03s2VmNrbc+lvNzM0sK3je\nx8y2mFlh8HNXXTUvIiJVk8yds0qBce5eYGYtgXwze8fdPzGzjkBf4Kty2/zN3S+o7WZFRKRmEp7p\nu3uRuxcEj7cBy4H2werHgF8Bqb+7uoiIJFSlMX0zywZ6AAvM7EJgrbsvilN6qpktMrO3zKxbJfsa\nbmZ5Zpbnrt8ZIiIHQtI3RjezFsAs4CYiQz53Av3ilBYAR7t7sZmdB7wKdClf5O7PAs8CdGvfQqkv\nInIAJHWmb2aZRAJ/mrvPBo4BOgGLzGw10AEoMLMj3H2ruxcDuPubQObeD3lFRCS1Ep7pm5kBU4Dl\n7v4ogLsvAdrG1KwGerr7JjM7Aljv7m5mvYj8YtlcF82LiEjVJDO8czowCFhiZoXBsjuCs/h4LgNG\nmlkpsBMY6Bq0FxFJCwlD393nA5agJjvm8VPAUzXuTEREap2+kSsiEiIKfRGREFHoi4iEiEJfRCRE\nFPoiIiGi0BcRCRGFvohIiCj0RURCRKEvIhIiCn0RkRBR6IuIhIhCX0QkRBT6IiIhotAXEQkRhb6I\nSIgo9EVEQkShLyISIgp9EZEQUeiLiISIQl9EJEQU+iIiIaLQFxEJEYW+iEiIKPRFREJEoS8iEiIK\nfRGREFHoi4iESMLQN7OOZjbXzJab2TIzG1tu/a1m5maWFTw3M3vSzFaZ2WIzO7GumhcRkappnERN\nKTDO3QvMrCWQb2bvuPsnZtYR6At8FVM/AOgS/PwYeDr4s1LNMzOSarZbu0OSqqtOfUOuTZc+0qE2\nXfpIh9p06aO+1aZLH1Xtea+EZ/ruXuTuBcHjbcByoH2w+jHgV4DHbHIR8IJH/B/Q2szaVas7ERGp\nVVUa0zezbKAHsMDMLgTWuvuicmXtgX/GPF/D978kYvc13MzyzCyvpKSkSk2LiEj1JB36ZtYCmAXc\nRGTI507grnilcZZ5hQXuz7p7T3fvmZmZmWwbIiJSA0mFvpllEgn8ae4+GzgG6AQsMrPVQAegwMyO\nIHJm3zFm8w7AutpsWkREqieZq3cMmAIsd/dHAdx9ibu3dfdsd88mEvQnuvvXwGvA4OAqnlOALe5e\nVHeHICIiyUrm6p3TgUHAEjMrDJbd4e5vVlL/JnAesArYAVxb4y5FRKRWJAx9d59P/HH62JrsmMcO\njKpxZyIiUuv0jVwRkRBR6IuIhIhCX0QkRBT6IiIhotAXEQkRhb6ISIgo9EVEQkShLyISIgp9EZEQ\nUeiLiISIQl9EJEQU+iIiIaLQFxEJEYW+iEiIKPRFREJEoS8iEiIKfRGREFHoi4iEiEJfRCREFPoi\nIiGi0BcRCRGFvohIiJi7p7oHevbs6Xl5ealuQ0SkXjGzfHfvWZVtdKYvIhIiCn0RkRBR6IuIhEjC\n0DezjmY218yWm9kyMxsbLP8vM1tsZoVmNsfMjgyW9zGzLcHyQjO7q64PQkREktM4iZpSYJy7F5hZ\nSyDfzN4BHnL3/wQwszHAXcAvgm3+5u4X1EnHIiJSbQnP9N29yN0LgsfbgOVAe3ffGlN2MJD6y4BE\nRGS/kjnTjzKzbKAHsCB4fj8wGNgC/CSm9FQzWwSsA25192W10ayIiNRM0h/kmlkLYBZw096zfHe/\n0907AtOA0UFpAXC0u58A/AZ4tZL9DTezPDPL27hxY02OQUREkpTUl7PMLBN4A3jb3R+Ns/5o4M/u\n/qM461YDPd190372vw1YUYW+65ssoNLjbwB0fPVbQz6+hnxsAMe5e8uqbJBweMfMDJgCLI8NfDPr\n4u4rg6cXAv8Ilh8BrHd3N7NeRP43sTnBy6yo6rfK6hMzy9Px1V86vvqrIR8bRI6vqtskM6Z/OjAI\nWGJmhcGyO4DrzOw4YA/wJd9fuXMZMNLMSoGdwEBPh7keREQkcei7+3zA4qx6s5L6p4CnatiXiIjU\ngXT5Ru6zqW6gjun46jcdX/3VkI8NqnF8aTHLpoiIHBjpcqYvIiIHgEJfRCREUh76ZvbvZrbCzFaZ\n2fhU91PbzGy1mS0JJp+r93eKMbOpZrbBzJbGLDvMzN4xs5XBn4emssfqquTYJpjZ2pgJBM9LZY81\nsZ/JExvK+1fZ8TWI99DMmpnZQjNbFBzfPcHyTma2IHj/XjSzJvvdTyrH9M0sA/gU6AusAT4CrnT3\nT1LWVC1L5stp9YmZnQkUAy/s/TKemU0CvnH3B4Nf3Ie6+69T2Wd1VHJsE4Bid384lb3VBjNrB7SL\nnTwR+BkwlIbx/lV2fJfTAN7D4DtTB7t7cfCF2fnAWOAWYLa7zzCzZ4BF7v50ZftJ9Zl+L2CVu3/u\n7t8BM4CLUtyT7Ie7zwO+Kbf4IuD54PHzRP6h1TuVHFuDUdnkiTSc96+y42sQPKI4eJoZ/DhwNjAz\nWJ7w/Ut16LcH/hnzfA0N6E0KODDHzPLNbHiqm6kjP3D3Ioj8wwPaprif2jY6uHfE1Po69FFeuckT\nG9z7V35ySBrIe2hmGcGXZDcA7wCfAd+6e2lQkjBDUx368b701dCuIT3d3U8EBgCjgiEEqT+eBo4B\ncoEi4JHUtlNz8SZPbEjiHF+DeQ/dvczdc4EOREZKjo9Xtr99pDr01wAdY553IDIdc4Ph7uuCPzcA\nrxB5oxqa9cF46t5x1Q0p7qfWuPv64B/aHmAy9fz9C8aCZwHT3H12sLjBvH/xjq+hvYcA7v4t8D5w\nCtDazPbOrpAwQ1Md+h8BXYJPn5sAA4HXUtxTrTGzg4MPlDCzg4F+wNL9b1UvvQYMCR4PAf6Uwl5q\n1d4wDFxMPX7/Kps8kQby/u1ncsgG8R6aWRszax08bg6cS+Rzi7lE5jyDJN6/lH8jN7h86nEgA5jq\n7ventKFaZGadiZzdQ2Seo+n1/fjM7P8BfYhMWbseuJvIPRNeAo4CvgJ+7u717gPRSo6tD5FhAQdW\nAyP2jn/XN2Z2BvA3YAmRiRIhMnniAhrG+1fZ8V1JA3gPzSyHyAe1GURO2F9y93uDnJkBHAZ8DFzj\n7rsr3U+qQ19ERA6cVA/viIjIAaTQFxEJEYW+iEiIKPRFREJEoS8iEiIKfQkFM2ttZr+sxnZ31EU/\nIqmiSzYlFIK5WN7YO3tmFbYrdvcWddKUSAroTF/C4kHgmGA+9YfKrzSzdmY2L1i/1Mx6m9mDQPNg\n2bSg7ppgTvNCM/ttMD04ZlZsZo+YWYGZ/cXM2hzYwxNJjs70JRQSnemb2TigmbvfHwT5Qe6+LfZM\n38yOByYBl7h7iZn9D/B/7v6CmTmRb0JOM7O7gLbuPvpAHJtIVTROXCISCh8BU4MJu15198I4NecA\nJwEfRaZIRAoMAAAA/UlEQVR5oTnfT062B3gxePxHYHaFrUXSgIZ3RIjeQOVMYC3wBzMbHKfMgOfd\nPTf4Oc7dJ1S2yzpqVaRGFPoSFtuAlpWtNLOjgQ3uPpnITI0nBqtKgrN/gL8Al5lZ22Cbw4LtIPJv\nae9Mh1cRuZWdSNrR8I6EgrtvNrO/W+Sm52+5+23lSvoAt5lZCZH75O49038WWGxmBe5+tZn9B5E7\noTUCSoBRwJfAdqCbmeUDW4Ar6v6oRKpOH+SK1AJd2in1hYZ3RERCRGf6Eipm1h34Q7nFu939x6no\nR+RAU+iLiISIhndEREJEoS8iEiIKfRGREFHoi4iEiEJfRCRE/j/JXXx3QxAU0gAAAABJRU5ErkJg\ngg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nKPRFRELk/wHLx2YZmm3M0QAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEKCAYAAAD+XoUoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQyajjSUAAAAMSURBVCTpCyGED/l/Oz1/0C1SjDUAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "for i in [evodumb, evohalfherd, evoherd, evoherdwise, evowise]:\n", + " i['mean'].plot(yerr=i['std'])" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:29.248966Z", + "start_time": "2017-10-19T17:54:28.966025+02:00" + } + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEKCAYAAAD6q1UVAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "diff = evodumb['mean']-evohalfherd['mean']\n", + "diff.plot(yerr=evodumb['std']+evohalfherd['std']);" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:54:29.688734Z", + "start_time": "2017-10-19T17:54:29.251456+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAEKCAYAAAALoA6YAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nABdCCAclAS6EEA5KAlwIIRzU/wfsq3ynW1QhuQAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAEKCAYAAAALoA6YAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "evohalfherd['std'].plot()\n", + "evodumb['std'].plot()" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.2" + }, + "toc": { + "colors": { + "hover_highlight": "#DAA520", + "navigate_num": "#000000", + "navigate_text": "#333333", + "running_highlight": "#FF0000", + "selected_highlight": "#FFD700", + "sidebar_border": "#EEEEEE", + "wrapper_background": "#FFFFFF" + }, + "moveMenuLeft": true, + "nav_menu": { + "height": "30px", + "width": "252px" + }, + "navigate_menu": true, + "number_sections": true, + "sideBar": true, + "threshold": 4, + "toc_cell": false, + "toc_section_display": "block", + "toc_window_display": false, + "widenNotebook": false + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/examples/newsspread/NewsSpread.yml b/examples/newsspread/NewsSpread.yml new file mode 100644 index 0000000..6713d04 --- /dev/null +++ b/examples/newsspread/NewsSpread.yml @@ -0,0 +1,138 @@ +--- +default_state: {} +load_module: newsspread +environment_agents: [] +environment_params: + prob_neighbor_spread: 0.0 + prob_tv_spread: 0.01 +interval: 1 +max_time: 30 +name: Sim_all_dumb +network_agents: +- agent_type: DumbViewer + state: + has_tv: false + weight: 1 +- agent_type: DumbViewer + state: + has_tv: true + weight: 1 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +num_trials: 50 +--- +default_state: {} +load_module: newsspread +environment_agents: [] +environment_params: + prob_neighbor_spread: 0.0 + prob_tv_spread: 0.01 +interval: 1 +max_time: 30 +name: Sim_half_herd +network_agents: +- agent_type: DumbViewer + state: + has_tv: false + weight: 1 +- agent_type: DumbViewer + state: + has_tv: true + weight: 1 +- agent_type: HerdViewer + state: + has_tv: false + weight: 1 +- agent_type: HerdViewer + state: + has_tv: true + weight: 1 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +num_trials: 50 +--- +default_state: {} +load_module: newsspread +environment_agents: [] +environment_params: + prob_neighbor_spread: 0.0 + prob_tv_spread: 0.01 +interval: 1 +max_time: 30 +name: Sim_all_herd +network_agents: +- agent_type: HerdViewer + state: + has_tv: true + id: infected + weight: 1 +- agent_type: HerdViewer + state: + has_tv: true + id: neutral + weight: 1 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +num_trials: 50 +--- +default_state: {} +load_module: newsspread +environment_agents: [] +environment_params: + prob_neighbor_spread: 0.0 + prob_tv_spread: 0.01 + prob_neighbor_cure: 0.1 +interval: 1 +max_time: 30 +name: Sim_wise_herd +network_agents: +- agent_type: HerdViewer + state: + has_tv: true + id: infected + weight: 1 +- agent_type: WiseViewer + state: + has_tv: true + weight: 1 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +num_trials: 50 +--- +default_state: {} +load_module: newsspread +environment_agents: [] +environment_params: + prob_neighbor_spread: 0.0 + prob_tv_spread: 0.01 + prob_neighbor_cure: 0.1 +interval: 1 +max_time: 30 +name: Sim_all_wise +network_agents: +- agent_type: WiseViewer + state: + has_tv: true + id: infected + weight: 1 +- agent_type: WiseViewer + state: + has_tv: true + weight: 1 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +network_params: + generator: barabasi_albert_graph + n: 500 + m: 5 +num_trials: 50 diff --git a/examples/newsspread/newsspread.py b/examples/newsspread/newsspread.py new file mode 100644 index 0000000..cdb3ee0 --- /dev/null +++ b/examples/newsspread/newsspread.py @@ -0,0 +1,79 @@ +from soil.agents import BaseAgent,FSM, state, default_state +import random +import logging + + +class DumbViewer(FSM): + ''' + A viewer that gets infected via TV (if it has one) and tries to infect + its neighbors once it's infected. + ''' + defaults = { + 'prob_neighbor_spread': 0.5, + 'prob_neighbor_cure': 0.25, + } + + @default_state + @state + def neutral(self): + r = random.random() + if self['has_tv'] and r < self.env['prob_tv_spread']: + self.infect() + return + + @state + def infected(self): + for neighbor in self.get_neighboring_agents(state_id=self.neutral.id): + prob_infect = self.env['prob_neighbor_spread'] + r = random.random() + if r < prob_infect: + self.set_state(self.infected.id) + neighbor.infect() + return + + def infect(self): + self.set_state(self.infected) + +class HerdViewer(DumbViewer): + ''' + A viewer whose probability of infection depends on the state of its neighbors. + ''' + + level = logging.DEBUG + + def infect(self): + infected = self.count_neighboring_agents(state_id=self.infected.id) + total = self.count_neighboring_agents() + prob_infect = self.env['prob_neighbor_spread'] * infected/total + self.debug('prob_infect', prob_infect) + r = random.random() + if r < prob_infect: + self.set_state(self.infected.id) + +class WiseViewer(HerdViewer): + ''' + A viewer that can change its mind. + ''' + @state + def cured(self): + prob_cure = self.env['prob_neighbor_cure'] + for neighbor in self.get_neighboring_agents(state_id=self.infected.id): + r = random.random() + if r < prob_cure: + try: + neighbor.cure() + except AttributeError: + self.debug('Viewer {} cannot be cured'.format(neighbor.id)) + return + + def cure(self): + self.set_state(self.cured.id) + + @state + def infected(self): + prob_cure = self.env['prob_neighbor_cure'] + r = random.random() + if r < prob_cure: + self.cure() + return + return super().infected() diff --git a/examples/rabbits/rabbit_agents.py b/examples/rabbits/rabbit_agents.py index 51977e1..176895e 100644 --- a/examples/rabbits/rabbit_agents.py +++ b/examples/rabbits/rabbit_agents.py @@ -1,4 +1,4 @@ -from soil.agents import NetworkAgent, FSM, state, default_state, BaseAgent +from soil.agents import FSM, state, default_state, BaseAgent from enum import Enum from random import random, choice from itertools import islice @@ -11,7 +11,7 @@ class Genders(Enum): female = 'female' -class RabbitModel(NetworkAgent, FSM): +class RabbitModel(FSM): level = logging.INFO @@ -26,7 +26,7 @@ class RabbitModel(NetworkAgent, FSM): life_expectancy = 365 * 3 gestation = 33 pregnancy = -1 - max_females = 2 + max_females = 5 @default_state @state @@ -71,6 +71,7 @@ class RabbitModel(NetworkAgent, FSM): self.debug('Pregnancy: {}'.format(self['pregnancy'])) if self['pregnancy'] >= self.gestation: number_of_babies = int(8+4*random()) + self.info('Having {} babies'.format(number_of_babies)) for i in range(number_of_babies): state = {} state['gender'] = choice(list(Genders)).value @@ -79,13 +80,13 @@ class RabbitModel(NetworkAgent, FSM): self.env.add_edge(self['mate'], child.id) # self.add_edge() self.debug('A BABY IS COMING TO LIFE') - self.env['rabbits_alive'] = self.env.get('rabbits_alive', 0)+1 + self.env['rabbits_alive'] = self.env.get('rabbits_alive', self.global_topology.number_of_nodes())+1 self.debug('Rabbits alive: {}'.format(self.env['rabbits_alive'])) self['offspring'] += 1 self.env.get_agent(self['mate'])['offspring'] += 1 - del self['mate'] - self['pregnancy'] = -1 - return self.fertile + del self['mate'] + self['pregnancy'] = -1 + return self.fertile @state def dead(self): @@ -98,12 +99,12 @@ class RabbitModel(NetworkAgent, FSM): class RandomAccident(BaseAgent): - level = logging.INFO + level = logging.DEBUG def step(self): rabbits_total = self.global_topology.number_of_nodes() rabbits_alive = self.env.get('rabbits_alive', rabbits_total) - prob_death = self.env.get('prob_death', 1e-100)*math.log(max(1, rabbits_alive)) + prob_death = self.env.get('prob_death', 1e-100)*math.floor(math.log10(max(1, rabbits_alive))) self.debug('Killing some rabbits with prob={}!'.format(prob_death)) for i in self.env.network_agents: if i.state['id'] == i.dead.id: diff --git a/examples/rabbits/rabbits.yml b/examples/rabbits/rabbits.yml index a2a89db..af22f78 100644 --- a/examples/rabbits/rabbits.yml +++ b/examples/rabbits/rabbits.yml @@ -1,14 +1,14 @@ --- load_module: rabbit_agents name: rabbits_example -max_time: 1500 +max_time: 1200 interval: 1 seed: MySeed agent_type: RabbitModel environment_agents: - agent_type: RandomAccident environment_params: - prob_death: 0.0001 + prob_death: 0.001 default_state: mating_prob: 0.01 topology: diff --git a/examples/tutorial/soil_tutorial.html b/examples/tutorial/soil_tutorial.html new file mode 100644 index 0000000..aad7f09 --- /dev/null +++ b/examples/tutorial/soil_tutorial.html @@ -0,0 +1,23569 @@ + + + +soil_tutorial + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+ +
+
+
+
+

Soil Tutorial

+
+
+
+
+
+
+
+

Introduction

+
+
+
+
+
+
+
+

This notebook is an introduction to the soil agent-based social network simulation framework. +In particular, we will focus on a specific use case: studying the propagation of news in a social network.

+

The steps we will follow are:

+
    +
  • Modelling the behavior of agents
    • +
  • Running the simulation using different configurations
    • +
  • Analysing the results of each simulation
    • +
+ +
+
+
+
+
+
+
+

But before that, let's import the soil module and networkx.

+ +
+
+
+
+
+
In [1]:
+
+
+
import soil
+import networkx as nx
+ 
+%load_ext autoreload
+%autoreload 2
+
+%pylab inline
+# To display plots in the notebooed_
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
Populating the interactive namespace from numpy and matplotlib
+
+
+
+ +
+
+ +
+
+
+
+
+

Basic concepts

+
+
+
+
+
+
+
+

There are three main elements in a soil simulation:

+
    +
  • The network topology. A simulation may use an existing NetworkX topology, or generate one on the fly
    • +
  • Agents. There are two types: 1) network agents, which are linked to a node in the topology, and 2) environment agents, which are freely assigned to the environment.
    • +
  • The environment. It assigns agents to nodes in the network, and stores the environment parameters (shared state for all agents).
    • +
+

Soil is based on simpy, which is an event-based network simulation library. +Soil provides several abstractions over events to make developing agents easier. +This means you can use events (timeouts, delays) in soil, but for the most part we will assume your models will be step-based.

+ +
+
+
+
+
+
+
+

Modeling behaviour

+
+
+
+
+
+
+
+

Our first step will be to model how every person in the social network reacts when it comes to news. +We will follow a very simple model (a finite state machine).

+

There are two types of people, those who have heard about a newsworthy event (infected) or those who have not (neutral). +A neutral person may heard about the news either on the TV (with probability prob_tv_spread) or through their friends. +Once a person has heard the news, they will spread it to their friends (with a probability prob_neighbor_spread). +Some users do not have a TV, so they only rely on their friends.

+

The spreading probabilities will change over time due to different factors. +We will represent this variance using an environment agent.

+ +
+
+
+
+
+
+
+

Network Agents

+
+
+
+
+
+
+
+

A basic network agent in Soil should inherit from soil.agents.BaseAgent, and define its behaviour in every step of the simulation by implementing a run(self) method. +The most important attributes of the agent are:

+
    +

  • agent.state, a dictionary with the state of the agent. agent.state['id'] reflects the state id of the agent. That state id can be used to look for other networks in that specific state. The state can be access via the agent as well. For instance:

    +
    a = soil.agents.BaseAgent(env=env)
+a['hours_of_sleep'] = 10
+print(a['hours_of_sleep'])
+
    +

    The state of the agent is stored in every step of the simulation:

    +
    print(a['hours_of_sleep', 10]) # hours of sleep before step #10
+print(a[None, 0]) # whole state of the agent before step #0
+
    +
    • +

  • agent.env, a reference to the environment. Most commonly used to get access to the environment parameters and the topology:

    +
    a.env.G.nodes() # Get all nodes ids in the topology
+  a.env['minimum_hours_of_sleep']
+
    +
    • +
+

Since our model is a finite state machine, we will be basing it on soil.agents.FSM.

+

With soil.agents.FSM, we do not need to specify a step method. +Instead, we describe every step as a function. +To change to another state, a function may return the new state. +If no state is returned, the state remains unchanged.[ +It will consist of two states, neutral (default) and infected.

+

Here's the code:

+ +
+
+
+
+
+
In [2]:
+
+
+
import random
+
+class NewsSpread(soil.agents.FSM):
+    @soil.agents.default_state
+    @soil.agents.state
+    def neutral(self):
+        r = random.random()
+        if self['has_tv'] and r < self.env['prob_tv_spread']:
+                return self.infected
+        return
+    
+    @soil.agents.state
+    def infected(self):
+        prob_infect = self.env['prob_neighbor_spread']
+        for neighbor in self.get_neighboring_agents(state_id=self.neutral.id):
+            r = random.random()
+            if r < prob_infect:
+                neighbor.state['id'] = self.infected.id
+        return
+        
+
+ +
+
+
+ +
+
+
+
+
+

Environment agents

+
+
+
+
+
+
+
+

Environment agents allow us to control the state of the environment. +In this case, we will use an environment agent to simulate a very viral event.

+

When the event happens, the agent will modify the probability of spreading the rumor.

+ +
+
+
+
+
+
In [3]:
+
+
+
NEIGHBOR_FACTOR = 0.9
+TV_FACTOR = 0.5
+class NewsEnvironmentAgent(soil.agents.BaseAgent):
+    def step(self):
+        if self.now == self['event_time']:
+            self.env['prob_tv_spread'] = 1
+            self.env['prob_neighbor_spread'] = 1
+        elif self.now > self['event_time']:
+            self.env['prob_tv_spread'] = self.env['prob_tv_spread'] * TV_FACTOR
+            self.env['prob_neighbor_spread'] = self.env['prob_neighbor_spread'] * NEIGHBOR_FACTOR
+
+ +
+
+
+ +
+
+
+
+
+

Testing the agents

+
+
+
+
+
+
+
+

Feel free to skip this section if this is your first time with soil.

+ +
+
+
+
+
+
+
+

Testing agents is not easy, and this is not a thorough testing process for agents. +Rather, this section is aimed to show you how to access internal pats of soil so you can test your agents.

+ +
+
+
+
+
+
+
+

First of all, let's check if our network agent has the states we would expect:

+ +
+
+
+
+
+
In [4]:
+
+
+
NewsSpread.states
+
+ +
+
+
+ +
+
+ + +
+ +
Out[4]:
+ + + + +
+
{'infected': <function __main__.NewsSpread.infected>,
+ 'neutral': <function __main__.NewsSpread.neutral>}
+
+ +
+ +
+
+ +
+
+
+
+
+

Now, let's run a simulation on a simple network. It is comprised of three nodes:

+ +
+
+
+
+
+
In [5]:
+
+
+
G = nx.Graph()
+G.add_edge(0, 1)
+G.add_edge(0, 2)
+G.add_edge(2, 3)
+G.add_node(4)
+pos = nx.spring_layout(G)
+nx.draw_networkx(G, pos, node_color='red')
+nx.draw_networkx(G, pos, nodelist=[0], node_color='blue')
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
+
+

Let's run a simple simulation that assigns a NewsSpread agent to all the nodes in that network. +Notice how node 0 is the only one with a TV.

+ +
+
+
+
+
+
In [6]:
+
+
+
env_params = {'prob_tv_spread': 0,
+             'prob_neighbor_spread': 0}
+
+MAX_TIME = 100
+EVENT_TIME = 10
+
+sim = soil.simulation.SoilSimulation(topology=G,
+                                     num_trials=1,
+                                     max_time=MAX_TIME,
+                                     environment_agents=[{'agent_type': NewsEnvironmentAgent,
+                                                         'state': {
+                                                             'event_time': EVENT_TIME
+                                                         }}],
+                                     network_agents=[{'agent_type': NewsSpread,
+                                                      'weight': 1}],
+                                     states={0: {'has_tv': True}},
+                                     default_state={'has_tv': False},
+                                     environment_params=env_params)
+env = sim.run_simulation()[0]
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.02695441246032715 seconds
+INFO:soil.utils:NOT dumping results
+INFO:soil.utils:Finished simulation in 0.03360605239868164 seconds
+
+
+
+ +
+
+ +
+
+
+
+
+

Now we can access the results of the simulation and compare them to our expected results

+ +
+
+
+
+
+
In [7]:
+
+
+
agents = list(env.network_agents)
+
+# Until the event, all agents are neutral
+for t in range(10):
+    for a in agents:
+        assert a['id', t] == a.neutral.id
+
+# After the event, the node with a TV is infected, the rest are not
+assert agents[0]['id', 11] == NewsSpread.infected.id
+
+for a in agents[1:4]:
+    assert a['id', 11] == NewsSpread.neutral.id
+
+# At the end, the agents connected to the infected one will probably be infected, too.
+assert agents[1]['id', MAX_TIME] == NewsSpread.infected.id
+assert agents[2]['id', MAX_TIME] == NewsSpread.infected.id
+
+# But the node with no friends should not be affected
+assert agents[4]['id', MAX_TIME] == NewsSpread.neutral.id
+        
+
+ +
+
+
+ +
+
+
+
+
+

Lastly, let's see if the probabilities have decreased as expected:

+ +
+
+
+
+
+
In [8]:
+
+
+
assert abs(env.environment_params['prob_neighbor_spread'] - (NEIGHBOR_FACTOR**(MAX_TIME-1-10))) < 10e-4
+assert abs(env.environment_params['prob_tv_spread'] - (TV_FACTOR**(MAX_TIME-1-10))) < 10e-6
+
+ +
+
+
+ +
+
+
+
+
+

Running the simulation

+
+
+
+
+
+
+
+

To run a simulation, we need a configuration. +Soil can load configurations from python dictionaries as well as JSON and YAML files. +For this demo, we will use a python dictionary:

+ +
+
+
+
+
+
In [9]:
+
+
+
config = {
+    'name': 'ExampleSimulation',
+    'max_time': 20,
+    'interval': 1,
+    'num_trials': 1,
+    'network_params': {
+       'generator': 'complete_graph',
+        'n': 500,
+    },
+    'network_agents': [
+        {
+            'agent_type': NewsSpread,
+            'weight': 1,
+            'state': {
+                'has_tv': False
+            }
+        },
+        {
+            'agent_type': NewsSpread,
+            'weight': 2,
+            'state': {
+                'has_tv': True
+            }
+        }
+    ],
+    'environment_agents':[
+        {'agent_type': NewsEnvironmentAgent,
+         'state': {
+             'event_time': 10
+         }
+        }
+    ],
+    'states': [ {'has_tv': True} ],
+    'environment_params':{
+        'prob_tv_spread': 0.01,
+        'prob_neighbor_spread': 0.5
+    }
+}
+
+ +
+
+
+ +
+
+
+
+
+

Let's run our simulation:

+ +
+
+
+
+
+
In [10]:
+
+
+
soil.simulation.run_from_config(config, dump=False)
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
INFO:soil.utils:Using config(s): ExampleSimulation
+INFO:soil.utils:Dumping results to soil_output/ExampleSimulation : False
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 5.869051456451416 seconds
+INFO:soil.utils:NOT dumping results
+INFO:soil.utils:Finished simulation in 6.9609293937683105 seconds
+
+
+
+ +
+
+ +
+
+
+
+
+

In real life, you probably want to run several simulations, varying some of the parameters so that you can compare and answer your research questions.

+

For instance:

+
    +
  • Does the outcome depend on the structure of our network? We will use different generation algorithms to compare them (Barabasi-Albert and Erdos-Renyi)
    • +
  • How does neighbor spreading probability affect my simulation? We will try probability values in the range of [0, 0.4], in intervals of 0.1.
    • +
+ +
+
+
+
+
+
In [11]:
+
+
+
network_1 = {
+       'generator': 'erdos_renyi_graph',
+        'n': 500,
+        'p': 0.1
+}
+network_2 = {
+       'generator': 'barabasi_albert_graph',
+        'n': 500,
+        'm': 2
+}
+
+
+for net in [network_1, network_2]:
+    for i in range(5):
+        prob = i / 10
+        config['environment_params']['prob_neighbor_spread'] = prob
+        config['network_params'] = net
+        config['name'] = 'Spread_{}_prob_{}'.format(net['generator'], prob)
+        s = soil.simulation.run_from_config(config)
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.0
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 1.2258412837982178 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0
+INFO:soil.utils:Finished simulation in 5.597268104553223 seconds
+INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.1
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 1.3026399612426758 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1
+INFO:soil.utils:Finished simulation in 5.534018278121948 seconds
+INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.2
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 1.4764575958251953 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2
+INFO:soil.utils:Finished simulation in 6.170421123504639 seconds
+INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.3
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 1.5429913997650146 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3
+INFO:soil.utils:Finished simulation in 5.936013221740723 seconds
+INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.4
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 1.4097135066986084 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4
+INFO:soil.utils:Finished simulation in 5.732810974121094 seconds
+INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.0
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.751497745513916 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0
+INFO:soil.utils:Finished simulation in 2.3415369987487793 seconds
+INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.1
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.8503265380859375 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1
+INFO:soil.utils:Finished simulation in 2.5671920776367188 seconds
+INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.2
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.8511502742767334 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2
+INFO:soil.utils:Finished simulation in 2.55816912651062 seconds
+INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.3
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.8982968330383301 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3
+INFO:soil.utils:Finished simulation in 2.6871559619903564 seconds
+INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.4
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4 : True
+INFO:soil.utils:Trial: 0
+INFO:soil.utils:	Running
+INFO:soil.utils:Finished trial in 0.9563727378845215 seconds
+INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4
+INFO:soil.utils:Finished simulation in 2.5253307819366455 seconds
+
+
+
+ +
+
+ +
+
+
+
+
+

The results are conveniently stored in pickle (simulation), csv and sqlite (history of agent and environment state) and gexf (dynamic network) format.

+ +
+
+
+
+
+
In [12]:
+
+
+
!tree soil_output
+!du -xh soil_output/*
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
soil_output
+├── Spread_barabasi_albert_graph_prob_0.0
+│   ├── Spread_barabasi_albert_graph_prob_0.0.dumped.yml
+│   ├── Spread_barabasi_albert_graph_prob_0.0.simulation.pickle
+│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508409808.7944386.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508428617.9811945.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv
+│   └── Spread_barabasi_albert_graph_prob_0.0_trial_0.gexf
+├── Spread_barabasi_albert_graph_prob_0.1
+│   ├── Spread_barabasi_albert_graph_prob_0.1.dumped.yml
+│   ├── Spread_barabasi_albert_graph_prob_0.1.simulation.pickle
+│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508409810.9913027.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508428620.3419535.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.db.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.environment.csv
+│   └── Spread_barabasi_albert_graph_prob_0.1_trial_0.gexf
+├── Spread_barabasi_albert_graph_prob_0.2
+│   ├── Spread_barabasi_albert_graph_prob_0.2.dumped.yml
+│   ├── Spread_barabasi_albert_graph_prob_0.2.simulation.pickle
+│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508409813.2012305.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508428622.91827.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.db.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.environment.csv
+│   └── Spread_barabasi_albert_graph_prob_0.2_trial_0.gexf
+├── Spread_barabasi_albert_graph_prob_0.3
+│   ├── Spread_barabasi_albert_graph_prob_0.3.dumped.yml
+│   ├── Spread_barabasi_albert_graph_prob_0.3.simulation.pickle
+│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508409815.5177016.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508428625.5117545.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.db.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.environment.csv
+│   └── Spread_barabasi_albert_graph_prob_0.3_trial_0.gexf
+├── Spread_barabasi_albert_graph_prob_0.4
+│   ├── Spread_barabasi_albert_graph_prob_0.4.dumped.yml
+│   ├── Spread_barabasi_albert_graph_prob_0.4.simulation.pickle
+│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508409818.1516452.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508428628.1986933.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.db.sqlite
+│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.environment.csv
+│   └── Spread_barabasi_albert_graph_prob_0.4_trial_0.gexf
+├── Spread_erdos_renyi_graph_prob_0.0
+│   ├── Spread_erdos_renyi_graph_prob_0.0.dumped.yml
+│   ├── Spread_erdos_renyi_graph_prob_0.0.simulation.pickle
+│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508409781.0791047.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508428588.625598.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.db.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.environment.csv
+│   └── Spread_erdos_renyi_graph_prob_0.0_trial_0.gexf
+├── Spread_erdos_renyi_graph_prob_0.1
+│   ├── Spread_erdos_renyi_graph_prob_0.1.dumped.yml
+│   ├── Spread_erdos_renyi_graph_prob_0.1.simulation.pickle
+│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508409786.6177793.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508428594.3783743.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.db.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.environment.csv
+│   └── Spread_erdos_renyi_graph_prob_0.1_trial_0.gexf
+├── Spread_erdos_renyi_graph_prob_0.2
+│   ├── Spread_erdos_renyi_graph_prob_0.2.dumped.yml
+│   ├── Spread_erdos_renyi_graph_prob_0.2.simulation.pickle
+│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508409791.9751768.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508428600.041021.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.db.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.environment.csv
+│   └── Spread_erdos_renyi_graph_prob_0.2_trial_0.gexf
+├── Spread_erdos_renyi_graph_prob_0.3
+│   ├── Spread_erdos_renyi_graph_prob_0.3.dumped.yml
+│   ├── Spread_erdos_renyi_graph_prob_0.3.simulation.pickle
+│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508409797.606661.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508428606.2884977.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.db.sqlite
+│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.environment.csv
+│   └── Spread_erdos_renyi_graph_prob_0.3_trial_0.gexf
+└── Spread_erdos_renyi_graph_prob_0.4
+    ├── Spread_erdos_renyi_graph_prob_0.4.dumped.yml
+    ├── Spread_erdos_renyi_graph_prob_0.4.simulation.pickle
+    ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508409803.4306188.sqlite
+    ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508428612.3312593.sqlite
+    ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.db.sqlite
+    ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.environment.csv
+    └── Spread_erdos_renyi_graph_prob_0.4_trial_0.gexf
+
+10 directories, 70 files
+2.5M	soil_output/Spread_barabasi_albert_graph_prob_0.0
+2.5M	soil_output/Spread_barabasi_albert_graph_prob_0.1
+2.5M	soil_output/Spread_barabasi_albert_graph_prob_0.2
+2.5M	soil_output/Spread_barabasi_albert_graph_prob_0.3
+2.5M	soil_output/Spread_barabasi_albert_graph_prob_0.4
+3.6M	soil_output/Spread_erdos_renyi_graph_prob_0.0
+3.7M	soil_output/Spread_erdos_renyi_graph_prob_0.1
+3.7M	soil_output/Spread_erdos_renyi_graph_prob_0.2
+3.7M	soil_output/Spread_erdos_renyi_graph_prob_0.3
+3.7M	soil_output/Spread_erdos_renyi_graph_prob_0.4
+
+
+
+ +
+
+ +
+
+
+
+
+

Analysing the results

+
+
+
+
+
+
+
+

Loading data

+
+
+
+
+
+
+
+

Once the simulations are over, we can use soil to analyse the results.

+

Soil allows you to load results for specific trials, or for a set of trials if you specify a pattern. The specific methods are:

+
    +
  • analysis.read_data(<directory pattern>) to load all the results from a directory. e.g. read_data('my_simulation/'). For each trial it finds in each folder matching the pattern, it will return the dumped configuration for the simulation, the results of the trial, and the configuration itself. By default, it will try to load data from the sqlite database.
    • +
  • analysis.read_csv(<csv_file>) to load all the results from a CSV file. e.g. read_csv('my_simulation/my_simulation_trial0.environment.csv')
    • +
  • analysis.read_sql(<sqlite_file>) to load all the results from a sqlite database . e.g. read_sql('my_simulation/my_simulation_trial0.db.sqlite')
    • +
+ +
+
+
+
+
+
+
+

Let's see it in action by loading the stored results into a pandas dataframe:

+ +
+
+
+
+
+
In [13]:
+
+
+
from soil.analysis import *
+
+ +
+
+
+ +
+
+
+
In [14]:
+
+
+
df  = read_csv('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv', keys=['id'])
+df
+
+ +
+
+
+ +
+
+ + +
+ +
Out[14]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
agent_idt_stepkeyvaluevalue_type
500idneutralstr
710idneutralstr
920idneutralstr
1130idneutralstr
1340idneutralstr
1550idneutralstr
1760idneutralstr
1970idneutralstr
2180idneutralstr
2390idneutralstr
25100idneutralstr
27110idneutralstr
29120idneutralstr
31130idneutralstr
33140idneutralstr
35150idneutralstr
37160idneutralstr
39170idneutralstr
41180idneutralstr
43190idneutralstr
45200idneutralstr
47210idneutralstr
49220idneutralstr
51230idneutralstr
53240idneutralstr
55250idneutralstr
57260idneutralstr
59270idneutralstr
61280idneutralstr
63290idneutralstr
..................
2102547020idinfectedstr
2102747120idinfectedstr
2102947220idinfectedstr
2103147320idinfectedstr
2103347420idinfectedstr
2103547520idinfectedstr
2103747620idinfectedstr
2103947720idinfectedstr
2104147820idinfectedstr
2104347920idinfectedstr
2104548020idinfectedstr
2104748120idinfectedstr
2104948220idinfectedstr
2105148320idinfectedstr
2105348420idinfectedstr
2105548520idinfectedstr
2105748620idinfectedstr
2105948720idinfectedstr
2106148820idinfectedstr
2106348920idinfectedstr
2106549020idinfectedstr
2106749120idinfectedstr
2106949220idinfectedstr
2107149320idinfectedstr
2107349420idinfectedstr
2107549520idinfectedstr
2107749620idinfectedstr
2107949720idinfectedstr
2108149820idinfectedstr
2108349920idinfectedstr
+

10500 rows × 5 columns

+
+
+ +
+ +
+
+ +
+
+
+
+
+

Soil can also process the data for us and return a dataframe with as many columns as there are attributes in the environment and the agent states:

+ +
+
+
+
+
+
In [15]:
+
+
+
env, agents = process(df)
+agents
+
+ +
+
+
+ +
+
+ + +
+ +
Out[15]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
t_stepagent_id
00neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
.........
2072infected
73infected
74infected
75infected
76infected
77infected
78infected
79infected
8infected
80infected
81infected
82infected
83infected
84infected
85infected
86infected
87infected
88infected
89infected
9infected
90infected
91infected
92infected
93infected
94infected
95infected
96infected
97infected
98infected
99infected
+

10500 rows × 1 columns

+
+
+ +
+ +
+
+ +
+
+
+
+
+

The index of the results are the simulation step and the agent_id. Hence, we can access the state of the simulation at a given step:

+ +
+
+
+
+
+
In [16]:
+
+
+
agents.loc[0]
+
+ +
+
+
+ +
+
+ + +
+ +
Out[16]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
agent_id
0neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
......
72neutral
73neutral
74neutral
75neutral
76neutral
77neutral
78neutral
79neutral
8neutral
80neutral
81neutral
82neutral
83neutral
84neutral
85neutral
86neutral
87neutral
88neutral
89neutral
9neutral
90neutral
91neutral
92neutral
93neutral
94neutral
95neutral
96neutral
97neutral
98neutral
99neutral
+

500 rows × 1 columns

+
+
+ +
+ +
+
+ +
+
+
+
+
+

Or, we can perform more complex tasks such as showing the agents that have changed their state between two simulation steps:

+ +
+
+
+
+
+
In [17]:
+
+
+
changed = agents.loc[1]['id'] != agents.loc[0]['id']
+agents.loc[0][changed]
+
+ +
+
+
+ +
+
+ + +
+ +
Out[17]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
agent_id
140neutral
164neutral
170neutral
310neutral
455neutral
+
+
+ +
+ +
+
+ +
+
+
+
+
+

To focus on specific agents, we can swap the levels of the index:

+ +
+
+
+
+
+
In [18]:
+
+
+
agents1 = agents.swaplevel()
+
+ +
+
+
+ +
+
+
+
In [19]:
+
+
+
agents1.loc['0'].dropna(axis=1)
+
+ +
+
+
+ +
+
+ + +
+ +
Out[19]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
id
t_step
0neutral
1neutral
2neutral
3neutral
4neutral
5neutral
6neutral
7neutral
8neutral
9neutral
10neutral
11infected
12infected
13infected
14infected
15infected
16infected
17infected
18infected
19infected
20infected
+
+
+ +
+ +
+
+ +
+
+
+
+
+

Plotting data

+
+
+
+
+
+
+
+

If you don't want to work with pandas, you can also use some pre-defined functions from soil to conveniently plot the results:

+ +
+
+
+
+
+
In [20]:
+
+
+
plot_all('soil_output/Spread_barabasi_albert_graph_prob_0.0/', get_count, 'id');
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [21]:
+
+
+
plot_all('soil_output/Spread_barabasi*', get_count, 'id');
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [22]:
+
+
+
plot_all('soil_output/Spread_erdos*', get_value, 'prob_tv_spread');
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
+
+

Manually plotting with pandas

+
+
+
+
+
+
+
+

Although the simplest way to visualize the results of a simulation is to use the built-in methods in the analysis module, sometimes the setup is more complicated and we need to explore the data a little further.

+

For that, we can use native pandas over the results.

+

Soil provides some convenience methods to simplify common operations:

+
    +
  • analysis.split_df to separate a history dataframe into environment and agent parameters.
    • +
  • analysis.get_count to get a dataframe with the value counts for different attributes during the simulation.
    • +
  • analysis.get_value to get the evolution of the value of an attribute during the simulation.
    • +
+

And, as we saw earlier, analysis.process can turn a dataframe in canonical form into a dataframe with a column per attribute.

+ +
+
+
+
+
+
In [23]:
+
+
+
p = read_sql('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite')
+env, agents = split_df(p);
+
+ +
+
+
+ +
+
+
+
+
+

Let's look at the evolution of agent parameters in the simulation

+ +
+
+
+
+
+
In [24]:
+
+
+
res = agents.groupby(by=['t_step', 'key', 'value']).size().unstack(level=[1,2]).fillna(0)
+res.plot();
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
+
+

As we can see, event_time is cluttering our results,

+ +
+
+
+
+
+
In [25]:
+
+
+
del res['event_time']
+res.plot()
+
+ +
+
+
+ +
+
+ + +
+ +
Out[25]:
+ + + + +
+
<matplotlib.axes._subplots.AxesSubplot at 0x7fd795b17b38>
+
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [28]:
+
+
+
processed = process_one(agents);
+processed
+
+ +
+
+
+ +
+
+ + +
+ +
Out[28]:
+ + + +
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
event_timehas_tvid
t_stepagent_id
000Trueneutral
10Falseneutral
100Trueneutral
1000Trueneutral
1010Trueneutral
1020Falseneutral
1030Trueneutral
1040Trueneutral
1050Falseneutral
1060Falseneutral
1070Trueneutral
1080Trueneutral
1090Falseneutral
110Trueneutral
1100Falseneutral
1110Falseneutral
1120Trueneutral
1130Trueneutral
1140Trueneutral
1150Trueneutral
1160Falseneutral
1170Trueneutral
1180Trueneutral
1190Falseneutral
120Falseneutral
1200Falseneutral
1210Trueneutral
1220Trueneutral
1230Trueneutral
1240Falseneutral
...............
20730Trueinfected
740Trueinfected
750Trueinfected
760Trueinfected
770Trueinfected
780Trueinfected
790Falseinfected
80Falseinfected
800Trueinfected
810Falseinfected
820Falseinfected
830Trueinfected
840Falseinfected
850Trueinfected
860Trueinfected
870Trueinfected
880Falseinfected
890Falseinfected
90Trueinfected
900Trueinfected
910Trueinfected
920Trueinfected
930Falseinfected
940Trueinfected
950Trueinfected
960Trueinfected
970Trueinfected
980Falseinfected
990Trueinfected
NewsEnvironmentAgent10False0
+

10521 rows × 3 columns

+
+
+ +
+ +
+
+ +
+
+
+
+
+

Which is equivalent to:

+ +
+
+
+
+
+
In [30]:
+
+
+
get_count(agents, 'id', 'has_tv').plot()
+
+ +
+
+
+ +
+
+ + +
+ +
Out[30]:
+ + + + +
+
<matplotlib.axes._subplots.AxesSubplot at 0x7fd799c15748>
+
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [31]:
+
+
+
get_value(agents, 'event_time').plot()
+
+ +
+
+
+ +
+
+ + +
+ +
Out[31]:
+ + + + +
+
<matplotlib.axes._subplots.AxesSubplot at 0x7fd79a228c88>
+
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
+
+

Dealing with bigger data

+
+
+
+
+
+
In [32]:
+
+
+
from soil import analysis
+
+ +
+
+
+ +
+
+
+
In [33]:
+
+
+
!du -xsh ../rabbits/soil_output/rabbits_example/
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
267M	../rabbits/soil_output/rabbits_example/
+
+
+
+ +
+
+ +
+
+
+
+
+

If we tried to load the entire history, we would probably run out of memory. Hence, it is recommended that you also specify the attributes you are interested in.

+ +
+
+
+
+
+
In [34]:
+
+
+
p = analysis.plot_all('../rabbits/soil_output/rabbits_example/', analysis.get_count, 'id')
+
+ +
+
+
+ +
+
+ + +
+ +
+ + + + +
+ +
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [39]:
+
+
+
df = analysis.read_sql('../rabbits/soil_output/rabbits_example/rabbits_example_trial_0.db.sqlite', keys=['id', 'rabbits_alive'])
+
+ +
+
+
+ +
+
+
+
In [40]:
+
+
+
states = analysis.get_count(df, 'id')
+states.plot()
+
+ +
+
+
+ +
+
+ + +
+ +
Out[40]:
+ + + + +
+
<matplotlib.axes._subplots.AxesSubplot at 0x7fd799b5b2b0>
+
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [41]:
+
+
+
alive = analysis.get_value(df, 'rabbits_alive', 'rabbits_alive', aggfunc='sum').apply(pd.to_numeric)
+alive.plot()
+
+ +
+
+
+ +
+
+ + +
+ +
Out[41]:
+ + + + +
+
<matplotlib.axes._subplots.AxesSubplot at 0x7fd796161cf8>
+
+ +
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [44]:
+
+
+
h = alive.join(states);
+h.plot();
+
+ +
+
+
+ +
+
+ + +
+ +
+ + +
+
/home/jfernando/.local/lib/python3.6/site-packages/pandas/core/reshape/merge.py:551: UserWarning: merging between different levels can give an unintended result (1 levels on the left, 2 on the right)
+  warnings.warn(msg, UserWarning)
+
+
+
+ +
+ +
+ + + + +
+ +
+ +
+ +
+
+ +
+
+
+
In [ ]:
+
+
+
states[[('id','newborn'),('id','fertile'),('id', 'pregnant')]].sum(axis=1).sub(alive['rabbits_alive'], fill_value=0)
+
+ +
+
+
+ +
+
+
+ + + + + + diff --git a/examples/tutorial/soil_tutorial.ipynb b/examples/tutorial/soil_tutorial.ipynb new file mode 100644 index 0000000..af9d462 --- /dev/null +++ b/examples/tutorial/soil_tutorial.ipynb @@ -0,0 +1,3867 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T12:41:48.007238Z", + "start_time": "2017-10-19T14:41:47.980725+02:00" + } + }, + "source": [ + "# Soil Tutorial" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T16:44:14.120953Z", + "start_time": "2017-07-02T18:44:14.117152+02:00" + } + }, + "source": [ + "## Introduction" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "cell_style": "center", + "collapsed": true + }, + "source": [ + "This notebook is an introduction to the soil agent-based social network simulation framework.\n", + "In particular, we will focus on a specific use case: studying the propagation of news in a social network.\n", + "\n", + "The steps we will follow are:\n", + "\n", + "* Modelling the behavior of agents\n", + "* Running the simulation using different configurations\n", + "* Analysing the results of each simulation" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T13:38:48.052876Z", + "start_time": "2017-07-03T15:38:48.044762+02:00" + } + }, + "source": [ + "But before that, let's import the soil module and networkx." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:07.621891Z", + "start_time": "2017-10-19T17:56:06.963273+02:00" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Populating the interactive namespace from numpy and matplotlib\n" + ] + } + ], + "source": [ + "import soil\n", + "import networkx as nx\n", + " \n", + "%load_ext autoreload\n", + "%autoreload 2\n", + "\n", + "%pylab inline\n", + "# To display plots in the notebooed_" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T13:41:19.788717Z", + "start_time": "2017-07-03T15:41:19.785448+02:00" + } + }, + "source": [ + "## Basic concepts" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "There are three main elements in a soil simulation:\n", + " \n", + "* The network topology. A simulation may use an existing NetworkX topology, or generate one on the fly\n", + "* Agents. There are two types: 1) network agents, which are linked to a node in the topology, and 2) environment agents, which are freely assigned to the environment.\n", + "* The environment. It assigns agents to nodes in the network, and stores the environment parameters (shared state for all agents).\n", + "\n", + "Soil is based on ``simpy``, which is an event-based network simulation library.\n", + "Soil provides several abstractions over events to make developing agents easier.\n", + "This means you can use events (timeouts, delays) in soil, but for the most part we will assume your models will be step-based.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T15:55:12.933978Z", + "start_time": "2017-07-02T17:55:12.930860+02:00" + } + }, + "source": [ + "## Modeling behaviour" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T13:49:31.269687Z", + "start_time": "2017-07-03T15:49:31.257850+02:00" + } + }, + "source": [ + "Our first step will be to model how every person in the social network reacts when it comes to news.\n", + "We will follow a very simple model (a finite state machine).\n", + "\n", + "There are two types of people, those who have heard about a newsworthy event (infected) or those who have not (neutral).\n", + "A neutral person may heard about the news either on the TV (with probability **prob_tv_spread**) or through their friends.\n", + "Once a person has heard the news, they will spread it to their friends (with a probability **prob_neighbor_spread**).\n", + "Some users do not have a TV, so they only rely on their friends.\n", + "\n", + "The spreading probabilities will change over time due to different factors.\n", + "We will represent this variance using an environment agent." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Network Agents" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T14:03:07.171127Z", + "start_time": "2017-07-03T16:03:07.165779+02:00" + } + }, + "source": [ + "A basic network agent in Soil should inherit from ``soil.agents.BaseAgent``, and define its behaviour in every step of the simulation by implementing a ``run(self)`` method.\n", + "The most important attributes of the agent are:\n", + "\n", + "* ``agent.state``, a dictionary with the state of the agent. ``agent.state['id']`` reflects the state id of the agent. That state id can be used to look for other networks in that specific state. The state can be access via the agent as well. For instance:\n", + "```py\n", + "a = soil.agents.BaseAgent(env=env)\n", + "a['hours_of_sleep'] = 10\n", + "print(a['hours_of_sleep'])\n", + "```\n", + " The state of the agent is stored in every step of the simulation:\n", + " ```py\n", + " print(a['hours_of_sleep', 10]) # hours of sleep before step #10\n", + " print(a[None, 0]) # whole state of the agent before step #0\n", + " ```\n", + "\n", + "* ``agent.env``, a reference to the environment. Most commonly used to get access to the environment parameters and the topology:\n", + " ```py\n", + " a.env.G.nodes() # Get all nodes ids in the topology\n", + " a.env['minimum_hours_of_sleep']\n", + "\n", + " ```\n", + "\n", + "Since our model is a finite state machine, we will be basing it on ``soil.agents.FSM``.\n", + "\n", + "With ``soil.agents.FSM``, we do not need to specify a ``step`` method.\n", + "Instead, we describe every step as a function.\n", + "To change to another state, a function may return the new state.\n", + "If no state is returned, the state remains unchanged.[\n", + "It will consist of two states, ``neutral`` (default) and ``infected``.\n", + "\n", + "Here's the code:" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:08.659268Z", + "start_time": "2017-10-19T17:56:08.606261+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "import random\n", + "\n", + "class NewsSpread(soil.agents.FSM):\n", + " @soil.agents.default_state\n", + " @soil.agents.state\n", + " def neutral(self):\n", + " r = random.random()\n", + " if self['has_tv'] and r < self.env['prob_tv_spread']:\n", + " return self.infected\n", + " return\n", + " \n", + " @soil.agents.state\n", + " def infected(self):\n", + " prob_infect = self.env['prob_neighbor_spread']\n", + " for neighbor in self.get_neighboring_agents(state_id=self.neutral.id):\n", + " r = random.random()\n", + " if r < prob_infect:\n", + " neighbor.state['id'] = self.infected.id\n", + " return\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T12:22:53.931963Z", + "start_time": "2017-07-02T14:22:53.928340+02:00" + } + }, + "source": [ + "### Environment agents" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Environment agents allow us to control the state of the environment.\n", + "In this case, we will use an environment agent to simulate a very viral event.\n", + "\n", + "When the event happens, the agent will modify the probability of spreading the rumor." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:09.116995Z", + "start_time": "2017-10-19T17:56:09.081481+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "NEIGHBOR_FACTOR = 0.9\n", + "TV_FACTOR = 0.5\n", + "class NewsEnvironmentAgent(soil.agents.BaseAgent):\n", + " def step(self):\n", + " if self.now == self['event_time']:\n", + " self.env['prob_tv_spread'] = 1\n", + " self.env['prob_neighbor_spread'] = 1\n", + " elif self.now > self['event_time']:\n", + " self.env['prob_tv_spread'] = self.env['prob_tv_spread'] * TV_FACTOR\n", + " self.env['prob_neighbor_spread'] = self.env['prob_neighbor_spread'] * NEIGHBOR_FACTOR" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T11:23:18.052235Z", + "start_time": "2017-07-02T13:23:18.047452+02:00" + } + }, + "source": [ + "### Testing the agents" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T16:14:54.572431Z", + "start_time": "2017-07-02T18:14:54.564095+02:00" + } + }, + "source": [ + "Feel free to skip this section if this is your first time with soil." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Testing agents is not easy, and this is not a thorough testing process for agents.\n", + "Rather, this section is aimed to show you how to access internal pats of soil so you can test your agents." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "cell_style": "split" + }, + "source": [ + "First of all, let's check if our network agent has the states we would expect:" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:11.367368Z", + "start_time": "2017-10-19T17:56:11.344245+02:00" + }, + "cell_style": "split" + }, + "outputs": [ + { + "data": { + "text/plain": [ + "{'infected': ,\n", + " 'neutral': }" + ] + }, + "execution_count": 4, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "NewsSpread.states" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "cell_style": "split" + }, + "source": [ + "Now, let's run a simulation on a simple network. It is comprised of three nodes:\n" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:12.472479Z", + "start_time": "2017-10-19T17:56:12.206162+02:00" + }, + "cell_style": "split", + "scrolled": false + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAD8CAYAAACfF6SlAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/EVEYuj/A/nJqW3BkOC1AAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "G = nx.Graph()\n", + "G.add_edge(0, 1)\n", + "G.add_edge(0, 2)\n", + "G.add_edge(2, 3)\n", + "G.add_node(4)\n", + "pos = nx.spring_layout(G)\n", + "nx.draw_networkx(G, pos, node_color='red')\n", + "nx.draw_networkx(G, pos, nodelist=[0], node_color='blue')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T11:53:30.997756Z", + "start_time": "2017-07-03T13:53:30.989609+02:00" + }, + "cell_style": "split" + }, + "source": [ + "Let's run a simple simulation that assigns a NewsSpread agent to all the nodes in that network.\n", + "Notice how node 0 is the only one with a TV." + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:12.719473Z", + "start_time": "2017-10-19T17:56:12.653974+02:00" + }, + "cell_style": "split" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.02695441246032715 seconds\n", + "INFO:soil.utils:NOT dumping results\n", + "INFO:soil.utils:Finished simulation in 0.03360605239868164 seconds\n" + ] + } + ], + "source": [ + "env_params = {'prob_tv_spread': 0,\n", + " 'prob_neighbor_spread': 0}\n", + "\n", + "MAX_TIME = 100\n", + "EVENT_TIME = 10\n", + "\n", + "sim = soil.simulation.SoilSimulation(topology=G,\n", + " num_trials=1,\n", + " max_time=MAX_TIME,\n", + " environment_agents=[{'agent_type': NewsEnvironmentAgent,\n", + " 'state': {\n", + " 'event_time': EVENT_TIME\n", + " }}],\n", + " network_agents=[{'agent_type': NewsSpread,\n", + " 'weight': 1}],\n", + " states={0: {'has_tv': True}},\n", + " default_state={'has_tv': False},\n", + " environment_params=env_params)\n", + "env = sim.run_simulation()[0]" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "cell_style": "split" + }, + "source": [ + "Now we can access the results of the simulation and compare them to our expected results" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:15.004439Z", + "start_time": "2017-10-19T17:56:14.904160+02:00" + }, + "cell_style": "split", + "collapsed": true, + "scrolled": false + }, + "outputs": [], + "source": [ + "agents = list(env.network_agents)\n", + "\n", + "# Until the event, all agents are neutral\n", + "for t in range(10):\n", + " for a in agents:\n", + " assert a['id', t] == a.neutral.id\n", + "\n", + "# After the event, the node with a TV is infected, the rest are not\n", + "assert agents[0]['id', 11] == NewsSpread.infected.id\n", + "\n", + "for a in agents[1:4]:\n", + " assert a['id', 11] == NewsSpread.neutral.id\n", + "\n", + "# At the end, the agents connected to the infected one will probably be infected, too.\n", + "assert agents[1]['id', MAX_TIME] == NewsSpread.infected.id\n", + "assert agents[2]['id', MAX_TIME] == NewsSpread.infected.id\n", + "\n", + "# But the node with no friends should not be affected\n", + "assert agents[4]['id', MAX_TIME] == NewsSpread.neutral.id\n", + " " + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T16:41:09.110652Z", + "start_time": "2017-07-02T18:41:09.106966+02:00" + }, + "cell_style": "split" + }, + "source": [ + "Lastly, let's see if the probabilities have decreased as expected:" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:17.382019Z", + "start_time": "2017-10-19T17:56:17.340851+02:00" + }, + "cell_style": "split", + "collapsed": true + }, + "outputs": [], + "source": [ + "assert abs(env.environment_params['prob_neighbor_spread'] - (NEIGHBOR_FACTOR**(MAX_TIME-1-10))) < 10e-4\n", + "assert abs(env.environment_params['prob_tv_spread'] - (TV_FACTOR**(MAX_TIME-1-10))) < 10e-6" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Running the simulation" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T11:20:28.566944Z", + "start_time": "2017-07-03T13:20:28.561052+02:00" + }, + "cell_style": "split" + }, + "source": [ + "To run a simulation, we need a configuration.\n", + "Soil can load configurations from python dictionaries as well as JSON and YAML files.\n", + "For this demo, we will use a python dictionary:" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:19.477080Z", + "start_time": "2017-10-19T17:56:19.386840+02:00" + }, + "cell_style": "split", + "collapsed": true + }, + "outputs": [], + "source": [ + "config = {\n", + " 'name': 'ExampleSimulation',\n", + " 'max_time': 20,\n", + " 'interval': 1,\n", + " 'num_trials': 1,\n", + " 'network_params': {\n", + " 'generator': 'complete_graph',\n", + " 'n': 500,\n", + " },\n", + " 'network_agents': [\n", + " {\n", + " 'agent_type': NewsSpread,\n", + " 'weight': 1,\n", + " 'state': {\n", + " 'has_tv': False\n", + " }\n", + " },\n", + " {\n", + " 'agent_type': NewsSpread,\n", + " 'weight': 2,\n", + " 'state': {\n", + " 'has_tv': True\n", + " }\n", + " }\n", + " ],\n", + " 'environment_agents':[\n", + " {'agent_type': NewsEnvironmentAgent,\n", + " 'state': {\n", + " 'event_time': 10\n", + " }\n", + " }\n", + " ],\n", + " 'states': [ {'has_tv': True} ],\n", + " 'environment_params':{\n", + " 'prob_tv_spread': 0.01,\n", + " 'prob_neighbor_spread': 0.5\n", + " }\n", + "}" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T11:57:34.219618Z", + "start_time": "2017-07-03T13:57:34.213817+02:00" + }, + "cell_style": "split" + }, + "source": [ + "Let's run our simulation:" + ] + }, + { + "cell_type": "code", + "execution_count": 10, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:56:28.208300Z", + "start_time": "2017-10-19T17:56:20.515069+02:00" + }, + "cell_style": "split" + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "INFO:soil.utils:Using config(s): ExampleSimulation\n", + "INFO:soil.utils:Dumping results to soil_output/ExampleSimulation : False\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 5.869051456451416 seconds\n", + "INFO:soil.utils:NOT dumping results\n", + "INFO:soil.utils:Finished simulation in 6.9609293937683105 seconds\n" + ] + } + ], + "source": [ + "soil.simulation.run_from_config(config, dump=False)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T12:03:32.183588Z", + "start_time": "2017-07-03T14:03:32.167797+02:00" + }, + "cell_style": "split", + "collapsed": true + }, + "source": [ + "In real life, you probably want to run several simulations, varying some of the parameters so that you can compare and answer your research questions.\n", + "\n", + "For instance:\n", + " \n", + "* Does the outcome depend on the structure of our network? We will use different generation algorithms to compare them (Barabasi-Albert and Erdos-Renyi)\n", + "* How does neighbor spreading probability affect my simulation? We will try probability values in the range of [0, 0.4], in intervals of 0.1." + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:10.690166Z", + "start_time": "2017-10-19T17:56:28.210104+02:00" + }, + "cell_style": "split", + "scrolled": true + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.0\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 1.2258412837982178 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.0\n", + "INFO:soil.utils:Finished simulation in 5.597268104553223 seconds\n", + "INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.1\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 1.3026399612426758 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.1\n", + "INFO:soil.utils:Finished simulation in 5.534018278121948 seconds\n", + "INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.2\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 1.4764575958251953 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.2\n", + "INFO:soil.utils:Finished simulation in 6.170421123504639 seconds\n", + "INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.3\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 1.5429913997650146 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.3\n", + "INFO:soil.utils:Finished simulation in 5.936013221740723 seconds\n", + "INFO:soil.utils:Using config(s): Spread_erdos_renyi_graph_prob_0.4\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 1.4097135066986084 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_erdos_renyi_graph_prob_0.4\n", + "INFO:soil.utils:Finished simulation in 5.732810974121094 seconds\n", + "INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.0\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.751497745513916 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.0\n", + "INFO:soil.utils:Finished simulation in 2.3415369987487793 seconds\n", + "INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.1\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.8503265380859375 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.1\n", + "INFO:soil.utils:Finished simulation in 2.5671920776367188 seconds\n", + "INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.2\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.8511502742767334 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.2\n", + "INFO:soil.utils:Finished simulation in 2.55816912651062 seconds\n", + "INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.3\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.8982968330383301 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.3\n", + "INFO:soil.utils:Finished simulation in 2.6871559619903564 seconds\n", + "INFO:soil.utils:Using config(s): Spread_barabasi_albert_graph_prob_0.4\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4 : True\n", + "INFO:soil.utils:Trial: 0\n", + "INFO:soil.utils:\tRunning\n", + "INFO:soil.utils:Finished trial in 0.9563727378845215 seconds\n", + "INFO:soil.utils:Dumping results to soil_output/Spread_barabasi_albert_graph_prob_0.4\n", + "INFO:soil.utils:Finished simulation in 2.5253307819366455 seconds\n" + ] + } + ], + "source": [ + "network_1 = {\n", + " 'generator': 'erdos_renyi_graph',\n", + " 'n': 500,\n", + " 'p': 0.1\n", + "}\n", + "network_2 = {\n", + " 'generator': 'barabasi_albert_graph',\n", + " 'n': 500,\n", + " 'm': 2\n", + "}\n", + "\n", + "\n", + "for net in [network_1, network_2]:\n", + " for i in range(5):\n", + " prob = i / 10\n", + " config['environment_params']['prob_neighbor_spread'] = prob\n", + " config['network_params'] = net\n", + " config['name'] = 'Spread_{}_prob_{}'.format(net['generator'], prob)\n", + " s = soil.simulation.run_from_config(config)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T11:05:18.043194Z", + "start_time": "2017-07-03T13:05:18.034699+02:00" + }, + "cell_style": "split" + }, + "source": [ + "The results are conveniently stored in pickle (simulation), csv and sqlite (history of agent and environment state) and gexf (dynamic network) format." + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:28.534861Z", + "start_time": "2017-10-19T17:57:28.258984+02:00" + }, + "cell_style": "split", + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[01;34msoil_output\u001b[00m\n", + "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.0\u001b[00m\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0.dumped.yml\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0.simulation.pickle\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508409808.7944386.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.backup1508428617.9811945.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv\n", + "│   └── Spread_barabasi_albert_graph_prob_0.0_trial_0.gexf\n", + "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.1\u001b[00m\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1.dumped.yml\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1.simulation.pickle\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508409810.9913027.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.backup1508428620.3419535.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.db.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.environment.csv\n", + "│   └── Spread_barabasi_albert_graph_prob_0.1_trial_0.gexf\n", + "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.2\u001b[00m\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2.dumped.yml\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2.simulation.pickle\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508409813.2012305.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.backup1508428622.91827.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.db.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.environment.csv\n", + "│   └── Spread_barabasi_albert_graph_prob_0.2_trial_0.gexf\n", + "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.3\u001b[00m\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3.dumped.yml\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3.simulation.pickle\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508409815.5177016.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.backup1508428625.5117545.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.db.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.environment.csv\n", + "│   └── Spread_barabasi_albert_graph_prob_0.3_trial_0.gexf\n", + "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.4\u001b[00m\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4.dumped.yml\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4.simulation.pickle\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508409818.1516452.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.backup1508428628.1986933.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.db.sqlite\n", + "│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.environment.csv\n", + "│   └── Spread_barabasi_albert_graph_prob_0.4_trial_0.gexf\n", + "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.0\u001b[00m\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0.dumped.yml\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0.simulation.pickle\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508409781.0791047.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.backup1508428588.625598.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.db.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.environment.csv\n", + "│   └── Spread_erdos_renyi_graph_prob_0.0_trial_0.gexf\n", + "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.1\u001b[00m\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1.dumped.yml\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1.simulation.pickle\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508409786.6177793.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.backup1508428594.3783743.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.db.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.environment.csv\n", + "│   └── Spread_erdos_renyi_graph_prob_0.1_trial_0.gexf\n", + "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.2\u001b[00m\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2.dumped.yml\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2.simulation.pickle\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508409791.9751768.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.backup1508428600.041021.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.db.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.environment.csv\n", + "│   └── Spread_erdos_renyi_graph_prob_0.2_trial_0.gexf\n", + "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.3\u001b[00m\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3.dumped.yml\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3.simulation.pickle\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508409797.606661.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.backup1508428606.2884977.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.db.sqlite\n", + "│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.environment.csv\n", + "│   └── Spread_erdos_renyi_graph_prob_0.3_trial_0.gexf\n", + "└── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.4\u001b[00m\n", + " ├── Spread_erdos_renyi_graph_prob_0.4.dumped.yml\n", + " ├── Spread_erdos_renyi_graph_prob_0.4.simulation.pickle\n", + " ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508409803.4306188.sqlite\n", + " ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.backup1508428612.3312593.sqlite\n", + " ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.db.sqlite\n", + " ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.environment.csv\n", + " └── Spread_erdos_renyi_graph_prob_0.4_trial_0.gexf\n", + "\n", + "10 directories, 70 files\n", + "2.5M\tsoil_output/Spread_barabasi_albert_graph_prob_0.0\n", + "2.5M\tsoil_output/Spread_barabasi_albert_graph_prob_0.1\n", + "2.5M\tsoil_output/Spread_barabasi_albert_graph_prob_0.2\n", + "2.5M\tsoil_output/Spread_barabasi_albert_graph_prob_0.3\n", + "2.5M\tsoil_output/Spread_barabasi_albert_graph_prob_0.4\n", + "3.6M\tsoil_output/Spread_erdos_renyi_graph_prob_0.0\n", + "3.7M\tsoil_output/Spread_erdos_renyi_graph_prob_0.1\n", + "3.7M\tsoil_output/Spread_erdos_renyi_graph_prob_0.2\n", + "3.7M\tsoil_output/Spread_erdos_renyi_graph_prob_0.3\n", + "3.7M\tsoil_output/Spread_erdos_renyi_graph_prob_0.4\n" + ] + } + ], + "source": [ + "!tree soil_output\n", + "!du -xh soil_output/*" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-02T10:40:14.384177Z", + "start_time": "2017-07-02T12:40:14.381885+02:00" + } + }, + "source": [ + "## Analysing the results" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Loading data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Once the simulations are over, we can use soil to analyse the results.\n", + "\n", + "Soil allows you to load results for specific trials, or for a set of trials if you specify a pattern. The specific methods are:\n", + "\n", + "* `analysis.read_data()` to load all the results from a directory. e.g. `read_data('my_simulation/')`. For each trial it finds in each folder matching the pattern, it will return the dumped configuration for the simulation, the results of the trial, and the configuration itself. By default, it will try to load data from the sqlite database. \n", + "* `analysis.read_csv()` to load all the results from a CSV file. e.g. `read_csv('my_simulation/my_simulation_trial0.environment.csv')`\n", + "* `analysis.read_sql()` to load all the results from a sqlite database . e.g. `read_sql('my_simulation/my_simulation_trial0.db.sqlite')`" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-07-03T14:44:30.978223Z", + "start_time": "2017-07-03T16:44:30.971952+02:00" + } + }, + "source": [ + "Let's see it in action by loading the stored results into a pandas dataframe:" + ] + }, + { + "cell_type": "code", + "execution_count": 13, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:43.662893Z", + "start_time": "2017-10-19T17:57:43.632252+02:00" + }, + "cell_style": "center", + "collapsed": true + }, + "outputs": [], + "source": [ + "from soil.analysis import *" + ] + }, + { + "cell_type": "code", + "execution_count": 14, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:44.101253Z", + "start_time": "2017-10-19T17:57:44.039710+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
agent_idt_stepkeyvaluevalue_type
500idneutralstr
710idneutralstr
920idneutralstr
1130idneutralstr
1340idneutralstr
1550idneutralstr
1760idneutralstr
1970idneutralstr
2180idneutralstr
2390idneutralstr
25100idneutralstr
27110idneutralstr
29120idneutralstr
31130idneutralstr
33140idneutralstr
35150idneutralstr
37160idneutralstr
39170idneutralstr
41180idneutralstr
43190idneutralstr
45200idneutralstr
47210idneutralstr
49220idneutralstr
51230idneutralstr
53240idneutralstr
55250idneutralstr
57260idneutralstr
59270idneutralstr
61280idneutralstr
63290idneutralstr
..................
2102547020idinfectedstr
2102747120idinfectedstr
2102947220idinfectedstr
2103147320idinfectedstr
2103347420idinfectedstr
2103547520idinfectedstr
2103747620idinfectedstr
2103947720idinfectedstr
2104147820idinfectedstr
2104347920idinfectedstr
2104548020idinfectedstr
2104748120idinfectedstr
2104948220idinfectedstr
2105148320idinfectedstr
2105348420idinfectedstr
2105548520idinfectedstr
2105748620idinfectedstr
2105948720idinfectedstr
2106148820idinfectedstr
2106348920idinfectedstr
2106549020idinfectedstr
2106749120idinfectedstr
2106949220idinfectedstr
2107149320idinfectedstr
2107349420idinfectedstr
2107549520idinfectedstr
2107749620idinfectedstr
2107949720idinfectedstr
2108149820idinfectedstr
2108349920idinfectedstr
\n", + "

10500 rows × 5 columns

\n", + "
" + ], + "text/plain": [ + " agent_id t_step key value value_type\n", + "5 0 0 id neutral str\n", + "7 1 0 id neutral str\n", + "9 2 0 id neutral str\n", + "11 3 0 id neutral str\n", + "13 4 0 id neutral str\n", + "15 5 0 id neutral str\n", + "17 6 0 id neutral str\n", + "19 7 0 id neutral str\n", + "21 8 0 id neutral str\n", + "23 9 0 id neutral str\n", + "25 10 0 id neutral str\n", + "27 11 0 id neutral str\n", + "29 12 0 id neutral str\n", + "31 13 0 id neutral str\n", + "33 14 0 id neutral str\n", + "35 15 0 id neutral str\n", + "37 16 0 id neutral str\n", + "39 17 0 id neutral str\n", + "41 18 0 id neutral str\n", + "43 19 0 id neutral str\n", + "45 20 0 id neutral str\n", + "47 21 0 id neutral str\n", + "49 22 0 id neutral str\n", + "51 23 0 id neutral str\n", + "53 24 0 id neutral str\n", + "55 25 0 id neutral str\n", + "57 26 0 id neutral str\n", + "59 27 0 id neutral str\n", + "61 28 0 id neutral str\n", + "63 29 0 id neutral str\n", + "... ... ... .. ... ...\n", + "21025 470 20 id infected str\n", + "21027 471 20 id infected str\n", + "21029 472 20 id infected str\n", + "21031 473 20 id infected str\n", + "21033 474 20 id infected str\n", + "21035 475 20 id infected str\n", + "21037 476 20 id infected str\n", + "21039 477 20 id infected str\n", + "21041 478 20 id infected str\n", + "21043 479 20 id infected str\n", + "21045 480 20 id infected str\n", + "21047 481 20 id infected str\n", + "21049 482 20 id infected str\n", + "21051 483 20 id infected str\n", + "21053 484 20 id infected str\n", + "21055 485 20 id infected str\n", + "21057 486 20 id infected str\n", + "21059 487 20 id infected str\n", + "21061 488 20 id infected str\n", + "21063 489 20 id infected str\n", + "21065 490 20 id infected str\n", + "21067 491 20 id infected str\n", + "21069 492 20 id infected str\n", + "21071 493 20 id infected str\n", + "21073 494 20 id infected str\n", + "21075 495 20 id infected str\n", + "21077 496 20 id infected str\n", + "21079 497 20 id infected str\n", + "21081 498 20 id infected str\n", + "21083 499 20 id infected str\n", + "\n", + "[10500 rows x 5 columns]" + ] + }, + "execution_count": 14, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df = read_csv('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv', keys=['id'])\n", + "df" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Soil can also process the data for us and return a dataframe with as many columns as there are attributes in the environment and the agent states:" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:45.777794Z", + "start_time": "2017-10-19T17:57:45.698020+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id
t_stepagent_id
00neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
.........
2072infected
73infected
74infected
75infected
76infected
77infected
78infected
79infected
8infected
80infected
81infected
82infected
83infected
84infected
85infected
86infected
87infected
88infected
89infected
9infected
90infected
91infected
92infected
93infected
94infected
95infected
96infected
97infected
98infected
99infected
\n", + "

10500 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " id\n", + "t_step agent_id \n", + "0 0 neutral\n", + " 1 neutral\n", + " 10 neutral\n", + " 100 neutral\n", + " 101 neutral\n", + " 102 neutral\n", + " 103 neutral\n", + " 104 neutral\n", + " 105 neutral\n", + " 106 neutral\n", + " 107 neutral\n", + " 108 neutral\n", + " 109 neutral\n", + " 11 neutral\n", + " 110 neutral\n", + " 111 neutral\n", + " 112 neutral\n", + " 113 neutral\n", + " 114 neutral\n", + " 115 neutral\n", + " 116 neutral\n", + " 117 neutral\n", + " 118 neutral\n", + " 119 neutral\n", + " 12 neutral\n", + " 120 neutral\n", + " 121 neutral\n", + " 122 neutral\n", + " 123 neutral\n", + " 124 neutral\n", + "... ...\n", + "20 72 infected\n", + " 73 infected\n", + " 74 infected\n", + " 75 infected\n", + " 76 infected\n", + " 77 infected\n", + " 78 infected\n", + " 79 infected\n", + " 8 infected\n", + " 80 infected\n", + " 81 infected\n", + " 82 infected\n", + " 83 infected\n", + " 84 infected\n", + " 85 infected\n", + " 86 infected\n", + " 87 infected\n", + " 88 infected\n", + " 89 infected\n", + " 9 infected\n", + " 90 infected\n", + " 91 infected\n", + " 92 infected\n", + " 93 infected\n", + " 94 infected\n", + " 95 infected\n", + " 96 infected\n", + " 97 infected\n", + " 98 infected\n", + " 99 infected\n", + "\n", + "[10500 rows x 1 columns]" + ] + }, + "execution_count": 15, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "env, agents = process(df)\n", + "agents" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-18T14:01:00.669671Z", + "start_time": "2017-10-18T16:01:00.635624+02:00" + } + }, + "source": [ + "The index of the results are the simulation step and the agent_id. Hence, we can access the state of the simulation at a given step: " + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:47.132212Z", + "start_time": "2017-10-19T17:57:47.084737+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id
agent_id
0neutral
1neutral
10neutral
100neutral
101neutral
102neutral
103neutral
104neutral
105neutral
106neutral
107neutral
108neutral
109neutral
11neutral
110neutral
111neutral
112neutral
113neutral
114neutral
115neutral
116neutral
117neutral
118neutral
119neutral
12neutral
120neutral
121neutral
122neutral
123neutral
124neutral
......
72neutral
73neutral
74neutral
75neutral
76neutral
77neutral
78neutral
79neutral
8neutral
80neutral
81neutral
82neutral
83neutral
84neutral
85neutral
86neutral
87neutral
88neutral
89neutral
9neutral
90neutral
91neutral
92neutral
93neutral
94neutral
95neutral
96neutral
97neutral
98neutral
99neutral
\n", + "

500 rows × 1 columns

\n", + "
" + ], + "text/plain": [ + " id\n", + "agent_id \n", + "0 neutral\n", + "1 neutral\n", + "10 neutral\n", + "100 neutral\n", + "101 neutral\n", + "102 neutral\n", + "103 neutral\n", + "104 neutral\n", + "105 neutral\n", + "106 neutral\n", + "107 neutral\n", + "108 neutral\n", + "109 neutral\n", + "11 neutral\n", + "110 neutral\n", + "111 neutral\n", + "112 neutral\n", + "113 neutral\n", + "114 neutral\n", + "115 neutral\n", + "116 neutral\n", + "117 neutral\n", + "118 neutral\n", + "119 neutral\n", + "12 neutral\n", + "120 neutral\n", + "121 neutral\n", + "122 neutral\n", + "123 neutral\n", + "124 neutral\n", + "... ...\n", + "72 neutral\n", + "73 neutral\n", + "74 neutral\n", + "75 neutral\n", + "76 neutral\n", + "77 neutral\n", + "78 neutral\n", + "79 neutral\n", + "8 neutral\n", + "80 neutral\n", + "81 neutral\n", + "82 neutral\n", + "83 neutral\n", + "84 neutral\n", + "85 neutral\n", + "86 neutral\n", + "87 neutral\n", + "88 neutral\n", + "89 neutral\n", + "9 neutral\n", + "90 neutral\n", + "91 neutral\n", + "92 neutral\n", + "93 neutral\n", + "94 neutral\n", + "95 neutral\n", + "96 neutral\n", + "97 neutral\n", + "98 neutral\n", + "99 neutral\n", + "\n", + "[500 rows x 1 columns]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "agents.loc[0]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Or, we can perform more complex tasks such as showing the agents that have changed their state between two simulation steps:" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:48.168805Z", + "start_time": "2017-10-19T17:57:48.113961+02:00" + } + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id
agent_id
140neutral
164neutral
170neutral
310neutral
455neutral
\n", + "
" + ], + "text/plain": [ + " id\n", + "agent_id \n", + "140 neutral\n", + "164 neutral\n", + "170 neutral\n", + "310 neutral\n", + "455 neutral" + ] + }, + "execution_count": 17, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "changed = agents.loc[1]['id'] != agents.loc[0]['id']\n", + "agents.loc[0][changed]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "To focus on specific agents, we can swap the levels of the index:" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:49.046261Z", + "start_time": "2017-10-19T17:57:49.019721+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "agents1 = agents.swaplevel()" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:49.459500Z", + "start_time": "2017-10-19T17:57:49.420016+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
id
t_step
0neutral
1neutral
2neutral
3neutral
4neutral
5neutral
6neutral
7neutral
8neutral
9neutral
10neutral
11infected
12infected
13infected
14infected
15infected
16infected
17infected
18infected
19infected
20infected
\n", + "
" + ], + "text/plain": [ + " id\n", + "t_step \n", + "0 neutral\n", + "1 neutral\n", + "2 neutral\n", + "3 neutral\n", + "4 neutral\n", + "5 neutral\n", + "6 neutral\n", + "7 neutral\n", + "8 neutral\n", + "9 neutral\n", + "10 neutral\n", + "11 infected\n", + "12 infected\n", + "13 infected\n", + "14 infected\n", + "15 infected\n", + "16 infected\n", + "17 infected\n", + "18 infected\n", + "19 infected\n", + "20 infected" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "agents1.loc['0'].dropna(axis=1)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T10:35:40.140920Z", + "start_time": "2017-10-19T12:35:40.106265+02:00" + } + }, + "source": [ + "### Plotting data" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "If you don't want to work with pandas, you can also use some pre-defined functions from soil to conveniently plot the results:" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:52.271094Z", + "start_time": "2017-10-19T17:57:51.102434+02:00" + } + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niGoAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xl8W9WZ8PHfY9mWvMlOvCUkIQ4QKNkIJiwtBUIJUCg0\nbIUwhJ3Ssry0L20H3naGUkrfoR0GKO07tOyEBggFCgyTthAKk7KThJCyZYNAnDix4yS2vG/n/eMe\nybIsyZItWZL9fD8ffSTde3T16Fq+j86595wjxhiUUkqNXVmpDkAppVRqaSJQSqkxThOBUkqNcZoI\nlFJqjNNEoJRSY5wmAqWUGuM0EYxiIvKwiNw6SJn5IlKTTjENYZv7ikiziLiGsY1++0FEtojIgsRE\nmL5E5BIReS0N4hgT+ztdaSJIABH5qoi8ISKNIrJbRF4XkcNTHddYYYz5whhTaIzpSXUskeiBLjlE\n5AQR+UREWkXkFRGZGqVslS3Tal+jfw9LE8EwiYgXeAH4DTAemAT8DOiIczsiIhn99xCR7FTHkG6S\nvU8yYZ8nK0YRKQOeAf4V539vFbAsykseB94DSoGfAE+JSHkyYss0GX3gSRMHAhhjHjfG9Bhj2owx\nLxpj1tlq9+si8htbW/hERE7wv1BEXhWRX4jI60ArsJ+IFIvIAyJSKyLbRORWf5OHiOwvIn8TkQYR\n2SUiS0WkJGh7h4rIGhHxicgywBPrhxCRH9ttbhGRC4KWf0NE3hORJhHZKiI3B62rEhEjIpeLyBfA\n3+zyP4rIDvuZV4rIzJC3KxORl2yc/xP8K05Efm3fp0lEVovIMUHrjhCRVXbdThG5IySOqAccEblU\nRD627/upiHxnkN1yuIh8JCJ7ROQhEQnsTxE5TUTWisheWxucE7Rui4jcICLrgBYReRzYF/gv24T1\nz4PEeZGIfG7/zv8aXJsQkZtF5CkR+YOINAGX2P3ypo2lVkR+KyK5QdszInKd/cy7ROTfQ390iMjt\n9nN+JiKnDLJf/N/dfxORd+zf+TkRGW/XRfpefFNEPrRxvioiB8e6vyM4C/jQGPNHY0w7cDNwiIh8\nKUy8BwLVwE/t/+jTwD+Aswf7rGOCMUZvw7gBXqABeAQ4BRgXtO4SoBv430AOcB7QCIy3618FvgBm\nAtm2zLPA74ECoAJ4B/iOLX8AcCLgBsqBlcBddl0u8HnQe50DdAG3DhL/fBvjHXa7xwEtwEFB62fj\n/GiYA+wEzrDrqgADLLHx5tnllwFFdnt3AWuD3u9hwAcca9f/GngtaP1inF9s2cAPgB2Ax657E7jQ\nPi4EjgqJI3uQz/oNYH9A7OdsBaqDPmdNUNktwAfAFJxfm6/79yXOAaUOOBJwARfb8u6g1661r80L\nWrYghu/TDKAZ+Kr9m95u/44L7Pqb7fMz7N8kDzgMOMrusyrgY+D7Qds0wCv2c+wLbACuCPqOdgHf\ntp/lKmA7IIPE+SqwDZhl//ZPA3+I9L3A+cHUgvP9zQH+GdgE5A62v6PE8GvgnpBlHwBnhyl7JvBx\nyLLfAr9J9TEkHW4pD2A03ICDcQ5wNTgH1eeBSvtP1u+fCufA7j+YvQrcErSuEqdJKS9o2fnAKxHe\n9wzgPfv42DDv9UYM/0zzbcwFQcueBP41Qvm7gDvtY/8//H5Rtl9iyxTb5w8DTwStLwR6gCkRXr8H\nOMQ+XonT7FYWUsYfR9REEGbbzwLfC9oPoYngu0HPTwU228f3AD8P2dZ64Lig114Wsn4LsSWCm4DH\ng57nA530TwQrB9nG94E/BT03wNeDnl8NvGwfXwJsCnk/A0wY5D1eBW4Lej7DxukK973Aab55Muh5\nFk4imT/Y/o4SwwPBMdhlrwOXhCl7IfBWyLJfAA/H850ZrTdtGkoAY8zHxphLjDGTcX4h7YNzwATY\nZuy3zvrcrvfbGvR4Ks6vpVpbfd6LUzuoABCRChF5wjYZNQF/AMrsa/eJ8F6x2GOMaQkXo4gcKc4J\ntnoRaQS+G/SeAz6DiLhE5DYR2Wxj3GJXlYUrb4xpBnYHvd8PbPNNo/38xUGvvRznl+UnIvKuiJwW\n4+fzx3aKiLwlzgn9vTgHm9DPEvZz0f/vNhX4gf9vZLc1hch/13jsQ//904pT44wUFyJyoIi8YJvj\nmoD/S5S/EQO/gztC3g+cBD2Y0G3mEOHvbN8v8H00xvTa9ZNijDGcZpwaeTAvTo1zOGXHHE0ECWaM\n+QTnV+8su2iSiEhQkX1xfrkHXhL0eCtOjaDMGFNib15jjL+N/d9s+TnGGC9OM4p/27UR3isW40Sk\nIEKMj+HUcKYYY4qB3wW9Z7jP8E/AQmABzkG8yi4Pfs0U/wMRKcRpCthuzwfcAJyL08RWgtOUJgDG\nmI3GmPNxEuMvcU72BccdkYi4cZovbgcq7baXh/kswaYEPQ7eJ1uBXwT9jUqMMfnGmMeDyocO6xvr\nML+1wOSguPNwmsqibese4BNguv1e/JiBnyvSZxmO0G12AbsixLkdJ4ECzsUR9vXbhhHjh8AhQdss\nwGn6+zBC2f1EpCho2SERyo45mgiGSUS+ZH/FTrbPp+A057xli1QA14lIjoh8C6cZaXm4bRljaoEX\ngf8QEa+IZIlzgvg4W6QI55fNXhGZBPwo6OVv4jTxXCci2SJyFnBEHB/lZyKSaw/GpwF/DHrP3caY\ndhE5AudAH00RTjJrwGlm+L9hypwqziW3ucDPgbeNMVvta7uBeiBbRG4i6FeciCwWkXL7a3KvXRzr\nJaO5OOck6oFue0L0pEFec42ITLYnQX9M3xUp9wHftbUlEZECcU6qF0XeFDuB/WKI8yngdBH5it0/\nPyN6sgJnvzUBzfZE6VVhyvxIRMbZ7+f3iH51TawWi8gMEckHbgGeMpEv4X0S+IY4l3vm4Jz/6cBp\nvvSLtL8j+RMwS0TOtieWbwLW2R9j/RhjNuCct/mpiHhE5Eycc15Px/5xRy9NBMPnwzlp+LaItOAk\ngA9wvugAbwPTcX4p/QI4xxgTWtUPdhHOQesjnPbxp4CJdt3PcE5UNgL/jXPpHADGmE6cqygusa87\nL3j9IHbY12wHluK01fr/ma4GbhERH84/2pODbGsJTrV+m/0Mb4Up8xjwU5wmocMA/1VKfwX+jHMy\n83Ognf7NBV8HPhSRZpwThYuMc7XIoIwxPuA6G/8enIT2/CAvewwnMX9qb7faba3CObn6W7utTTj7\nPZp/A/7FNiX9MEqcHwL/C3gCp3bgwzkxHe1y5B/az+PDSVLhDqDPAatxDob/jdO+PlyP4tR+d+Bc\noXZdpILGmPU4Ndjf4PwvnA6cbr+3fmH3d5Rt1uNc9fMLnL/DkcAi/3oR+Z2I/C7oJYuAebbsbTj/\ni/UxfM5RT/o3KatEEpFLcK7O+GqqY1GZyTad7cVp9vlsiNsw9vWbEhjXqzhXCd2fqG2q1NEagVJp\nRkROF5F82+Z9O8717ltSG5UazTQRjAHidBZrDnP7c6pjS7QIn7NZgjqmpZqIXBAhRv+Jy4U4zXTb\ncZoVF5kUVN3TYV+Ope9uKmnTkFJKjXFaI1BKqTFOE4FSSo1xaTFyYVlZmamqqkp1GEoplVFWr169\nyxgz7BFU0yIRVFVVsWrVqlSHoZRSGUVEYh1GJiptGlJKqTFOE4FSSo1xmgiUUmqM00SglFJjXEyJ\nQJyp8v4hztR8q+yy8eJMN7jR3o+zy0VE7haRTSKyTkSqk/kBlFJKDU88NYLjjTFzjTHz7PMbcWY5\nmg68bJ+DM13jdHu7EmesdKWUUmlqOE1DC3Hm6cXenxG0fIlxvAWUiMjEcBtQSimVerH2IzDAi3Y4\n298bY+7FmeWpFpwJVUSkwpadRP8x5GvsstpIG1+/w8d5v3+TSSV57GNvk8blManEwz4leeTnpkV3\nB6VGXmcLPHMlfBFuWgelEiPWI+zRxpjt9mD/kogMmAEoSLjZlAaMbCciV+I0HeHdZz+Mgbc/282O\npnZ6evsXL8nPCSQJ594TeDypJI+yQjdZWYNN4qRUhmlvgsfOha1vwyHnQ7Yn1RGptHNnQrYSUyIw\nxmy393Ui8iecKRB3ishEWxuYiDOLEjg1gOC5RycTZu5RW6u4F2DevHnmye9+GYDunl7qfB1s39vG\nNnvbvreN7Xvb2bq7lbc2N+Dr6O63rVxXFpPH5TG1NJ+ppQVMKytgamk+VaUFTB6XR7ZLL45SGaZt\nD/zhbKh9H855EGaemeqIVFoaoURgJ8fIMsb47OOTcOYnfR64GGfKt4txpsLDLr9WRJ7AmTqu0d+E\nFFNArqxA89C8CGWa2rucRLHHSRI1e9vYuruVLbtaefuz3bR29k2bmp0lNkkUUFWaT1VZAVWlTqKY\nMj6fHE0SKt20NMCjZ0D9J3DuEvjSN1IdkRrlYqkRVAJ/EhF/+ceMMX8RkXeBJ0XkcuAL4Fu2/HLg\nVJx5XFuBSxMdtNeTg3dCDl+a4B2wzhhDfXMHnze0smVXC1saWtjS0MrnDS2s/nwPzUG1CVeWMKnE\nX5PIp7TATUl+jr3lUpLXd+/Ny8GlzU8q2ZrrYMlC2P0pLHocpi9IdURqDEiLiWnmzZtnRmLQOWMM\nDS2dfN7QwpZdrf2SxOcNrTS2dUV9vdeTTUl+LuPycygOJIocSvKc58V5ORTkuihwZ1PgdpGfm01B\nbjb5bhcFudl4crKwCVWpgZq2wyPfhKZtcP7jsN/8VEek0pyIrA66pH/IxtTlOCJCWaGbskI3h00d\nP2B9T6+hqa2LvW1d7G3tZG9rF3vb7H1rF43+5W3O8y8aWtjb5iyPJZ+K4CQGmyzyc119icKdTUGu\ni9JCN1X2XEdVaQGVXrcmj7Fg7xdOEmjZBYufhqlfSXVEagwZU4lgMK4sYVxBLuMKcoGCmF/X22vw\ntXfT2NZFS2c3rZ3dtHT09L/v7KG1w97b5S0d3bR0drO7pZOtu1tp6eihoaWDrp6+rOLJyQqc06gq\nLaAq6ET4BK9Hr5YaDXZ/6iSB9ia46FmYPOwfeErFRRNBAmRlCcX5ORTn5wx7Wz29hu172/qarXY5\n95vrW3jlk3o6e3oDZd3ZWYErpYJPhE8el8fE4jxys/VEeNrbtREeOR262+Hi52GfuamOSI1BmgjS\njCtLmDLeuaLpmOn91/X0GnY0tfP5rhY+s+c1tuxy7lduqKejuy9JiEB5obtf34t+HfZK8ijJz9Fm\np1Ta+ZFzYhgDl/w3VM5MdURqjNJEkEH8VzlNKsnjKweU9VvX22vY6Wtny65Wp/+FvbR2e2MbH9c2\nseLjnf0SBUB+risoMXjYp7gvUVR43VQUuSl0Z2uySIba92HJGeDKhYv/C8oPTHVEagzTRDBKZGUJ\nE4udJqFwjDHsbulk+952tu1tZdvedttRz+m099H2RnY1dw54nScni/IiN+WFbue+yE15oYcKb/9l\nZYVubYqKVc1q+MOZkFvkNAeV7p/qiNQYp4lgjBARSgvdlBa6mT25OGyZ9q4eahudBFHv66De10Gd\nr9153NzBZ7taeOez3expDX+ZbUl+DhU2MZQWuAdcZjsuP5die7ltSX4uXk/22Ov1/cVb8IdzoKAU\nLnoexk1NdURKaSJQfTw5LqaVOUN0RNPZ3cuu5o5AsqhvDkkavg7W7t5LY1sXTe3RL60t8mQzLj+X\nkvwcivOCO/LlML4gN1AbqfB6KC9yU5Drytymqs9WwmOLwDvRSQLFk1IdkVKAJgI1BLnZfcOADGZA\n34y2Lhpbncd7wvTNqNnTxp7Wzoh9M/JyXIHmqIpAU1VQs1WRm4oiD6WFuek1fMimFfDEBTBuGlz0\nHBRVpjoipQI0EaikGk7fjL1tXQNqGsE1kE11zbyxuSFij/DxBbmBJFFR1D9ZOLUM53yHNy/JJ8TX\n/xmevAjKD4ILn3OahZRKI5oIVFrKyhLGF+QyviCXgyYURS3b0d3DrubO/ski5PzGO1taqPN10Bly\n5RQ4o9eWF7kpC1PL2Hd8PsdMLxt6ovj0f2DZYpgwx+kxnD+wR7tSqaaJQGU8d7YrcFltNMYYmtq7\nB9QsgpPG1t2tvPfFHhpaOgNNU89eczRzp5QMLbiPnoOcfKfHsCf8SXqlUk0TgRozRITiPOek9AEV\nhVHLdvf0svrzPZx371vU7GkdeiLw7YDiKZoEVFpLo7NpSqWPbFdWoElqZ1PH0Dfkq4WiCQmKSqnk\n0ESgVATFeTnkZmdR19Q+9I34dkDRxMQFpVQSaCJQKgIRodLrZudQE0FvDzTv1BqBSnuaCJSKorLI\nM/SmoZZdYHo0Eai0p4lAqSgqvR52+oZYI/DZqbq1aUilOU0ESkVR4XVTN9QagW+Hc6+JQKU5TQRK\nRVHp9dDc0U1zR3f8Lw7UCLRpSKU3TQRKRVHpdQMM7coh3w5AoLAisUEplWCaCJSKorLIAwyxL4Gv\nFgrKwTX8KUyVSiZNBEpFUeF1EkHdUE4Y+3Zos5DKCJoIlIrC3zQ0pL4Evlo9UawygiYCpaIodGeT\nn+saYtOQ1ghUZtBEoFQUTu9iT/w1gp4uaKnXGoHKCJoIlBpERdEQ+hI01wFGawQqI2giUGoQQ+pd\nrJ3JVAbRRKDUIPwDz5lwkyhHop3JVAbRRKDUICq9Htq7emlqj6N3sY4zpDKIJgKlBhHoSxDPCWPf\nDhAXFJQlKSqlEifmRCAiLhF5T0ResM+nicjbIrJRRJaJSK5d7rbPN9n1VckJXamRUVnk70sQxwlj\n3w4orIQsV5KiUipx4qkRfA/4OOj5L4E7jTHTgT3A5Xb55cAeY8wBwJ22nFIZq9LrH2YinhqBTlGp\nMkdMiUBEJgPfAO63zwX4GvCULfIIcIZ9vNA+x64/wZZXKiNV+HsXx3PlkE5RqTJIrDWCu4B/Bnrt\n81JgrzHGf/asBphkH08CtgLY9Y22fD8icqWIrBKRVfX19UMMX6nky8/NpsiTHV9fAq0RqAwyaCIQ\nkdOAOmPM6uDFYYqaGNb1LTDmXmPMPGPMvPLy8piCVSpV4upd3N0Bbbu1RqAyRnYMZY4GvikipwIe\nwItTQygRkWz7q38ysN2WrwGmADUikg0UA7sTHrlSIyiuSewDncm0RqAyw6A1AmPM/zHGTDbGVAGL\ngL8ZYy4AXgHOscUuBp6zj5+3z7Hr/2bi6omjVPqJaxJ77VWsMsxw+hHcAFwvIptwzgE8YJc/AJTa\n5dcDNw4vRKVSr8Lroc4XY+9i7VWsMkwsTUMBxphXgVft40+BI8KUaQe+lYDYlEoblV43XT2GPa1d\njC/IjV5YawQqw2jPYqViEFdfAl8tZOVA/vgkR6VUYmgiUCoGcc1U5u9DoN1nVIbQRKBUDCqK/OMN\nxXDCWPsQqAyjiUCpGFTEXSPQRKAyhyYCpWLgznYxLj8ntmEmdHgJlWE0ESgVI6d38SBNQ50t0NGo\nNQKVUTQRKBWjCq9n8DkJ9NJRlYE0ESgVo8oi9+A1Ah1eQmUgTQRKxajS66G+uYOe3ii9i3WKSpWB\nNBEoFaNKr5ueXkNDS5RagdYIVAbSRKBUjPrmLo6WCGohOw88xSMUlVLDp4lAqRjFNMyEvw+B9ipW\nGUQTgVIx6htmYpCmIT0/oDKMJgKlYlRW6EZksBqBDi+hMo8mAqVilOPKorTATV2k3sXGaI1AZSRN\nBErFwZmyMkLTUIcPulq0RqAyjiYCpeIQdRJ77VWsMpQmAqXiELVGoFNUqgyliUCpOFQUeWho6aCr\np3fgSq0RqAyliUCpOFR6PRgDu5rD1AoCNYLKkQ1KqWHSRKBUHKL2JfDtgNwicBeNcFRKDY8mAqXi\nELV3sfYhUBlKE4FScfBPWRl2XgKdolJlKE0ESsWhtMCNK0siNA3V6olilZE0ESgVB1eWUF7oHtg0\nFOhVrDUClXk0ESgVp0qvm52+kBpB2x7o6dAagcpImgiUilPYuYt1QhqVwTQRKBUnp3dxaCLQKSpV\n5tJEoFScKos87GntoqO7p2+h1ghUBtNEoFScKsNNWanjDKkMlj1YARHxACsBty3/lDHmpyIyDXgC\nGA+sAS40xnSKiBtYAhwGNADnGWO2JCl+pUZcoC+Br50p4/Odhb4d4CmBnLwURpZYXV1d1NTU0N4e\nZSIeNSI8Hg+TJ08mJycnKdsfNBEAHcDXjDHNIpIDvCYifwauB+40xjwhIr8DLgfusfd7jDEHiMgi\n4JfAeUmJXqkU6OtdHFIjGGXnB2pqaigqKqKqqgrROZhTxhhDQ0MDNTU1TJs2LSnvMWjTkHE026c5\n9maArwFP2eWPAGfYxwvtc+z6E0S/RWoU6WsaCvqlPAr7ELS3t1NaWqpJIMVEhNLS0qTWzGI6RyAi\nLhFZC9QBLwGbgb3GmG5bpAaYZB9PArYC2PWNQGkig1Yqlcbl55Djkv59CUbpFJWaBNJDsv8OMSUC\nY0yPMWYuMBk4Ajg4XDF7Hy5iE7pARK4UkVUisqq+vj7WeJVKORGhoihoprLeXmgefTWCkbRlyxZm\nzZo1Zt8/1eK6asgYsxd4FTgKKBER/zmGycB2+7gGmAJg1xcDu8Ns615jzDxjzLzy8vKhRa9UilR6\n3X1XDbU2QG/3qKwRqLFh0EQgIuUiUmIf5wELgI+BV4BzbLGLgefs4+ftc+z6vxljBtQIlMpk/eYu\n1ktHE+rTTz/l0EMP5e233+ZHP/oRhx9+OHPmzOH3v/89ABdeeCHPPfdcoPwFF1zA888/328b5513\nHsuXLw88v+SSS3j66afZsmULxxxzDNXV1VRXV/PGG28MeP+HH36Ya6+9NvD8tNNO49VXXwXgxRdf\n5Mtf/jLV1dV861vform5ecDrM1EsNYKJwCsisg54F3jJGPMCcANwvYhswjkH8IAt/wBQapdfD9yY\n+LCVSq3+iUCnqEyU9evXc/bZZ/PQQw/x/vvvU1xczLvvvsu7777Lfffdx2effcYVV1zBQw89BEBj\nYyNvvPEGp556ar/tLFq0iGXLlgHQ2dnJyy+/zKmnnkpFRQUvvfQSa9asYdmyZVx33XUxx7Zr1y5u\nvfVWVqxYwZo1a5g3bx533HFH4j58Cg16+agxZh1waJjln+KcLwhd3g58KyHRKZWmKrxumtq7aevs\nIU9rBAlRX1/PwoULefrpp5k5cya33nor69at46mnnIsTGxsb2bhxIyeddBLXXHMNdXV1PPPMM5x9\n9tlkZ/c/lJ1yyilcd911dHR08Je//IVjjz2WvLw8Ghsbufbaa1m7di0ul4sNGzbEHN9bb73FRx99\nxNFHHw04CebLX/5y4nZACsXSj0ApFaKyyF5C6mtnqr9GUKhzFQ9HcXExU6ZM4fXXX2fmzJkYY/jN\nb37DySefPKDshRdeyNKlS3niiSd48MEHB6z3eDzMnz+fv/71ryxbtozzzz8fgDvvvJPKykref/99\nent78Xg8A16bnZ1Nb29v4Ln/sk1jDCeeeCKPP/54oj5y2tAhJpQagn6dyny1kF8G2bkpjiqz5ebm\n8uyzz7JkyRIee+wxTj75ZO655x66uroA2LBhAy0tLYDT5n/XXXcBMHPmTAC2bdvGCSecENjeokWL\neOihh/j73/8eSCaNjY1MnDiRrKwsHn30UXp6eghVVVXF2rVr6e3tZevWrbzzzjsAHHXUUbz++uts\n2rQJgNbW1rhqFOlME4FSQ9A3iX37qO1DkAoFBQW88MILgV/uM2bMoLq6mlmzZvGd73yH7m6n61Jl\nZSUHH3wwl156aeC1tbW1/ZqITjrpJFauXMmCBQvIzXWS9NVXX80jjzzCUUcdxYYNGygoKBgQw9FH\nH820adOYPXs2P/zhD6murgagvLychx9+mPPPP585c+Zw1FFH8cknnyRzd4wYSYcLeubNm2dWrVqV\n6jCUilljWxeH/OxF/uUbB3PFR5dCQTksfmrwF2aQjz/+mIMPDtdlKPVaW1uZPXs2a9asobi4GIDf\n/va37Lvvvnzzm99McXTJEe7vISKrjTHzhrttPUeg1BB4Pdl4crKo83U4NYIJs1Md0pixYsUKLrvs\nMq6//vpAEgD6XfKp4qOJQKkhEBEqvR7qG5uhpU6bhkbQggUL+OKLL1Idxqii5wiUGqLKIg/te3eC\n6dVLR1VG00Sg1BBVeN2YJp2iUmU+TQRKDVGl10N2y07nidYIVAbTcwRKDVFFkZv2ngbn55TWCFQG\n0xqBUkNU6fVQIXswkuVcPqoSrq2tjeOOO46enh62b9/OOeecE7bc/PnzGclL0O+66y5aW1vjft0l\nl1wSGDJj0aJFbNy4MdGhDYkmAqWGqMLrppI9dHnKwKWV62R48MEHOeuss3C5XOyzzz6Bg2iqRUsE\n4Xorh3PVVVfxq1/9KpFhDZkmAqWGqNLroVL20JKrtYFkWbp0KQsXLgT6Tx7T1tbGokWLmDNnDued\ndx5tbW2Dbmv+/PnccMMNHHHEERx44IH8/e9/B5wDd7jhrl999VVOO+20wOuvvfZaHn74Ye6++262\nb9/O8ccfz/HHHw9AYWEhN910E0ceeSRvvvkmt9xyC4cffjizZs3iyiuvJFzH3WOOOYYVK1YEekun\nkv6MUWqIKr0eOmQvjdlTGZfqYJLsZ//1IR9tb0roNmfs4+Wnp8+MuL6zs5NPP/2UqqqqAevuuece\n8vPzWbduHevWrQsMAzGY7u5u3nnnHZYvX87PfvYzVqxYwQMPPBAY7rqjo4Ojjz6ak046KeI2rrvu\nOu644w5eeeUVysrKAGhpaWHWrFnccsstzmebMYObbroJcAbIe+GFFzj99NP7bScrK4sDDjiA999/\nn8MOOyym+JNFawRKDVGhO5tK2cMuGZ/qUEalXbt2UVJSEnbdypUrWbx4MQBz5sxhzpw5MW3zrLPO\nAuCwww5jy5YtgDPZzJIlS5g7dy5HHnkkDQ0Ncbfdu1wuzj777MDzV155hSOPPJLZs2fzt7/9jQ8/\n/DDs6yoqKti+fXvYdSNJawRKDVV3J6XSxJsm/MFqNIn2yz1Z8vLyAkNAhzOUCd3dbmewQJfLFWiS\niTTc9WuvvRZ2OOpwPB4PLpcrUO7qq69m1apVTJkyhZtvvjnia9vb28nLy4v7cySa1giUGqqWOgC2\ndhUPUlBu0AyjAAAZT0lEQVQNxbhx4+jp6Ql7ED322GNZunQpAB988AHr1q0LrLvooosCQ0fHItJw\n11OnTuWjjz6io6ODxsZGXn755cBrioqK8Pl8Ybfnj7esrIzm5uaoJ7g3bNgQGEY7lbRGoNRQ2Qlp\nPusoSnEgo9dJJ53Ea6+9xoIFC/otv+qqq7j00kuZM2cOc+fO5Ygj+iZLXLduHRMnxt6v44orrmDL\nli1UV1djjKG8vJxnn32WKVOmcO655zJnzhymT5/OoYf2TdR45ZVXcsoppzBx4kReeeWVftsrKSnh\n29/+NrNnz6aqqorDDz887Pvu3LmTvLy8uGJNFh2GWqmh+vi/YNliFnbfxrM//+6QmirSWToMQ/3e\ne+9xxx138Oijj8ZUvqmpicsvv5w//vGPSY5s+O688068Xi+XX355TOWTOQy1Ng0pNVS2RlDTXUxT\nW+ovARyNDj30UI4//viYr833er0ZkQTAqTlcfPHFqQ4D0ESg1ND5aumVbHZTxE5f5BOJanguu+yy\nwInY0eTSSy/tN6NaKmkiUGqofDvoyq/AkOVMWalUhtJEoNRQ+Wqh0Bl1dGdTR4qDUWroNBEoNVS+\nHWQX7wOgNQKV0TQRKDVUvlpcxRPxerKp00SgMpgmAqWGoqsd2vZA0QQqvR5tGkqSRA5DfdNNN7Fi\nxYqoZTo6OliwYAFz585l2bJlccW6ZcsWHnvssbheA+kxNLUmAqWGotm5dJSiiU4i0KuGkiKRw1Df\ncsstAzqmhXrvvffo6upi7dq1nHfeeXFtf6iJIFiqhqbWRKDUUPj8iWACFV43dVojSIpEDkMd/Mu7\nqqqKn/70p1RXVzN79mw++eQT6urqWLx4MWvXrmXu3Lls3ryZ1atXc9xxx3HYYYdx8sknU1vrzFG9\nadMmFixYwCGHHEJ1dTWbN2/mxhtv5O9//ztz587lzjvvjDi8tTGGa6+9lhkzZvCNb3yDurq6QIyp\nGpo6PS5iVSrT+Pomra/0ZlHna6e315CVNbp6Fwf8+UbY8Y/EbnPCbDjltoirkzEMdbCysjLWrFnD\nf/7nf3L77bdz//33c//993P77bfzwgsv0NXVxYUXXshzzz1HeXk5y5Yt4yc/+QkPPvggF1xwATfe\neCNnnnkm7e3t9Pb2cttttwVeC3DvvfeGHd76vffeY/369fzjH/9g586dzJgxg8suuwxI3dDUmgiU\nGoqgGkFlUSNdPYY9rZ2UFrpTG9coMtgw1Ndddx0Q3zDUwYKHpH7mmWcGrF+/fj0ffPABJ554IuBM\nYDNx4kR8Ph/btm3jzDPPBJyRR8N58cUXWbduXaAW0tjYyMaNG1m5ciXnn39+oLnra1/7Wr/X+Yem\n1kSgVLrz1YLLDXnjqPQ6zUI7mzpGbyKI8ss9WZIxDHWwcENSBzPGMHPmTN58881+y5uaYpugJ9Lw\n1suXL48aeyqGph70HIGITBGRV0TkYxH5UES+Z5ePF5GXRGSjvR9nl4uI3C0im0RknYjEX2dTKt35\ndkBRJYhQ4XV+EeoJ48QaqWGoIznooIOor68PJIKuri4+/PBDvF4vkydP5tlnnwWcK41aW1sHDE0d\naXjrY489lieeeIKenh5qa2sHjF6aiqGpYzlZ3A38wBhzMHAUcI2IzABuBF42xkwHXrbPAU4Bptvb\nlcA9CY9aqVTz1UKRM3xwpdf5Zal9CRLPPwx1qKuuuorm5mbmzJnDr371q2ENQx1Jbm4uTz31FDfc\ncAOHHHIIc+fO5Y033gDg0Ucf5e6772bOnDl85StfYceOHcyZM4fs7GwOOeQQ7rzzTq644gpmzJhB\ndXU1s2bN4jvf+Q7d3d2ceeaZTJ8+ndmzZ3PVVVdx3HHHBd4zZUNTG2PiugHPAScC64GJdtlEYL19\n/Hvg/KDygXKRbocddphRKqP8Zp4xyy40xhjT3tVtpt7wgvn1ig0pDiqxPvroo1SHYNasWWMWL14c\nc/nGxkZzzjnnJDGi5LrjjjvM/fffH3ZduL8HsMrEeQwPd4vr8lERqQIOBd4GKo0xtTaZ1AIVttgk\nYGvQy2rsstBtXSkiq0RkVX19fTxhKJV6vh2BGoE728X4glwdZiIJRvMw1OGkamjqmBOBiBQCTwPf\nN8ZEO1sS7izIgNlvjDH3GmPmGWPmlZeXxxqGUqnX0QwdTVA0IbCoositvYuTZLQOQx1OqoamjikR\niEgOThJYaozxX2e1U0Qm2vUTAX+viBpgStDLJwPbExOuUmmgeadzX9TXjlvp9VCnJ4tVhorlqiEB\nHgA+NsbcEbTqecBfh7kY59yBf/lF9uqho4BGfxOSUqNCoDNZX42g0uselU1DJg2mslXJ/zvEUgc5\nGrgQ+IeIrLXLfgzcBjwpIpcDXwDfsuuWA6cCm4BW4NKERqxUqvn6xhnyq/R6qPd10NNrcI2S3sUe\nj4eGhgZKS0tH3XzMmcQYQ0NDQ8SOa4kwaCIwxrxG+HZ/gBPClDfANcOMS6n0FaZGUOH10Gugobkj\n0K8g002ePJmamhr0Yo7U83g8TJ48OWnb157FSsXLtwNy8sHtDSyqLHL6EuxsGj2JICcnh2nTpqU6\nDDUCdPRRpeLlq3VqA0HNJZX+3sWj8DyBGv00ESgVr6A+BH6VOsyEymCaCJSKl79GEKSsMBcRncRe\nZSZNBErFw5iwNYJsVxZlhW4db0hlJE0ESsWjowm6WgfUCGD09iVQo58mAqXiEaYPgV9lkU5irzKT\nJgKl4hGmD4FfhQ4zoTKUJgKl4hGtRuB1s6u5k66e3hEOSqnh0USgVDz8NYLCygGr/JeQ1vu0eUhl\nFk0ESsXDt8PpUewuHLDKP1OZnjBWmUYTgVLxCNOHwK+iyN+7WGsEKrNoIlAqHr4dEROBv2lITxir\nTKOJQKl4BE1aH6q0IBdXlmjTkMo4mgiUilWgV3H4GkFWluiUlSojaSJQKlZte6CnM2KNAJy+BFoj\nUJlGE4FSsYrSmcyvsshNndYIVIbRRKBUrAKJIHKNoNLr0aGoVcbRRKBUrAK9iqPUCLxu9rZ20d7V\nM0JBKTV8mgiUilWgV3HkRFChvYtVBtJEoFSsfDsgbxzkRJ6TWKesVJlIE4FSsQozIU2ovmEmtEag\nMocmAqViFWV4Cb/KIq0RqMyjiUCpWMVQIyjJzyHXlaVXDqmMoolAqVj09kbtVewnIlR4tS+Byiya\nCJSKResuMD2D1gjA9iXQpiGVQTQRKBWLGHoV++kk9irTaCJQKhZRpqgMVVHk0aYhlVE0ESgVi7hq\nBB58Hd20dHQnOSilEkMTgVKx8NcIwsxVHMrfl6BOexerDDFoIhCRB0WkTkQ+CFo2XkReEpGN9n6c\nXS4icreIbBKRdSJSnczglRoxvlooKAdXzqBFtXexyjSx1AgeBr4esuxG4GVjzHTgZfsc4BRgur1d\nCdyTmDCVSrEYLh3100nsVaYZNBEYY1YCu0MWLwQesY8fAc4IWr7EON4CSkRk8LNrSqW7KFNUhvIP\nPKcnjFWmGOo5gkpjTC2Ava+wyycBW4PK1dhlSmW2OGoERe5s8nJcWiNQGSPRJ4slzDITtqDIlSKy\nSkRW1dfXJzgMpRKopxua62KuEYiI05dATxarDDHURLDT3+Rj7+vs8hpgSlC5ycD2cBswxtxrjJln\njJlXXl4+xDCUGgEtdYCJuUYAOnexyixDTQTPAxfbxxcDzwUtv8hePXQU0OhvQlIqY8UwRWWoSq+H\nOk0EKkPEcvno48CbwEEiUiMilwO3ASeKyEbgRPscYDnwKbAJuA+4OilRKzWSYpiiMlRlkZudTR0Y\nE7ZlVKm0kj1YAWPM+RFWnRCmrAGuGW5QSqWVIdYI2rp68HV04/UM3vdAqVTSnsVKDca3AyTL6VAW\nowp/72JtHlIZQBOBUoPx1TpDS2S5Yn5JX+9ivXJIpT9NBEoNJo4+BH46zITKJJoIlBpMDFNUhqoo\n0knsVebQRKDUYGKYtD5UgTubIne21ghURtBEoFQ03R3Q2hB3jQCcE8Z1Oom9ygCaCJSKpnmncx9n\njQD8cxdr05BKf5oIlIomjikqQ+kk9ipTaCJQKpo4pqgMVeF1U6e9i1UG0ESgVDTDqREUeejs6WVv\na1eCg1IqsTQRKBWNrxayciBvfNwvDfQl0BPGKs1pIlAqGn9nsqz4/1X6pqzUE8YqvWkiUCqaIfQh\n8NPexSpTaCJQKpohDC/hV16kA8+pzKCJQKlo4pi0PpQnx0VJfo42Dam0p4lAqUg6W6G9ccg1AnCu\nHNKmIZXuNBEoFUnz0C8d9avQSexVBhh0hjKlRq3eHmjZ5Qwj0e9W59zv/swpV1g55Leo9HrYuHNX\nggJWKjk0EajRxRjo8NmD+Y7+B/bmOufkr/956y4wvQO34S6GwgonAcy9AKYcMeRwvjShiKdW13Dn\nSxv4/oLpiMgwPpxSyaGJQGWG7k5oqYtwYA9Z1t028PVZOc6BvbACiifDpGqn7d9/wPevK6yEnLyE\nhX3p0dP4ZIePX7+8kY7uXm74+kGaDFTa0USgRl5PN7Tvhdbd0LYnzM0ub9nV98u+bU/4beWN7zuI\nTznSuS+a4CwrKO97nDcOUnAAdmUJvzp7Du7sLH73P5vp6O7hptNmaDJQaUUTgRoeY6CzeeCv85b6\n/gf1wG0vdDRF2aBAXolz4M4vhdL9YepXQn692/uCCsjOHbGPOlRZWcKtZ8wiNzuLh17fQmd3Lz9f\nOIusLE0GKj1oIlDh9XQ5B/PgNvXAfciyrtaBrxeXczD33wonQPnBfc/zx9vHJf3LuYuHNJxDuhMR\nbjptBu5sl60Z9PLLs+fg0mSg0oAmgrGot9c5yDfWQONWe6sJel7jzMoVTt64vl/lkw8Pal8P+qVe\nNAE8JaPygD4cIsINXz8IT04Wd63YSGd3L3ecewjZLt1PKrU0EYxGXe39D+oD7rdBT8i17bmFUDzF\nOZG6z6HOtfMDDvIVkO1OzWcaJUSE7y84kNzsLH71l/V09fTy60WHkputyUCljiaCTNXeCLs/7bs1\nBD1uqQspLM6BvWSKc5A/+PS+g77/3lOckpOpY9XV8w/Ane3i5y98ROcfVvP/LqjGk+NKdVhqjNJE\nkM7a9tiD+2fQsLn/gb81pJNS0T7OidUDT4ZxU6F4X3ugnwzefcCVk5rPoCK6/KvTcGdn8S/PfsC3\nl6zi3gvnkZeryUCNPE0Eydbd6VxV09kSdGsOWtbcf7lvpz3Ybx54yaR3MpTuBwefBuP3g/H7O/fj\nqiA3PyUfTw3P4qOmkpudxQ1Pr+PSh9/hgYsPp8Ct/5ZqZOk3bjA9Xc4lj9Gudw++NLLfwb4FeuOY\npjAnH/LLnIP9zDNDDvZTE9rRSaWPc+dNwZ2dxfVPvs9FD77DQ5cejtejNTg1csZuIuhqhz2f9TW1\n7NniXCkTfGBv3QOdvsjbkCzn6pjgyx9LpkBuEeQWBN0KY3hcAFnaLDBWLZw7iVxXFv/r8fdYfP/b\nLLnsCEry07+PhBodRnci6Gztf7APtLN/Bk3bANNX1lPi9ET1X/NeMaP/Ab7fNe/2Gni3Vy+RVAlz\nyuyJ/M6VxdVL1/BP973No5cfQWmhXqWlkk+MMYOXinejIl8Hfg24gPuNMbdFKz9v3jyzatWq+N/I\nGOeXe2NN3wG/YbNzoN/9Kfi29y+fX9rX1DJ+P+fk6vhpzuO8cfG/v1JJsHJDPd9esop9x+ez9NtH\nUlHkSXVIKk2JyGpjzLxhbyfRiUBEXMAG4ESgBngXON8Y81Gk10RMBD1d0LQ9pLNTcOenGqctPlhB\necjB3t6Pm+b8olcqA7y5uYHLH3mXCV4PS799JBOL9fyQGihRiSAZTUNHAJuMMZ8CiMgTwEIgYiKg\nvQneuS+k01ONM01g6DDB+WXOJZGlB8D+X7OXR05yftmPmwYebxI+klIj68v7l7LksiO45KF3Off3\nb/KLM2ZrPwOVNMlIBJOArUHPa4Ajo75i92ZY/kNw5ToH9eLJsN/8vuvgiyc718V799HLJNWYMa9q\nPEuvOJILH3ibix58J9XhqFEsGYkgXPfUAe1PInIlcCXA/lMmwA/WOs06evJVqYBDppSw4vrj2FjX\nPHhhNeZ89ZeJ2U4yEkENMCXo+WRge2ghY8y9wL3gnCOgaOjTASo1mlV4PVR49YSxSp5k/Px+F5gu\nItNEJBdYBDyfhPdRSimVAAmvERhjukXkWuCvOJePPmiM+TDR76OUUioxktKhzBizHFiejG0rpZRK\nLD0zq5RSY5wmAqWUGuM0ESil1BiniUAppca4pAw6F3cQIj5gfarjiEEZsGvQUqmncSZOJsQIGmei\nZUqcBxljioa7kXQZhnp9IgZOSjYRWaVxJk4mxJkJMYLGmWiZFGcitqNNQ0opNcZpIlBKqTEuXRLB\nvakOIEYaZ2JlQpyZECNonIk2puJMi5PFSimlUiddagRKKaVSRBOBUkqNcSOaCETk6yKyXkQ2iciN\nYda7RWSZXf+2iFSNZHw2hiki8oqIfCwiH4rI98KUmS8ijSKy1t5uGuk4bRxbROQfNoYBl5GJ4267\nP9eJSPUIx3dQ0D5aKyJNIvL9kDIp25ci8qCI1InIB0HLxovISyKy0d6Pi/Dai22ZjSJy8QjH+O8i\n8on9m/5JRMJOxj3Y92ME4rxZRLYF/W1PjfDaqMeFEYhzWVCMW0RkbYTXjuT+DHscStr30xgzIjec\nIak3A/sBucD7wIyQMlcDv7OPFwHLRiq+oBgmAtX2cRGwIUyc84EXRjq2MLFuAcqirD8V+DPOrHFH\nAW+nMFYXsAOYmi77EjgWqAY+CFr2K+BG+/hG4JdhXjce+NTej7OPx41gjCcB2fbxL8PFGMv3YwTi\nvBn4YQzfi6jHhWTHGbL+P4Cb0mB/hj0OJev7OZI1gsCk9saYTsA/qX2whcAj9vFTwAkiEm7qy6Qx\nxtQaY9bYxz7gY5x5mDPRQmCJcbwFlIjIxBTFcgKw2RjzeYrefwBjzEpgd8ji4O/gI8AZYV56MvCS\nMWa3MWYP8BLw9ZGK0RjzojGm2z59C2cWwJSKsC9jEctxIWGixWmPNecCjyfr/WMV5TiUlO/nSCaC\ncJPahx5gA2XsF70RKB2R6MKwTVOHAm+HWf1lEXlfRP4sIjNHNLA+BnhRRFbbOaBDxbLPR8oiIv+D\npcO+9Ks0xtSC888IVIQpk0779TKcWl84g30/RsK1tgnrwQjNGOm0L48BdhpjNkZYn5L9GXIcSsr3\ncyQTQSyT2sc08f1IEJFC4Gng+8aYppDVa3CaOA4BfgM8O9LxWUcbY6qBU4BrROTYkPVpsT/FmbL0\nm8Afw6xOl30Zj3TZrz8BuoGlEYoM9v1ItnuA/YG5QC1Os0uotNiX1vlErw2M+P4c5DgU8WVhlkXd\npyOZCGKZ1D5QRkSygWKGVt0cFhHJwdn5S40xz4SuN8Y0GWOa7ePlQI6IlI1wmBhjttv7OuBPONXs\nYLHs85FwCrDGGLMzdEW67MsgO/3NZ/a+LkyZlO9XewLwNOACYxuGQ8Xw/UgqY8xOY0yPMaYXuC/C\n+6d8X0LgeHMWsCxSmZHenxGOQ0n5fo5kIohlUvvnAf8Z7nOAv0X6kieLbSd8APjYGHNHhDIT/Ocu\nROQInP3YMHJRgogUiEiR/zHOCcQPQoo9D1wkjqOARn+1coRF/KWVDvsyRPB38GLguTBl/gqcJCLj\nbHPHSXbZiBCRrwM3AN80xrRGKBPL9yOpQs5HnRnh/WM5LoyEBcAnxpiacCtHen9GOQ4l5/s5EmfA\ng85mn4pz9nsz8BO77BacLzSAB6f5YBPwDrDfSMZnY/gqTjVqHbDW3k4Fvgt815a5FvgQ5wqHt4Cv\npCDO/ez7v29j8e/P4DgF+H92f/8DmJeCOPNxDuzFQcvSYl/iJKdaoAvnV9TlOOekXgY22vvxtuw8\n4P6g115mv6ebgEtHOMZNOG3A/u+n/0q7fYDl0b4fIxzno/Z7tw7nADYxNE77fMBxYSTjtMsf9n8n\ng8qmcn9GOg4l5fupQ0wopdQYpz2LlVJqjNNEoJRSY5wmAqWUGuM0ESil1BiniUCNCSJSIiJXD+F1\nP05GPEqlE71qSI0Jtpv+C8aYWXG+rtkYU5iUoJRKE1ojUGPFbcD+dgjhfw9dKSITRWSlXf+BiBwj\nIrcBeXbZUltusYi8Y5f9XkRcdnmziPyHiKwRkZdFpHxkP55SQ6c1AjUmDFYjEJEfAB5jzC/swT3f\nGOMLrhGIyME4wwCfZYzpEpH/BN4yxiwREQMsNsYsFWdOhQpjzLUj8dmUGq7sVAegVJp4F3jQju/y\nrDEm3OQkJwCHAe/aUTHy6BvrpZe+cWr+AAwYo0qpdKVNQ0oRGKf+WGAb8KiIXBSmmACPGGPm2ttB\nxpibI20ySaEqlXCaCNRY4cOZ6SksEZkK1Blj7sMZ7Ms/rWeXrSWAM7bLOSJSYV8z3r4OnP+lc+zj\nfwJeS3D8SiWNNg2pMcEY0yAir4szV+2fjTE/CikyH/iRiHQBzYC/RnAvsE5E1hhjLhCRf8GZnCQL\nZ+Cya4DPgRZgpoisxplQ6bzkfyqlEkNPFiuVAHqZqcpk2jSklFJjnNYI1JgiIrNxxskP1mGMOTIV\n8SiVDjQRKKXUGKdNQ0opNcZpIlBKqTFOE4FSSo1xmgiUUmqM00SglFJjnCYCpZQa4/4/tFbef8jw\niGoAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plot_all('soil_output/Spread_barabasi_albert_graph_prob_0.0/', get_count, 'id');" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:57:57.982007Z", + "start_time": "2017-10-19T17:57:52.273160+02:00" + }, + "scrolled": false + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niGoAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niGoAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xd4FNX6wPHvm0YSSkIvSei9BKQLUpQmWMAK/kTFcrEh\neq3YELF7bVe9otjxomJFLqI0QZp0AekECL2XQEiAkJzfHzOJS9gkG7K7s8m+n+fZZ3dnzsy8Ozs7\n786cmXPEGINSSqngFeJ0AEoppZyliUAppYKcJgKllApymgiUUirIaSJQSqkgp4lAKaWCnCaCEkxE\nPhOR5wso011EdgZSTOcxz5oikioioUWYx1nrQUSSRaSndyIMXCIyRETmBUAcQbG+A5UmAi8QkYtE\nZIGIpIjIYRGZLyLtnI4rWBhjthtjyhhjMp2OJS+6o/MNEekhIutFJE1EZolIrTzKVRGRr0Rkt/07\nnS8iHfwdb6DSRFBEIlIOmAy8A1QA4oBngVOFnI+ISLH+PkQkzOkYAo2v10lxWOe+ilFEKgE/AE9j\n/faWAhPyKF4GWAK0sct+DvwsImV8EVtxU6x3PAGiIYAx5itjTKYxJt0YM80Ys8o+7J4vIu/Y/0LW\ni0iP7AlFZLaIvCAi84E0oK6IxIjIxyKyR0R2icjz2ac8RKSeiPwmIodE5KCIjBeRWJf5XSAiy0Xk\nuIhMACI9/RAi8oQ9z2QRudFl+GUi8qeIHBORHSIyymVcbRExInK7iGwHfrOHfysie+3PPEdEmuVa\nXCURmW7H+bvrvzgR+be9nGMiskxEuriMay8iS+1x+0TkjVxx5LvDEZFbRWSdvdwtInJnAaulnYis\nFZEjIvKpiOSsTxG5XERWiMhR+2gw0WVcsog8JiKrgBMi8hVQE/iffQrr0QLivFlEttnf89OuRxMi\nMkpEvhOR/4rIMWCIvV7+sGPZIyLvikiEy/yMiAy3P/NBEflX7j8dIvKa/Tm3ikjfAtZL9rb7kogs\ntr/nn0Skgj0ur+3iShFZY8c5W0SaeLq+83A1sMYY860x5iQwCmgpIo1zFzTGbDHGvGGM2WP/TscC\nEUCjgj5rUDDG6KMID6AccAjrH0ZfoLzLuCHAGeCfQDgwEEgBKtjjZwPbgWZAmF1mIvABUBqoAiwG\n7rTL1wd6AaWAysAc4C17XASwzWVZ1wIZwPMFxN/djvENe77dgBNAI5fxLbD+NCQC+4AB9rjagAHG\n2fFG2cNvA8ra83sLWOGyvM+A40BXe/y/gXku4wcDFe318RCwF4i0x/0B3GS/LgN0zBVHWAGf9TKg\nHiD250wDWrt8zp0uZZOB1UAC1j/I+dnrEmgN7Ac6AKHALXb5Ui7TrrCnjXIZ1tOD7akpkApcZH+n\nr9nfY097/Cj7/QD7O4nC+pfb0V5ntYF1wAMu8zTALPtz1AQ2Ane4bKMZwD/sz3I3sBuQAuKcDewC\nmtvf/ffAf/PaLrD+MJ3A2n7DgUeBJCCioPWdTwz/BsbkGrYauMaD9dwKOAnEOL0PCYSH4wGUhAfQ\nBGsHtxNrpzoJqGr/yM76UWHt2LN3ZrOB0S7jqmKdUopyGXYDMCuP5Q4A/rRfd3WzrAUe/Ji62zGX\ndhn2DfB0HuXfAt60X2f/4OvmM/9Yu0yM/f4z4GuX8WWATCAhj+mPAC3t13OwTrtVylUmO458E4Gb\neU8E7ndZD7kTwV0u7/sBm+3XY4Dncs1rA9DNZdrbco1PxrNEMBL4yuV9NHCasxPBnALm8QDwo8t7\nA1zq8v4eYKb9egiQlGt5BqhWwDJmAy+7vG9qxxnqbrvAOn3zjcv7EKxE0r2g9Z1PDB+7xmAPmw8M\nKWC6csBfwOOF2V5K8kNPDXmBMWadMWaIMSYe6x9SDawdJsAuY299tm32+Gw7XF7Xwvq3tMc+fD6K\ndXRQBXIqvL62TxkdA/4LVLKnrZHHsjxxxBhzwl2MItJBrEq4AyKSAtzlssxzPoOIhIrIyyKy2Y4x\n2R5VyV15Y0wqcNhleQ/Zp29S7M8f4zLt7Vj/LNeLyBIRudzDz5cdW18RWShWhf5RrJ1N7s/i9nNx\n9vdWC3go+zuy55VA3t9rYdTg7PWThnXEmVdciEhDEZlsn447BrxIPt8R526De3MtD6wEXZDc8wwn\nj+/ZXl7O9miMybLHx3kYozupWDt1V+WwjjjdEpEo4H/AQmPMSwXMP2hoIvAyY8x6rH+9ze1BcSIi\nLkVqYv1zz5nE5fUOrCOCSsaYWPtRzhiTfY79Jbt8ojGmHNZplOx578ljWZ4oLyKl84jxS6wjnARj\nTAzwvssy3X2G/wP6Az2xduK17eGu0yRkvxCrsq4CsNuuD3gMuB7rFFss1qk0ATDGbDLG3ICVGF8B\nvssVd55EpBTW6YvXgKr2vKe4+SyuElxeu66THcALLt9RrDEm2hjzlUv53M36etrM7x4g3iXuKKxT\nZfnNawywHmhgbxdPcO7nyuuzFEXueWYAB/OIczdWAgWsiyPs6XcVIcY1QEuXeZbGOvW3xl1hexuY\naC+zoPqhoKKJoIhEpLH9Lzbefp+AdTpnoV2kCjBcRMJF5Dqs00hT3M3LGLMHmAa8LiLlRCRErAri\nbnaRslj/go6KSBzwiMvkf2Cd4hkuImEicjXQvhAf5VkRibB3xpcD37os87Ax5qSItMfa0eenLFYy\nO4R1muFFN2X6iXXJbQTwHLDIGLPDnvYMcAAIE5GRuPzjE5HBIlLZ/jd51B7s6SWjEVh1EgeAM3aF\naO8CprlXROLtStAn+PuKlA+Bu+yjJRGR0mJVqpfNZ177gLoexPkdcIWIdLLXz7Pkn6zAWm/HgFS7\novRuN2UeEZHy9vZ5P3lfXVMYg0WkqYhEA6OB70zel/B+A1wm1uWe4Vj1P6ewTl9my2t95+VHoLmI\nXGNXLI8EVtl/xs5iL/M7IB242d6GlE0TQdEdx6o0XCQiJ7ASwGqsDR1gEdAA65/SC8C1xpjch/qu\nbsbaaa3FOj/+HVDdHvcsVkVlCvAz1qVzABhjTmNdRTHEnm6g6/gC7LWn2Q2MxzpXm/1jugcYLSLH\nsX5o3xQwr3FYh/W77M+w0E2ZL4FnsE4JtQGyr1KaCvyCVZm5Dasyz/V0waXAGhFJxaooHGSsq0UK\nZIw5Dgy34z+CldAmFTDZl1iJeYv9eN6e11KsytV37XklYa33/LwEPGWfSno4nzjXAPcBX2MdHRzH\nqpjO73Lkh+3PcxwrSbnbgf4ELMOqxP4Z6/x6UX2BdfS7F+sKteF5FTTGbMA6gn0H67dwBXCFvd1m\nc7u+85nnAeAarN/VEazf4aDs8SLyvoi8b7/thPUHpzfWH6lU+9EFZVUsKt8QkSFYV2dc5HQsqniy\nT50dxTrts/U852Hs6ZO8GNdsrKuEPvLWPJVz9IhAqQAjIleISLR9zvs1rCtckp2NSpVkmgiCgFg3\ni6W6efzidGzelsfnDKhTACJyYx4xZldy9sc6Tbcb67TiIOPAoXsgrMtg2nadpKeGlFIqyOkRgVJK\nBTlNBEopFeQCouXCSpUqmdq1azsdhlJKFSvLli07aIypXNT5BEQiqF27NkuXLnU6DKWUKlZExNNm\nZPKlp4aUUirIaSJQSqkgp4lAKaWCnCYCpZQKch4lArG6yvtLrK75ltrDKojV3eAm+7m8PVxE5G0R\nSRKRVSLS2pcfQCmlVNEU5ojgYmNMK2NMW/v9CKxejhoAM+33YHXX2MB+DMVqK10ppVSAKsqpof5Y\n/fRiPw9wGT7OWBYCsSJS3d0MlFJKOc/T+wgMMM1uzvYDY8xYrF6e9oDVoYqIVLHLxnF2G/I77WF7\n8pr5uj3HaPPc9EIH7yoqIpTy0RHERocTExVObHQ4sVHW+9joCGKzh0WHE2MPDw/VKhLlY0s/hVkv\ngLbppQKYp4mgszFmt72zny4i5/QA5MJdb0rn/ApEZCjWqSNia9Slb4tqHobiZuYG0k9nciTtNEfT\nM9h1JJ2j6RkcTTtNVj6/vzKlwnKSRvnoCKrFRFIjNoq42OznKGrERhEZHnresakgdvIYzHwWytaA\nmh2djkaVSG96ZS4eJQJjzG77eb+I/IjVBeI+EaluHw1Ux+pFCawjANe+R+Nx0/eofVQxFqBt27bm\n+QEtzv9T5CEry5B6+gxHT2RwNP00R9MyOJqeQUra36+PpJ0mJS2Dw2mnmZ90kH3HTp6TPCqWjqBG\nbBQ1YiOJi422n6PsYVFUKhOBSEG9Caqgs3AMpB+BwT9AnF4zoXzBT4nA7hwjxBhz3H7dG6t/0knA\nLcDL9vNP9iSTgGEi8jVW13Ep2aeQ/C0kRCgXGU65yHBqEu3RNBmZWexNOcnuo+nsTkln15F0dh21\n3m85cIK5mw6SdvrsblkjwkKIi42iVsVoOtSpSKd6FWkeF0NoiCaHoJV2GP54FxpfrklABTxPjgiq\nAj/a/3jDgC+NMb+KyBLgGxG5HdgOXGeXnwL0w+rHNQ241etR+1B4aAgJFaJJqOA+cRhjSEnPYNfR\ndHbbCWKX/di49zivbLDOmpWNDKNj3Yp0rleRTvUr0aBKGT1qCCYL3oFTx+HiJ5yORKkCFZgIjDFb\ngJZuhh8CergZboB7vRJdABIRq/I5OoJmNWLOGb//+En+2HyIPzYfYv7mg0xfuw+ASmVK0aleRTrX\nr0inepXyTDSqBEjdD4veh+bXQNVmTkejVIECovXRkqRK2Uj6t4qjf6s4AHYcTmPB5oMs2HyI+UmH\nmLTSqi5JqBBFp7qV6FS/IhfWq0iVspFOhq28ad6bcOYkdH/c6UiU8ogmAh9LqBDNwAo1GdiuJsYY\nkvanMj/JSgxTVu9hwlLrStuGVcvQqV4l+reqwQU1yzsctTpvKbtgycfQ8v+gUn2no1HKI5oI/EhE\naFC1LA2qlmVI5zpkZhlW70phweZDLNh8kK+XbOeLhdt4ol8TbutcW+sUiqO5r4HJgm6POh2JUh7T\nROCg0BChZUIsLRNiubt7PY6fzOChb1by3OS1rNmVwotXt9B7GIqTI8mwfBy0GQLlazkdjVIe01tr\nA0jZyHDeH9yGB3s15Ic/d3Hd+3+w62i602EpT/3+KoSEQZeHnY5EqULRRBBgQkKE4T0a8NHNbUk+\neIIr35nHwi2HnA5LFeTARlj5FbS7A8pp01qqeNFEEKB6Nq3KxGGdiYkOZ/BHi/h8QTJG26sJXLNf\ngrAo6PyA05EoVWiaCAJYvcplmHhvZ7o3qswzk9bw6HerOJmRWfCEyr/2roY1P0DHu6BMZaejUarQ\nNBEEuHKR4Yy9qS3DezTg22U7GTh2IXtStN4goMx6EUrFQKf7nI5EqfOiiaAYCAkRHuzVkA9uakPS\nvuNc8c58liQfdjosBbBrGWz42UoCUXr/hyqeNBEUI32aVWPivZ0pGxnGDWMX8t+F27TewGm/PQ9R\nFazTQkoVU5oIipkGVcsy8d7OdGlQiacmrubxH/7i1BmtN3BE8nzY/Btc9E8oVdbpaJQ6b5oIiqGY\nqHA+uqUdwy6uz9dLdjBo7EL2HTvpdFjBxRjraKBMVeuSUaWKMU0ExVRoiPBwn0a8d2NrNuw9zuXv\nzGPZtiNOhxU8tsyC7Qusm8citCVZVbxpIijm+rWozo/3dCYqPJRBY//g68XbnQ6p5Ms+GohJgDa3\nOB2NUkWmiaAEaFStLJOGdaZj3YqM+OEvPpyzxemQSrYNv1hXC3V7FMJKOR2NUkWmiaCEiI2O4LNb\n29OzSVVen76BHYfTnA6pZMrKglkvQIW60PIGp6NRyis0EZQgoSHC6P7NEITRk9c6HU7JtHYi7Ftt\ndToTGu50NEp5hSaCEqZGbBTDezRg+tp9/LZ+n9PhlCyZZ6y7iCs3trqhVKqE0ERQAt1+UR3qVynD\nM5PWaNtE3vTXt3Bok9UhfYj2E6FKDk0EJVBEWAijr2zGjsPpjJm92elwSobMDKuF0WqJ0ORKp6NR\nyqs0EZRQnepX4oqWNRjz+2a2HTrhdDjF359fwNFtcMnToF2IqhJGE0EJ9tRlTYgIDeGZSWu0TaKi\nyDgJv/8L4ttDg15OR6OU12kiKMGqlovkgZ4NmL3hAFPXaMXxeVv2KRzfDZc8pUcDqkTSRFDCDelU\nm8bVyjL6f2tIO33G6XCKn9MnYO7rULsL1O3mdDRK+YQmghIuLDSE5wY0Z3fKSd79LcnpcIqfxWPh\nxAGrbkCpEkoTQRBoV7sC17SO58O5W0jan+p0OMXHyRSY9xY06A01OzgdjVI+o4kgSDzerzGR4aE8\nM2m1Vhx7atpTcOoYXPyk05Eo5VOaCIJEpTKleKRPI+YnHWLyqj1OhxP4Nk6F5eOg03Co0crpaJTy\nKU0EQeTGDrVoHleO539eS+oprTjOU9phmHQfVGlq3UWsVAmniSCIhIYIz/Vvzv7jp3hr+kanwwlc\nUx6GtENw1fvazLQKCh4nAhEJFZE/RWSy/b6OiCwSkU0iMkFEIuzhpez3Sfb42r4JXZ2PC2qWZ1C7\nBD5dkMz6vcecDifwrP4BVn8P3UZA9ZZOR6OUXxTmiOB+YJ3L+1eAN40xDYAjwO328NuBI8aY+sCb\ndjkVQB7t05hykWGMnKh3HJ/l+F74+UGIa2N1SK9UkPAoEYhIPHAZ8JH9XoBLgO/sIp8DA+zX/e33\n2ON72OVVgChfOoLHLm3M4uTD/PjnLqfDCQzGwKThkJEOA96H0DCnI1LKbzw9IngLeBTIst9XBI4a\nY7JrHHcCcfbrOGAHgD0+xS5/FhEZKiJLRWTpgQMHzjN8db6ub5tAq4RYXpyyjpT0DKfDcd6fX8Cm\nqdDjGajc0OlolPKrAhOBiFwO7DfGLHMd7Kao8WDc3wOMGWuMaWuMaVu5cmWPglXeExIiPD+gOYdP\nnOaNaRucDsdZR7bBr49bzUh0uMvpaJTyO0+OCDoDV4pIMvA11imht4BYEck+fo4HdtuvdwIJAPb4\nGOCwF2NWXtI8LobBHWvxxcJtrN6V4nQ4zsjKgp/uBQT6/wdC9EI6FXwK3OqNMY8bY+KNMbWBQcBv\nxpgbgVnAtXaxW4Cf7NeT7PfY438zWiMZsB7q3YgKpSN4auJqsrKC8Gta/AEkz4VLX4TytZyORilH\nFOXvz2PAgyKShFUH8LE9/GOgoj38QWBE0UJUvhQTFc7jfZuwYsdRvl22w+lw/OvARpgxChr0gQtu\ncjoapRxTqEsjjDGzgdn26y1AezdlTgLXeSE25SdXt45jwpIdvPzLeno3rUb50hFOh+R7mWdg4l0Q\nHgVXvq39DKigpidEFSLC6AHNOHbyDK9ODZKK4/lvwq5lcNnrULaa09Eo5ShNBAqAxtXKcWun2ny9\nZDsrdhx1Ohzf2rMKZr8Cza6G5tc4HY1SjtNEoHLc37MBlcuU4qmJf5FZUiuOz5yCH++E6ArW0YBS\nShOB+lvZyHCeurwpq3cd46vF250OxzdmvQj718KV71rJQCmliUCd7YrE6nSsW4HXpm3gaNppp8Px\nru2LYMHb0PpmaNjb6WiUChiaCNRZRIRRVzbj+MkzvD6tBDVVffqEdUooJh76vOh0NEoFFE0E6hyN\nq5Xjpo61GL9oG2t3l5Cmqqc/A0e2Qv/3oFRZp6NRKqBoIlBu/bNnQ2KjIxg1qQQ0Vb15Fiz5EDre\nA3W6OB2NUgFHE4FyKyY6nEf6NGJx8mH+V5z7OE4/arUlVKkh9BjpdDRKBSRNBCpP17dNoHlcOV78\neR0nimsfx7+OsDqcuep96y5ipdQ5NBGoPIWGCM9e2Yy9x07yn1lJTodTeOsmw8qvoMtDVq9jSim3\nNBGofLWpVYGrL4jjo7lbST54wulwPJd2GCY/ANUSoesjTkejVEDTRKAKNKJvY8JDhecmr3U6FM/9\n9hykHbL6GAgLgkb0lCoCTQSqQFXKRTK8RwNmrt/PrPX7nQ6nYLuWw9JPof2dUD3R6WiUCniaCJRH\nbu1ch7qVSjN68lpOncl0Opy8ZWXCzw9BmSpw8eNOR6NUsaCJQHkkIiyEkVc0ZevBE3w6P9npcPK2\n/HPYvRx6vwCRMU5Ho1SxoIlAeax7oyr0bFKVd2ZuYt+xk06Hc64TB2HGs1Yn9C2uLbi8UgrQRKAK\naeTlTcnIMrz8y3qnQznXjGfgdCr0e017HFOqEDQRqEKpWTGaoV3q8uOfu1iafNjpcP62fRH8+V+r\nGYkqjZ2ORqliRROBKrR7Lq5H9ZhIRv60JjA6sMk8Y1UQl4uDbo85HY1SxY4mAlVo0RFhPNGvCWv3\nHOPrJQHQgc3Sj2HfX1bz0qXKOB2NUsWOJgJ1Xi5PrE6HOhV4barDHdgc3we/PQ/1LoGm/Z2LQ6li\nTBOBOi/ZHdikpGfwxnQHO7CZ/jScOakVxEoVgSYCdd6aVLc6sPnvQoc6sEmeB6smQOf7oWI9/y9f\nqRJCE4Eqkn/2akhMVDij/ufnDmwyM+DnhyGmJlz0oP+Wq1QJpIlAFUlsdASP9GnM4q1+7sBm4Rg4\nsA76vgIR0f5brlIlkCYCVWQD2/3dgU3aaT90YJOyC2a/DA0vhcb9fL88pUo4TQSqyPzegc3UJ8Bk\nWkcDSqki00SgvCK7A5sP52xl2yEfdmCz+TdYO9Hqdax8bd8tR6kgoolAeY3PO7A5cwqmPAIV6kKn\n4b5ZhlJBKKygAiISCcwBStnlvzPGPCMidYCvgQrAcuAmY8xpESkFjAPaAIeAgcaYZB/FrwJIdgc2\nL/2ynlkb9nNxoyreXcCCd+BQEgz+HsIjvTtvdY6MjAx27tzJyZMB2NJskImMjCQ+Pp7w8HCfzL/A\nRACcAi4xxqSKSDgwT0R+AR4E3jTGfC0i7wO3A2Ps5yPGmPoiMgh4BRjok+hVwLm1cx0mLNnBc/9b\nS5f6lQgL9dJB55FtMOc1aHIl1O/pnXmqfO3cuZOyZctSu3ZtRG/Wc4wxhkOHDrFz507q1Knjk2UU\n+Cs1llT7bbj9MMAlwHf28M+BAfbr/vZ77PE9RLeioBERFsJjfRuz5eAJfv7Li5eT/vq4defwpS95\nb54qXydPnqRixYqaBBwmIlSsWNGnR2Ye/V0TkVARWQHsB6YDm4GjxpjsawV3AnH26zhgB4A9PgWo\n6M2gVWDr1aQq9auU4f3ft3jnJrONU2HDz9DtUYiJL/r8lMc0CQQGX38PHiUCY0ymMaYVEA+0B5q4\nK2Y/u4v4nL2BiAwVkaUisvTAgQOexquKgZAQYWjXuqzbc4w5mw4WbWYZ6VYFcaVG0PFe7wSoAk5y\ncjLNmzcP2uU7rVAncI0xR4HZQEcgVkSy6xjigd32651AAoA9PgY4pwcTY8xYY0xbY0zbypUrn1/0\nKmANaBVHtXKRvD97c9FmNO8tOLoNLnsNwiK8E5xS6iwFJgIRqSwisfbrKKAnsA6YBWR3DHsL8JP9\nepL9Hnv8b8avjdCoQBARFsLtF9Xhjy2HWLnj6PnN5PAWmPcmNL8W6nT1boAqYG3ZsoULLriARYsW\n8cgjj9CuXTsSExP54IMPALjpppv46aefcsrfeOONTJo06ax5DBw4kClTpuS8HzJkCN9//z3Jycl0\n6dKF1q1b07p1axYsWHDO8j/77DOGDRuW8/7yyy9n9uzZAEybNo0LL7yQ1q1bc91115GamnrO9MWR\nJ0cE1YFZIrIKWAJMN8ZMBh4DHhSRJKw6gI/t8h8DFe3hDwIjvB+2Kg5u6FCTcpFhvP/7eRwVGANT\nHoXQCOjzgveDUwFpw4YNXHPNNXz66aesXLmSmJgYlixZwpIlS/jwww/ZunUrd9xxB59++ikAKSkp\nLFiwgH79zm5qZNCgQUyYMAGA06dPM3PmTPr160eVKlWYPn06y5cvZ8KECQwf7vn9KAcPHuT5559n\nxowZLF++nLZt2/LGG29478M7qMDLR40xq4AL3AzfglVfkHv4SeA6r0SnirUypcK46cJavDd7M1sO\npFK3ciF6D1s/GZKmQ5+XoGw13wWpAsaBAwfo378/33//Pc2aNeP5559n1apVfPeddXFiSkoKmzZt\nonfv3tx7773s37+fH374gWuuuYawsLN3ZX379mX48OGcOnWKX3/9la5duxIVFUVKSgrDhg1jxYoV\nhIaGsnGj531pLFy4kLVr19K5c2fASjAXXnih91aAgzy5j0Cp8zakUx0+nLuVD+du4aWrEz2bKCsT\npj8DVZpB+6G+DVAFjJiYGBISEpg/fz7NmjXDGMM777xDnz59zil70003MX78eL7++ms++eSTc8ZH\nRkbSvXt3pk6dyoQJE7jhhhsAePPNN6latSorV64kKyuLyMhzb0wMCwsjKysr5332ZZvGGHr16sVX\nX33lrY8cMLSJCeVTlcuW4vq28Xy/bBf7j3l4HfS6/8HhzdbloqH6XyVYREREMHHiRMaNG8eXX35J\nnz59GDNmDBkZGQBs3LiREyesdqyGDBnCW2+9BUCzZs0A2LVrFz169MiZ36BBg/j000+ZO3duTjJJ\nSUmhevXqhISE8MUXX5CZmXlOHLVr12bFihVkZWWxY8cOFi9eDEDHjh2ZP38+SUlWw4ppaWmFOqII\nZJoIlM8N7VKPM1lZfDx/a8GFjYH5b0GFetDkCt8HpwJK6dKlmTx5cs4/96ZNm9K6dWuaN2/OnXfe\nyZkz1q1LVatWpUmTJtx666050+7Zs+esU0S9e/dmzpw59OzZk4gI64qze+65h88//5yOHTuyceNG\nSpcufU4MnTt3pk6dOrRo0YKHH36Y1q1bA1C5cmU+++wzbrjhBhITE+nYsSPr16/35erwGwmEC3ra\ntm1rli5d6nQYyoeGfbmc3zccYP7jl1AuMp/2Urb8DuOuhMvfgra35l1O+dy6deto0sTdLUPOS0tL\no0WLFixfvpyYmBgA3n33XWrWrMmVV17pcHS+4e77EJFlxpi2RZ23HhEov7irWz2OnzrD+IXb8y84\n/y0oUxVa3uCfwFSxM2PGDBo3bsx9992XkwQAhg0bVmKTgK/pCVjlF83jYujSoBKfzN/KrZ1rExke\nem6hPSut/gZ6jtLWRVWeevbsyfbtBfyhUIWiRwTKb+7qVo8Dx0/x45+73BeY/28oVQ7a3ubfwJQK\ncpoIlN8qPKjWAAAf+klEQVR0qleRFnExjJ2zhcysXHVTh7fCmh+teoHIGPczUEr5hCYC5Tciwl3d\n6rH14Ammrdl79sgF70BIGHS8x5nglApimgiUX13avBq1K0bz/u+b/26iOvUArBgPLQfpXcRKOUAT\ngfKr0BBhaNd6rNyZwh9bDlkDF71v9Ufc6X5ng1MBJz09nW7dupGZmcnu3bu59tpr3Zbr3r07/rwE\n/a233iItLa3Q0w0ZMiSnyYxBgwaxadMmb4d2XjQRKL+7unUclcqUYszszXDqOCz5EJpcDpXqOx2a\nCjCffPIJV199NaGhodSoUSNnJ+q0/BKBu7uV3bn77rt59dVXvRnWedNEoPwuMjyU2y6qzdxNB9nz\n2wdwMgU6/9PpsFQAGj9+PP379wfO7jwmPT2dQYMGkZiYyMCBA0lPTy9wXt27d+exxx6jffv2NGzY\nkLlz5wLWjttdc9ezZ8/m8ssvz5l+2LBhfPbZZ7z99tvs3r2biy++mIsvvhiAMmXKMHLkSDp06MAf\nf/zB6NGjadeuHc2bN2fo0KFue+rr0qULM2bMyLlb2kl6H4FyxI0dajF21gYil42B2l0gvo3TIal8\nPPu/Nazdfcyr82xaoxzPXNEsz/GnT59my5Yt1K5d+5xxY8aMITo6mlWrVrFq1aqcZiAKcubMGRYv\nXsyUKVN49tlnmTFjBh9//HFOc9enTp2ic+fO9O7dO895DB8+nDfeeINZs2ZRqVIlAE6cOEHz5s0Z\nPXq09dmaNmXkyJGA1UDe5MmTueKKs5tMCQkJoX79+qxcuZI2bZzd/vWIQDkiJiqc5+uupfyZg+xP\nvNvpcFQAOnjwILGxsW7HzZkzh8GDBwOQmJhIYqJnLdteffXVALRp04bk5GTA6mxm3LhxtGrVig4d\nOnDo0KFCn7sPDQ3lmmuuyXk/a9YsOnToQIsWLfjtt99Ys2aN2+mqVKnC7t273Y7zJz0iUM7IyuLS\nlG9Ya2rz1baaPOfZHzrlkPz+uftKVFRUThPQ7pxPh+6lSpUCrB139imZvJq7njdvntvmqN2JjIwk\nNDQ0p9w999zD0qVLSUhIYNSoUXlOe/LkSaKiogr9ObxNjwiUMzb+QtjhjaxIuIVvlu3kYOoppyNS\nAaZ8+fJkZma63Yl27dqV8ePHA7B69WpWrVqVM+7mm2/OaTraE3k1d12rVi3Wrl3LqVOnSElJYebM\nmTnTlC1bluPHj7udX3a8lSpVIjU1Nd8K7o0bN+Y0o+0kTQTK/4yxOqWPrUWHK27jdGYWny9Idjoq\nFYB69+7NvHnzzhl+9913k5qaSmJiIq+++irt2//dWeKqVauoXr26x8u444473DZ3nZCQwPXXX09i\nYiI33ngjF1zwd0eNQ4cOpW/fvjmVxa5iY2P5xz/+QYsWLRgwYADt2rVzu9x9+/YRFRVVqFh9xhjj\n+KNNmzZGBZHk+cY8U86YRWONMcbcOW6pSRw11aSezHA4MOVq7dq1Todgli9fbgYPHuxx+ZSUFHPt\ntdf6MCLveeONN8xHH33kcXl33wew1HhhH6xHBMr/5r0F0RWh1Y0A3NW9HinpGXy1WFuUVGe74IIL\nuPjiiz2+Nr9cuXJ8++23Po7KO2JjY7nlllucDgPQU0PK3/athU1TocNdEBENQKuEWDrWrcBHc7dy\n+kxWATNQwea2227LqYgtSW699dazelRzkiYC5V/z/w3hpaHdHWcNvqtbPfYeO8lPK/Joolop5TOa\nCJT/HN0Bq7+DNkMgusJZo7o1rEyT6uX4YM4WsnI3Ua2U8ilNBMp//viP9XzhuU1NW01U1yVpfyoz\n1+/3c2BKBTdNBMo/0g7D8s+hxfUQE++2yGUtqhNfPor3f9/s5+CUCm6aCJR/LB4LGWnQOe+mpsNC\nQxjatS7Lth1hSfJhPwanApU3m6EeOXIkM2bMyLfMqVOn6NmzJ61atWLChAmFijU5OZkvv/yyUNNA\nYDRNrYlA+d7pE7DoA2jYF6o0zrfodW0SqFA6gvdn61GB8m4z1KNHj6Znz575lvnzzz/JyMhgxYoV\nDBw4sFDzP99E4Mqppqk1ESjf+/O/kH4YLnqgwKJREaEM6VSbmev3s2Gv+1v4VfDwZjPUrv+8a9eu\nzTPPPEPr1q1p0aIF69evZ//+/QwePJgVK1bQqlUrNm/ezLJly+jWrRtt2rShT58+7NmzB4CkpCR6\n9uxJy5Ytad26NZs3b2bEiBHMnTuXVq1a8eabb+bZvLUxhmHDhtG0aVMuu+wy9u//u07MqaapA+Mi\nVlVyZWbAgnchoSPU7OjRJDdfWIv3f9/Me7OT+PegCwqeQPneLyNg71/enWe1FtD35TxH+6IZaleV\nKlVi+fLlvPfee7z22mt89NFHfPTRR7z22mtMnjyZjIwMbrrpJn766ScqV67MhAkTePLJJ/nkk0+4\n8cYbGTFiBFdddRUnT54kKyuLl19+OWdagLFjx7pt3vrPP/9kw4YN/PXXX+zbt4+mTZty2223Ac41\nTa2JQPnWmh8hZTv08/xwNzY6gls71+Y/szZzU8datK1doeCJVIlTUDPUw4cPBwrXDLUr1yapf/jh\nh3PGb9iwgdWrV9OrVy/A6sCmevXqHD9+nF27dnHVVVcBVsuj7kybNo1Vq1blHIWkpKSwadMm5syZ\nww033JBzuuuSSy45a7rspqk1EaiSwRjrBrLKjaFBn4LLu7j34vpM/HM3T01czeT7LiIsVM9iOiqf\nf+6+4otmqF25a5LalTGGZs2a8ccff5w1/NgxzzroMXk0bz1lypR8Y3eiaeoCf10ikiAis0RknYis\nEZH77eEVRGS6iGyyn8vbw0VE3haRJBFZJSLa0nywSpoB+1ZD5wcgpHA78uiIMJ6+vCnr9x7n8z+2\n+ShAFcj81Qx1Xho1asSBAwdyEkFGRgZr1qyhXLlyxMfHM3HiRMC60igtLe2cpqnzat66a9eufP31\n12RmZrJnzx5mzZp11nKdaJrak1/nGeAhY0wToCNwr4g0BUYAM40xDYCZ9nuAvkAD+zEUGOP1qFXx\nMO9NKBcPLdxf8leQPs2q0r1RZd6cvpF9x/L+Z6hKLn80Q52XiIgIvvvuOx577DFatmxJq1atWLBg\nAQBffPEFb7/9NomJiXTq1Im9e/eSmJhIWFgYLVu25M0338yzeeurrrqKBg0a0KJFC+6++266deuW\ns0zHmqYubHOlwE9AL2ADUN0eVh3YYL/+ALjBpXxOubwe2gx1CbR9sdXU9IL/FGk2yQdTTYMnp5j7\nvlzupcCUp7QZav/Lr2nqgGmGWkRqAxcAi4Cqxpg9djLZA1Sxi8UBO1wm22kPyz2voSKyVESWHjhw\noDBhqOJg/lsQGQutby7SbGpVLM3d3eoxaeVuFiQd9FJwqrgoyc1Qu+NU09QeJwIRKQN8DzxgjMmv\ntsRdLcg5rYgZY8YaY9oaY9pWrlzZ0zBUcXBgI6z/GdoPhVJlijy7u7vXI6FCFE//tFqbqQ5CJbUZ\nanecaprao0QgIuFYSWC8MSb7Oqt9IlLdHl8dyL4rYieQ4DJ5PLDbO+GqYmHWCxAWCR3u9MrsIsND\nefbKZmw+cIKP5231yjyVUn/z5KohAT4G1hlj3nAZNQnIPoa5BavuIHv4zfbVQx2BlOxTSCoIbPkd\n1k6ELg9C6Upem+0ljavSq2lV3p65id1HC76LVHmHdRpaOc3X34MnRwSdgZuAS0Rkhf3oB7wM9BKR\nTViVx9kXGk8BtgBJwIfAuW0Oq5IpMwN+eQxia0Gn4V6f/TNXNMVgeG7yWq/PW50rMjKSQ4cOaTJw\nmDGGQ4cO5XnjmjcUeDLKGDMP9+f9AXq4KW+Ae4sYlyqOlnwMB9bBwPEQ7v2NNr58NPdd0oB/Td3A\n7xsP0K2h1i35Unx8PDt37kQv5nBeZGQk8fHum2/3BgmEbN+2bVtTUBOyKsClHoB32kB8Gxj8AxTx\nrs+8nDqTSd+35pJlDL8+0JXI8OCoRFTKHRFZZoxpW9T56H37yjt+Gw0ZJ+DSV3yWBABKhYUyun9z\nkg+lMXbOFp8tR6lgoolAFd2u5bD8C+hwF1Ru6PPFXdSgEpclVuc/s5LYcTjN58tTqqTTRKCKJisL\nfnkUSleGbo/5bbFPX9aU0BBh1KQ1flumUiWVJgJVNKu+hp1LoNezEFnOb4utFhPJAz0bMHP9fqav\n3ee35SpVEmkiUOfv5DGY/gzEt4PEQX5f/K2d69CwahlGTVpD+mnPmiBQSp1LE4E6f7+/AicOQN9X\nC93MtDeEh4Ywun9zdh1N573ZSX5fvlIlhSYCdX4ObIRF70PrmyDOuS4nOtatyFUXxPHB71vYevCE\nY3EoVZxpIlCFZwz8+hiEl4ZLRjodDY/3a0ypsBBG/rRa74JV6jxoIlCFt/5n2PwbXPwElHH+7t4q\nZSN5qHdD5m46yC+r9zodjlLFjiYCVTgZ6TD1cajcBNrd7nQ0OQZ3rEXT6uUY/b+1nDh1bv+zSqm8\naSJQhbPgHTi6Hfq+AqHhTkeTIyw0hOcGNGfvsZO8PXOT0+EoVaxoIlCeO7oD5r4BTftD3W4Fl/ez\nNrXKc33beD6et5WN+44XPIFSCtBEoApj2lPWc+/nnY0jH49d2pjSpcJ4eqJWHCvlKU0EyjNb51gd\nzlz0T4it6XQ0eapYphSPXtqIRVsPM2mldoynlCc0EaiCZZ6xO5ypCZ293+GMtw1qV5OW8TE8//M6\njp3McDocpQKeJgJVsKUfw/610OclCI9yOpoChYYIzw9owcHUU7zyy3qnw1Eq4GkiUPk7cdDqjL7u\nxdD4Mqej8ViL+BjuuKgO4xdt5/eN2sOWUvnRRKDyN3M0nD5hXS7qww5nfOGh3o1oUKUMj323ipQ0\nPUWkVF40Eai87VoOy8fZHc40cjqaQosMD+WN61txMPUUo/6n/RYolRdNBMo9hzqc8bYW8TEMu6Q+\nP/65i19X73E6HKUCkiYC5d6qCVaHMz1H+bXDGV+49+L6tIiL4YkfV3Pg+Cmnw1Eq4GgiUOc6eQym\nj4S4ttDyBqejKbLw0BDeuL4lqafO8MSPf+mNZkrloolAnWvOq1aHM/2c6XDGFxpULcsjvRsxfe0+\nfli+y+lwlAooJeNXrrznwEZYOAYuGAxxbZyOxqtuu6gO7WtXYNSkNew+mu50OEoFDE0E6m/GwJSH\nIKI09HjG6Wi8LjREeO26lmQaw6PfrSIrS08RKQWaCJSr1d9bbQpd8nRAdDjjCzUrRvPkZU2Yl3SQ\n/y7a5nQ4SgUETQTKcuo4TH0SqreCtrc5HY1P/V/7mnRrWJkXp6zTfo6VQhOByjb7ZUjdB5e9ASGh\nTkfjUyLCK9ckEhEawkPfrCBTTxGpIKeJQMG+NVYFcZtbIL5kVRDnpVpMJM8NaM7y7UcZO2eL0+Eo\n5agCE4GIfCIi+0VktcuwCiIyXUQ22c/l7eEiIm+LSJKIrBKR1r4MXnmBMfDzwxAZUyIriPNzZcsa\n9GtRjTenb2T93mNOh6OUYzw5IvgMuDTXsBHATGNMA2Cm/R6gL9DAfgwFxngnTOUzK7+G7QusO4ij\nKzgdjV+JCM/1b065qDD+OWElp89kOR2SUo4oMBEYY+YAh3MN7g98br/+HBjgMnycsSwEYkWkureC\nVV6WfhSmPw3x7eCCm5yOxhEVy5TipasTWbfnmHZ6r4LW+dYRVDXG7AGwn6vYw+OAHS7ldtrDVCD6\n7XlIOwSXvV5i7iA+H72aVuXaNvG8NzuJP7cfcTocpfzO279+dw3Wu70kQ0SGishSEVl64IB2HOJ3\nu1dYPY+1uwOqt3Q6GseNvKIp1cpF8tA3K0k/nel0OEr51fkmgn3Zp3zs5/328J1Agku5eMBtD+LG\nmLHGmLbGmLaVK5fMm5cCVlYW/PwQRFeCi590OpqAUC4ynH9d15ItB0/w6lTt3lIFl/NNBJOAW+zX\ntwA/uQy/2b56qCOQkn0KSQWQP7+AXUuh93MQFet0NAGjc/1K3HJhLT6dn8yCzQedDkcpv/Hk8tGv\ngD+ARiKyU0RuB14GeonIJqCX/R5gCrAFSAI+BO7xSdTq/KUdhhmjoGYnSBzodDQBZ0TfJtSpVJpH\nvl3F8ZPavaUKDmEFFTDG5NUgfQ83ZQ1wb1GDUj40YxScTIHLXit2fRD7Q1REKK9f35Jrxyzguclr\nefVarT9RJV/wXioSjHYutfog7ng3VG3mdDQBq3XN8tzVrR7fLN3JjLX7nA5HKZ/TRBAssjLh5weh\nbDXoPqLg8kHu/p4NaFytLCN++IujaaedDkcpn9JEECyWfgJ7VkKfF6BUWaejCXilwkJ57bqWHDpx\nig+0LSJVwmkiCAapB+C356Bud2h2tdPRFBvN42K4smUNPpufrJ3eqxJNE0EwmD4STqdB339pBXEh\n3d+jAaczs3hvdpLToSjlM5oISrptf8DKL6HTMKjc0Oloip26lctwTes4xi/crv0cqxJLE0FJlnnG\nuoM4JgG6PuJ0NMXWfZc0wGB4d5YeFaiSSRNBSbb4A9i/Bi59yeqQXp2XhArRDGpXk2+W7GD7oTSn\nw1HK6zQRlFTH9sCsl6B+L2h8udPRFHvDLqlPaIjwb22qWpVAmghKqmlPQeZp6PeqVhB7QdVykdx8\nYS1+/HMnSfuPOx2OUl6liaAk2vI7rP4OLvonVKjrdDQlxl3d6hEZHsqbM/SoQJUsmghKmjOnYcrD\nEFsLLnrA6WhKlIplSnFb5zr8vGoPa3drH8eq5NBEUNIs/A8c3Aj9/gXhUU5HU+L8o0tdykaG8cb0\njU6HopTXaCIoSZaPg1kvQqPLoGEfp6MpkWKiw7mza11mrNvHih1HnQ5HKa/QRFASnDlt3S8w6T6o\n1Rn6v+t0RCXakM51qFA6gtenbXA6FKW8QhNBcZe6H8ZdCUs+gk7D4cbvILqC01GVaGVKhXF3t3rM\n3XSQRVsOOR2OUkWmiaA427UMPuhmdUR/zcdW15OhBfY1pLxgcMdaVClbitenbcTqj0mp4ksTQXG1\n4kv4pC+EhMHt06DFtU5HFFSiIkIZdkl9FicfZu4m7d9YFW+aCIqbzAz45TGYeDfU7ABDZ0P1RKej\nCkoD2yUQFxvF69M26FGBKtY0ERQnJw7CuAGw6H3oeC8M/hFKV3Q6qqBVKiyU+3s0YOXOFGas2+90\nOEqdN00ExcXuFTC2O+xaCleNhUtf1PqAAHB16zhqV4zm9WkbyMrSowJVPGkiKA5WToBP+oAxcNtU\naDnQ6YiULSw0hH/2asj6vcf5+a89Toej1HnRRBDIMs/A1Cfhx6EQ19aqD6jRyumoVC6XJ9agYdUy\nvDljI2cys5wOR6lC00QQqE4cgv9eDX+8C+3vhJsnQpnKTkel3AgNER7s1ZAtB04wccVup8NRqtA0\nEQSivX/Bh91h+0Lo/57VlHRouNNRqXz0aVaN5nHl+PfMjZw+o0cFqnjRRBBo/voOPuplnRa67Re4\n4EanI1IeEBEe6t2IHYfT+WbpDqfDUapQ9LKTQHB0u9WHQNJ0WPsT1LwQrh8HZao4HZkqhO4NK9Om\nVnne+W0T17aJJzI81OmQlPKIJgInpB6Arb/D1jnW85Fka3jpKtDpPrhkJIRFOBqiKjzrqKAh//fh\nIsYv2s7tF9VxOiSlPKKJwB9OpsC2Bda//q2/w/611vBSMVD7IuhwN9TtBpUba7eSxVynepXoVK8i\nY2YnMahdAqVL6U9MBT7dSn0hIx12LLJ3/HNg93IwWRAWCTU7QovroE43qN5SbworgR7q3Yhrxizg\n8z+Suad7fafDUapAuhcqCmMg7TCkbIeUnbB/vfWPf8diyDxlNQgX1wa6PAx1ukJCewgr5XTUysfa\n1CrPJY2r8MHvWxjcsRblIvWKLxXYfJIIRORS4N9AKPCRMeZlXyzH586chmM7rZ18zmMHHN3x9/sz\n6WdPU60FtP+H9Y+/1oVQqqwzsStHPdirIZe/M4+P5m7lwV4NnQ5HqXx5PRGISCjwH6AXsBNYIiKT\njDFrvb2s85KVaZ2zTz8C6Uch/bD1Ou0QHNt19k4+dR+Qq/2YMlUhJh6qNrW6g4yJh5gE67l8LYgq\n78jHUoGleVwMfZtX45N5WxnSqTYVSmvlvwpcvjgiaA8kGWO2AIjI10B/IO9EcDrVqkw9X8bA6RN/\n79RzP9Jchp9M4Zyde7awSHvHHg8NekJMzb/fx8RDuTgIjzz/OFVQ+Wevhvy6Zi//mrqeqy6Idzoc\npfLki0QQB7jeUbMT6JDvFAc3wad9vRiCQGSM9e88qrzVdWPFen+/z3lUOPt9dAW9akd5TcOqZRnQ\nKo6vFu/gq8V6k5kKXL5IBO72pOf8BReRocBQgPoJVeHmr4u21Igyf+/QI2MgRG/mUc574armXNcm\nPq9jUKWK5KJXvDMfXySCnUCCy/t44JyWuIwxY4GxAG3btjXU7e6DUJRyVnREGJ3qV3I6DKXy5Yu2\nhpYADUSkjohEAIOAST5YjlJKKS/w+hGBMeaMiAwDpmJdPvqJMWaNt5ejlFLKO3xyH4ExZgowxRfz\nVkop5V3aDLVSSgU5TQRKKRXkNBEopVSQ00SglFJBToxx/lYXETkObHA6Dg9UAg46HYQHNE7vKQ4x\ngsbpbcUlzkbGmCK3bBkozVBvMMa0dTqIgojIUo3Te4pDnMUhRtA4va04xemN+eipIaWUCnKaCJRS\nKsgFSiIY63QAHtI4vas4xFkcYgSN09uCKs6AqCxWSinlnEA5IlBKKeUQTQRKKRXk/JoIRORSEdkg\nIkkiMsLN+FIiMsEev0hEavszPjuGBBGZJSLrRGSNiNzvpkx3EUkRkRX2Y6S/47TjSBaRv+wYzrmM\nTCxv2+tzlYi09nN8jVzW0QoROSYiD+Qq49i6FJFPRGS/iKx2GVZBRKaLyCb72W0n1CJyi11mk4jc\n4ucY/yUi6+3v9EcRic1j2ny3Dz/EOUpEdrl8t/3ymDbf/YIf4pzgEmOyiKzIY1p/rk+3+yGfbZ/G\nGL88sJqk3gzUBSKAlUDTXGXuAd63Xw8CJvgrPpcYqgOt7ddlgY1u4uwOTPZ3bG5iTQYq5TO+H/AL\nVq9xHYFFDsYaCuwFagXKugS6Aq2B1S7DXgVG2K9HAK+4ma4CsMV+Lm+/Lu/HGHsDYfbrV9zF6Mn2\n4Yc4RwEPe7Bd5Ltf8HWcuca/DowMgPXpdj/kq+3Tn0cEOZ3aG2NOA9md2rvqD3xuv/4O6CHi306E\njTF7jDHL7dfHgXVY/TAXR/2BccayEIgVkeoOxdID2GyM2ebQ8s9hjJkDHM412HUb/BwY4GbSPsB0\nY8xhY8wRYDpwqb9iNMZMM8acsd8uxOoF0FF5rEtPeLJf8Jr84rT3NdcDX/lq+Z7KZz/kk+3Tn4nA\nXaf2uXewOWXsDT0FqOiX6NywT01dACxyM/pCEVkpIr+ISDO/BvY3A0wTkWV2H9C5ebLO/WUQef/A\nAmFdZqtqjNkD1o8RqOKmTCCt19uwjvrcKWj78Idh9imsT/I4jRFI67ILsM8YsymP8Y6sz1z7IZ9s\nn/5MBJ50au9Rx/f+ICJlgO+BB4wxx3KNXo51iqMl8A4w0d/x2TobY1oDfYF7RaRrrvEBsT7F6rL0\nSuBbN6MDZV0WRqCs1yeBM8D4PIoUtH342higHtAK2IN12iW3gFiXthvI/2jA7+uzgP1QnpO5GZbv\nOvVnIvCkU/ucMiISBsRwfoebRSIi4Vgrf7wx5ofc440xx4wxqfbrKUC4iPi9h3JjzG77eT/wI9Zh\ntitP1rk/9AWWG2P25R4RKOvSxb7s02f28343ZRxfr3YF4OXAjcY+MZybB9uHTxlj9hljMo0xWcCH\neSzf8XUJOfubq4EJeZXx9/rMYz/kk+3Tn4nAk07tJwHZNdzXAr/ltZH7in2e8GNgnTHmjTzKVMuu\nuxCR9ljr8ZD/ogQRKS0iZbNfY1Ugrs5VbBJws1g6AinZh5V+luc/rUBYl7m4boO3AD+5KTMV6C0i\n5e3THb3tYX4hIpcCjwFXGmPS8ijjyfbhU7nqo67KY/me7Bf8oSew3hiz091If6/PfPZDvtk+/VED\n7lKb3Q+r9nsz8KQ9bDTWBg0QiXX6IAlYDNT1Z3x2DBdhHUatAlbYj37AXcBddplhwBqsKxwWAp0c\niLOuvfyVdizZ69M1TgH+Y6/vv4C2DsQZjbVjj3EZFhDrEis57QEysP5F3Y5VJzUT2GQ/V7DLtgU+\ncpn2Nns7TQJu9XOMSVjngLO3z+wr7WoAU/LbPvwc5xf2drcKawdWPXec9vtz9gv+jNMe/ln2NulS\n1sn1mdd+yCfbpzYxoZRSQU7vLFZKqSCniUAppYKcJgKllApymgiUUirIaSJQQUFEYkXknvOY7glf\nxKNUINGrhlRQsG/Tn2yMaV7I6VKNMWV8EpRSAUKPCFSweBmoZzch/K/cI0WkuojMscevFpEuIvIy\nEGUPG2+XGywii+1hH4hIqD08VUReF5HlIjJTRCr79+Mpdf70iEAFhYKOCETkISDSGPOCvXOPNsYc\ndz0iEJEmWM0AX22MyRCR94CFxphxImKAwcaY8WL1qVDFGDPMH59NqaIKczoApQLEEuATu32XicYY\nd52T9ADaAEvsVjGi+Lutlyz+bqfmv8A5bVQpFaj01JBS5LRT3xXYBXwhIje7KSbA58aYVvajkTFm\nVF6z9FGoSnmdJgIVLI5j9fTklojUAvYbYz7Eauwru1vPDPsoAay2Xa4VkSr2NBXs6cD6LV1rv/4/\nYJ6X41fKZ/TUkAoKxphDIjJfrL5qfzHGPJKrSHfgERHJAFKB7COCscAqEVlujLlRRJ7C6pwkBKvh\nsnuBbcAJoJmILMPqUGmg7z+VUt6hlcVKeYFeZqqKMz01pJRSQU6PCFRQEZEWWO3kuzpljOngRDxK\nBQJNBEopFeT01JBSSgU5TQRKKRXkNBEopVSQ00SglFJBThOBUkoFOU0ESikV5P4fLrLdLgZF+zkA\nAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nK4YxWoQtWWgAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEXCAYAAACgUUN5AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nK4YxWoQtWWgAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plot_all('soil_output/Spread_barabasi*', get_count, 'id');" + ] + }, + { + "cell_type": "code", + "execution_count": 22, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:58:26.903783Z", + "start_time": "2017-10-19T17:57:57.983957+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nACn5i4gMQP8fEeHAAqu6cxAAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nACn5i4gMQP8fEeHAAqu6cxAAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhJT8RUQGof8Puw/Kf+5ObzkAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhJT8RUQGof8Puw/Kf+5ObzkAAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nmwAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nmwAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxQn7eJiJ/QAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nxQn7eJiJ/QAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRKQPUvIXEemDlPxFRPqg/w8q2vnGLNBQ+wAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAEXCAYAAABF40RQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRKQPUvIXEemDlPxFRPqg/w8q2vnGLNBQ+wAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "plot_all('soil_output/Spread_erdos*', get_value, 'prob_tv_spread');" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Manually plotting with pandas" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T11:00:37.003972Z", + "start_time": "2017-10-19T13:00:36.983128+02:00" + } + }, + "source": [ + "Although the simplest way to visualize the results of a simulation is to use the built-in methods in the analysis module, sometimes the setup is more complicated and we need to explore the data a little further.\n", + "\n", + "For that, we can use native pandas over the results.\n", + "\n", + "Soil provides some convenience methods to simplify common operations:\n", + "\n", + "* `analysis.split_df` to separate a history dataframe into environment and agent parameters.\n", + "* `analysis.get_count` to get a dataframe with the value counts for different attributes during the simulation.\n", + "* `analysis.get_value` to get the evolution of the value of an attribute during the simulation.\n", + "\n", + "And, as we saw earlier, `analysis.process` can turn a dataframe in canonical form into a dataframe with a column per attribute.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:15.791793Z", + "start_time": "2017-10-19T17:59:15.604960+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "p = read_sql('soil_output/Spread_barabasi_albert_graph_prob_0.0/Spread_barabasi_albert_graph_prob_0.0_trial_0.db.sqlite')\n", + "env, agents = split_df(p);" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Let's look at the evolution of agent parameters in the simulation" + ] + }, + { + "cell_type": "code", + "execution_count": 24, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:17.153282Z", + "start_time": "2017-10-19T17:59:16.830872+02:00" + } + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "res = agents.groupby(by=['t_step', 'key', 'value']).size().unstack(level=[1,2]).fillna(0)\n", + "res.plot();" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T11:10:36.086913Z", + "start_time": "2017-10-19T13:10:36.058547+02:00" + } + }, + "source": [ + "As we can see, `event_time` is cluttering our results, " + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:18.418348Z", + "start_time": "2017-10-19T17:59:18.143443+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 25, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nqggqHK0AAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "del res['event_time']\n", + "res.plot()" + ] + }, + { + "cell_type": "code", + "execution_count": 28, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:42.750011Z", + "start_time": "2017-10-19T17:59:42.649353+02:00" + } + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
event_timehas_tvid
t_stepagent_id
000Trueneutral
10Falseneutral
100Trueneutral
1000Trueneutral
1010Trueneutral
1020Falseneutral
1030Trueneutral
1040Trueneutral
1050Falseneutral
1060Falseneutral
1070Trueneutral
1080Trueneutral
1090Falseneutral
110Trueneutral
1100Falseneutral
1110Falseneutral
1120Trueneutral
1130Trueneutral
1140Trueneutral
1150Trueneutral
1160Falseneutral
1170Trueneutral
1180Trueneutral
1190Falseneutral
120Falseneutral
1200Falseneutral
1210Trueneutral
1220Trueneutral
1230Trueneutral
1240Falseneutral
...............
20730Trueinfected
740Trueinfected
750Trueinfected
760Trueinfected
770Trueinfected
780Trueinfected
790Falseinfected
80Falseinfected
800Trueinfected
810Falseinfected
820Falseinfected
830Trueinfected
840Falseinfected
850Trueinfected
860Trueinfected
870Trueinfected
880Falseinfected
890Falseinfected
90Trueinfected
900Trueinfected
910Trueinfected
920Trueinfected
930Falseinfected
940Trueinfected
950Trueinfected
960Trueinfected
970Trueinfected
980Falseinfected
990Trueinfected
NewsEnvironmentAgent10False0
\n", + "

10521 rows × 3 columns

\n", + "
" + ], + "text/plain": [ + " event_time has_tv id\n", + "t_step agent_id \n", + "0 0 0 True neutral\n", + " 1 0 False neutral\n", + " 10 0 True neutral\n", + " 100 0 True neutral\n", + " 101 0 True neutral\n", + " 102 0 False neutral\n", + " 103 0 True neutral\n", + " 104 0 True neutral\n", + " 105 0 False neutral\n", + " 106 0 False neutral\n", + " 107 0 True neutral\n", + " 108 0 True neutral\n", + " 109 0 False neutral\n", + " 11 0 True neutral\n", + " 110 0 False neutral\n", + " 111 0 False neutral\n", + " 112 0 True neutral\n", + " 113 0 True neutral\n", + " 114 0 True neutral\n", + " 115 0 True neutral\n", + " 116 0 False neutral\n", + " 117 0 True neutral\n", + " 118 0 True neutral\n", + " 119 0 False neutral\n", + " 12 0 False neutral\n", + " 120 0 False neutral\n", + " 121 0 True neutral\n", + " 122 0 True neutral\n", + " 123 0 True neutral\n", + " 124 0 False neutral\n", + "... ... ... ...\n", + "20 73 0 True infected\n", + " 74 0 True infected\n", + " 75 0 True infected\n", + " 76 0 True infected\n", + " 77 0 True infected\n", + " 78 0 True infected\n", + " 79 0 False infected\n", + " 8 0 False infected\n", + " 80 0 True infected\n", + " 81 0 False infected\n", + " 82 0 False infected\n", + " 83 0 True infected\n", + " 84 0 False infected\n", + " 85 0 True infected\n", + " 86 0 True infected\n", + " 87 0 True infected\n", + " 88 0 False infected\n", + " 89 0 False infected\n", + " 9 0 True infected\n", + " 90 0 True infected\n", + " 91 0 True infected\n", + " 92 0 True infected\n", + " 93 0 False infected\n", + " 94 0 True infected\n", + " 95 0 True infected\n", + " 96 0 True infected\n", + " 97 0 True infected\n", + " 98 0 False infected\n", + " 99 0 True infected\n", + " NewsEnvironmentAgent 10 False 0\n", + "\n", + "[10521 rows x 3 columns]" + ] + }, + "execution_count": 28, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "processed = process_one(agents);\n", + "processed" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Which is equivalent to:" + ] + }, + { + "cell_type": "code", + "execution_count": 30, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:51.165806Z", + "start_time": "2017-10-19T17:59:50.886780+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 30, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEKCAYAAAAfGVI8AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nqggqHK0AAAAASUVORK5CYII=\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "get_count(agents, 'id', 'has_tv').plot()" + ] + }, + { + "cell_type": "code", + "execution_count": 31, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T15:59:55.203641Z", + "start_time": "2017-10-19T17:59:54.950046+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 31, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYUAAAEKCAYAAAD9xUlFAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nbgAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "get_value(agents, 'event_time').plot()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Dealing with bigger data" + ] + }, + { + "cell_type": "code", + "execution_count": 32, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:18.148006Z", + "start_time": "2017-10-19T18:00:18.117654+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "from soil import analysis" + ] + }, + { + "cell_type": "code", + "execution_count": 33, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:18.636440Z", + "start_time": "2017-10-19T18:00:18.504421+02:00" + } + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "267M\t../rabbits/soil_output/rabbits_example/\r\n" + ] + } + ], + "source": [ + "!du -xsh ../rabbits/soil_output/rabbits_example/" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T11:22:22.301765Z", + "start_time": "2017-10-19T13:22:22.281986+02:00" + } + }, + "source": [ + "If we tried to load the entire history, we would probably run out of memory. Hence, it is recommended that you also specify the attributes you are interested in." + ] + }, + { + "cell_type": "code", + "execution_count": 34, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:25.080582Z", + "start_time": "2017-10-19T18:00:19.594165+02:00" + }, + "scrolled": false + }, + "outputs": [ + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEXCAYAAABGeIg9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n0SbFISIi2qQ4REREmxSHiIho8y9ffsz3DjLrngAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEXCAYAAABGeIg9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n0SbFISIi2qQ4REREmxSHiIho8y9ffsz3DjLrngAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "p = analysis.plot_all('../rabbits/soil_output/rabbits_example/', analysis.get_count, 'id')" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:38.434367Z", + "start_time": "2017-10-19T18:00:33.645762+02:00" + }, + "collapsed": true + }, + "outputs": [], + "source": [ + "df = analysis.read_sql('../rabbits/soil_output/rabbits_example/rabbits_example_trial_0.db.sqlite', keys=['id', 'rabbits_alive'])" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:39.160418Z", + "start_time": "2017-10-19T18:00:38.436153+02:00" + }, + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 40, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEKCAYAAAD5MJl4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "states = analysis.get_count(df, 'id')\n", + "states.plot()" + ] + }, + { + "cell_type": "code", + "execution_count": 41, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:39.515032Z", + "start_time": "2017-10-19T18:00:39.162240+02:00" + } + }, + "outputs": [ + { + "data": { + "text/plain": [ + "" + ] + }, + "execution_count": 41, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEKCAYAAAD5MJl4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\npAGFg4iINPD/AfaLVEq6LAp5AAAAAElFTkSuQmCC\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "alive = analysis.get_value(df, 'rabbits_alive', 'rabbits_alive', aggfunc='sum').apply(pd.to_numeric)\n", + "alive.plot()" + ] + }, + { + "cell_type": "code", + "execution_count": 44, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:00:58.815038Z", + "start_time": "2017-10-19T18:00:58.566807+02:00" + } + }, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/jfernando/.local/lib/python3.6/site-packages/pandas/core/reshape/merge.py:551: UserWarning: merging between different levels can give an unintended result (1 levels on the left, 2 on the right)\n", + " warnings.warn(msg, UserWarning)\n" + ] + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYcAAAEKCAYAAAD5MJl4AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/D/rW5PT2bI3LAAAAABJRU5ErkJggg==\n", + "text/plain": [ + "" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "h = alive.join(states);\n", + "h.plot();" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "ExecuteTime": { + "end_time": "2017-10-19T16:01:01.195253Z", + "start_time": "2017-10-19T18:01:01.142907+02:00" + }, + "collapsed": true, + "scrolled": true + }, + "outputs": [], + "source": [ + "states[[('id','newborn'),('id','fertile'),('id', 'pregnant')]].sum(axis=1).sub(alive['rabbits_alive'], fill_value=0)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.6.2" + }, + "toc": { + "colors": { + "hover_highlight": "#DAA520", + "navigate_num": "#000000", + "navigate_text": "#333333", + "running_highlight": "#FF0000", + "selected_highlight": "#FFD700", + "sidebar_border": "#EEEEEE", + "wrapper_background": "#FFFFFF" + }, + "moveMenuLeft": true, + "nav_menu": { + "height": "31px", + "width": "252px" + }, + "navigate_menu": true, + "number_sections": true, + "sideBar": true, + "threshold": 4, + "toc_cell": false, + "toc_position": { + "height": "867px", + "left": "0px", + "right": "1670px", + "top": "106px", + "width": "250px" + }, + "toc_section_display": "block", + "toc_window_display": true, + "widenNotebook": false + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/notebooks/soil_tutorial.ipynb b/notebooks/soil_tutorial.ipynb deleted file mode 100644 index d19424e..0000000 --- a/notebooks/soil_tutorial.ipynb +++ /dev/null @@ -1,1912 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T16:44:14.120953Z", - "start_time": "2017-07-02T18:44:14.117152+02:00" - } - }, - "source": [ - "# Introduction" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "cell_style": "center", - "collapsed": true - }, - "source": [ - "This notebook is an introduction to the soil agent-based social network simulation framework.\n", - "In particular, we will focus on a specific use case: studying the propagation of news in a social network.\n", - "\n", - "The steps we will follow are:\n", - "\n", - "* Modelling the behavior of agents\n", - "* Running the simulation using different configurations\n", - "* Analysing the results of each simulation" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T13:38:48.052876Z", - "start_time": "2017-07-03T15:38:48.044762+02:00" - } - }, - "source": [ - "But before that, let's import the soil module and networkx." - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:51.679937Z", - "start_time": "2017-07-03T16:42:51.185463+02:00" - }, - "collapsed": true - }, - "outputs": [], - "source": [ - "import soil\n", - "import networkx as nx" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:51.690373Z", - "start_time": "2017-07-03T16:42:51.682644+02:00" - } - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Populating the interactive namespace from numpy and matplotlib\n" - ] - } - ], - "source": [ - "%pylab inline\n", - "# To display plots in the notebook" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T13:41:19.788717Z", - "start_time": "2017-07-03T15:41:19.785448+02:00" - } - }, - "source": [ - "# Basic concepts" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "There are three main elements in a soil simulation:\n", - " \n", - "* The network topology. A simulation may use an existing NetworkX topology, or generate one on the fly\n", - "* Agents. There are two types: 1) network agents, which are linked to a node in the topology, and 2) environment agents, which are freely assigned to the environment.\n", - "* The environment. It assigns agents to nodes in the network, and stores the environment parameters (shared state for all agents).\n", - "\n", - "Soil is based on ``simpy``, which is an event-based network simulation library.\n", - "Soil provides several abstractions over events to make developing agents easier.\n", - "This means you can use events (timeouts, delays) in soil, but for the most part we will assume your models will be step-based.\n" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T15:55:12.933978Z", - "start_time": "2017-07-02T17:55:12.930860+02:00" - } - }, - "source": [ - "# Modeling behaviour" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T13:49:31.269687Z", - "start_time": "2017-07-03T15:49:31.257850+02:00" - } - }, - "source": [ - "Our first step will be to model how every person in the social network reacts when it comes to news.\n", - "We will follow a very simple model (a finite state machine).\n", - "\n", - "There are two types of people, those who have heard about a newsworthy event (infected) or those who have not (neutral).\n", - "A neutral person may heard about the news either on the TV (with probability **prob_tv_spread**) or through their friends.\n", - "Once a person has heard the news, they will spread it to their friends (with a probability **prob_neighbor_spread**).\n", - "Some users do not have a TV, so they only rely on their friends.\n", - "\n", - "The spreading probabilities will change over time due to different factors.\n", - "We will represent this variance using an environment agent." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## Network Agents" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:03:07.171127Z", - "start_time": "2017-07-03T16:03:07.165779+02:00" - } - }, - "source": [ - "A basic network agent in Soil should inherit from ``soil.agents.BaseAgent``, and define its behaviour in every step of the simulation by implementing a ``run(self)`` method.\n", - "The most important attributes of the agent are:\n", - "\n", - "* ``agent.state``, a dictionary with the state of the agent. ``agent.state['id']`` reflects the state id of the agent. That state id can be used to look for other networks in that specific state. The state can be access via the agent as well. For instance:\n", - "```py\n", - "a = soil.agents.BaseAgent(env=env)\n", - "a['hours_of_sleep'] = 10\n", - "print(a['hours_of_sleep'])\n", - "```\n", - " The state of the agent is stored in every step of the simulation:\n", - " ```py\n", - " print(a['hours_of_sleep', 10]) # hours of sleep before step #10\n", - " print(a[None, 0]) # whole state of the agent before step #0\n", - " ```\n", - "\n", - "* ``agent.env``, a reference to the environment. Most commonly used to get access to the environment parameters and the topology:\n", - " ```py\n", - " a.env.G.nodes() # Get all nodes ids in the topology\n", - " a.env['minimum_hours_of_sleep']\n", - "\n", - " ```\n", - "\n", - "Since our model is a finite state machine, we will be basing it on ``soil.agents.FSM``.\n", - "\n", - "With ``soil.agents.FSM``, we do not need to specify a ``step`` method.\n", - "Instead, we describe every step as a function.\n", - "To change to another state, a function may return the new state.\n", - "If no state is returned, the state remains unchanged.[\n", - "It will consist of two states, ``neutral`` (default) and ``infected``.\n", - "\n", - "Here's the code:" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:51.715535Z", - "start_time": "2017-07-03T16:42:51.692301+02:00" - }, - "collapsed": true - }, - "outputs": [], - "source": [ - "import random\n", - "\n", - "class NewsSpread(soil.agents.FSM):\n", - " @soil.agents.default_state\n", - " @soil.agents.state\n", - " def neutral(self):\n", - " r = random.random()\n", - " if self['has_tv'] and r < self.env['prob_tv_spread']:\n", - " return self.infected\n", - " return\n", - " \n", - " @soil.agents.state\n", - " def infected(self):\n", - " prob_infect = self.env['prob_neighbor_spread']\n", - " for neighbor in self.get_neighboring_agents(state_id=self.neutral.id):\n", - " r = random.random()\n", - " if r < prob_infect:\n", - " neighbor.state['id'] = self.infected.id\n", - " return\n", - " " - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T12:22:53.931963Z", - "start_time": "2017-07-02T14:22:53.928340+02:00" - } - }, - "source": [ - "## Environment agents" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Environment agents allow us to control the state of the environment.\n", - "In this case, we will use an environment agent to simulate a very viral event.\n", - "\n", - "When the event happens, the agent will modify the probability of spreading the rumor." - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:51.727938Z", - "start_time": "2017-07-03T16:42:51.717828+02:00" - }, - "collapsed": true - }, - "outputs": [], - "source": [ - "NEIGHBOR_FACTOR = 0.9\n", - "TV_FACTOR = 0.5\n", - "class NewsEnvironmentAgent(soil.agents.BaseAgent):\n", - " def step(self):\n", - " if self.now == self['event_time']:\n", - " self.env['prob_tv_spread'] = 1\n", - " self.env['prob_neighbor_spread'] = 1\n", - " elif self.now > self['event_time']:\n", - " self.env['prob_tv_spread'] = self.env['prob_tv_spread'] * TV_FACTOR\n", - " self.env['prob_neighbor_spread'] = self.env['prob_neighbor_spread'] * NEIGHBOR_FACTOR" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T11:23:18.052235Z", - "start_time": "2017-07-02T13:23:18.047452+02:00" - } - }, - "source": [ - "## Testing the agents" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T16:14:54.572431Z", - "start_time": "2017-07-02T18:14:54.564095+02:00" - } - }, - "source": [ - "Feel free to skip this section if this is your first time with soil." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Testing agents is not easy, and this is not a thorough testing process for agents.\n", - "Rather, this section is aimed to show you how to access internal pats of soil so you can test your agents." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "cell_style": "split" - }, - "source": [ - "First of all, let's check if our network agent has the states we would expect:" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:51.816465Z", - "start_time": "2017-07-03T16:42:51.811222+02:00" - }, - "cell_style": "split" - }, - "outputs": [ - { - "data": { - "text/plain": [ - "{'infected': ,\n", - " 'neutral': }" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "NewsSpread.states" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "cell_style": "split" - }, - "source": [ - "Now, let's run a simulation on a simple network. It is comprised of three nodes:\n" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:52.106636Z", - "start_time": "2017-07-03T16:42:51.904738+02:00" - }, - "cell_style": "split", - "scrolled": false - }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/X8ieN7dQkZLXwAAAABJRU5ErkJggg==\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "G = nx.Graph()\n", - "G.add_edge(0, 1)\n", - "G.add_edge(0, 2)\n", - "G.add_edge(2, 3)\n", - "G.add_node(4)\n", - "pos = nx.spring_layout(G)\n", - "nx.draw_networkx(G, pos, node_color='red')\n", - "nx.draw_networkx(G, pos, nodelist=[0], node_color='blue')" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T11:53:30.997756Z", - "start_time": "2017-07-03T13:53:30.989609+02:00" - }, - "cell_style": "split" - }, - "source": [ - "Let's run a simple simulation that assigns a NewsSpread agent to all the nodes in that network.\n", - "Notice how node 0 is the only one with a TV." - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:52.136477Z", - "start_time": "2017-07-03T16:42:52.108729+02:00" - }, - "cell_style": "split" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.014928102493286133 seconds\n", - "Finished simulation in 0.015764951705932617 seconds\n" - ] - } - ], - "source": [ - "env_params = {'prob_tv_spread': 0,\n", - " 'prob_neighbor_spread': 0}\n", - "\n", - "MAX_TIME = 100\n", - "EVENT_TIME = 10\n", - "\n", - "sim = soil.simulation.SoilSimulation(topology=G,\n", - " num_trials=1,\n", - " max_time=MAX_TIME,\n", - " environment_agents=[{'agent_type': NewsEnvironmentAgent,\n", - " 'state': {\n", - " 'event_time': EVENT_TIME\n", - " }}],\n", - " network_agents=[{'agent_type': NewsSpread,\n", - " 'weight': 1}],\n", - " states={0: {'has_tv': True}},\n", - " default_state={'has_tv': False},\n", - " environment_params=env_params)\n", - "env = sim.run_simulation()[0]" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "cell_style": "split" - }, - "source": [ - "Now we can access the results of the simulation and compare them to our expected results" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:52.160856Z", - "start_time": "2017-07-03T16:42:52.138976+02:00" - }, - "cell_style": "split", - "collapsed": true, - "scrolled": false - }, - "outputs": [], - "source": [ - "agents = list(env.network_agents)\n", - "\n", - "# Until the event, all agents are neutral\n", - "for t in range(10):\n", - " for a in agents:\n", - " assert a['id', t] == a.neutral.id\n", - "\n", - "# After the event, the node with a TV is infected, the rest are not\n", - "assert agents[0]['id', 11] == NewsSpread.infected.id\n", - "\n", - "for a in agents[1:4]:\n", - " assert a['id', 11] == NewsSpread.neutral.id\n", - "\n", - "# At the end, the agents connected to the infected one will probably be infected, too.\n", - "assert agents[1]['id', MAX_TIME] == NewsSpread.infected.id\n", - "assert agents[2]['id', MAX_TIME] == NewsSpread.infected.id\n", - "\n", - "# But the node with no friends should not be affected\n", - "assert agents[4]['id', MAX_TIME] == NewsSpread.neutral.id\n", - " " - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T16:41:09.110652Z", - "start_time": "2017-07-02T18:41:09.106966+02:00" - }, - "cell_style": "split" - }, - "source": [ - "Lastly, let's see if the probabilities have decreased as expected:" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:52.193918Z", - "start_time": "2017-07-03T16:42:52.163476+02:00" - }, - "cell_style": "split", - "collapsed": true - }, - "outputs": [], - "source": [ - "assert abs(env.environment_params['prob_neighbor_spread'] - (NEIGHBOR_FACTOR**(MAX_TIME-1-10))) < 10e-4\n", - "assert abs(env.environment_params['prob_tv_spread'] - (TV_FACTOR**(MAX_TIME-1-10))) < 10e-6" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Running the simulation" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T11:20:28.566944Z", - "start_time": "2017-07-03T13:20:28.561052+02:00" - }, - "cell_style": "split" - }, - "source": [ - "To run a simulation, we need a configuration.\n", - "Soil can load configurations from python dictionaries as well as JSON and YAML files.\n", - "For this demo, we will use a python dictionary:" - ] - }, - { - "cell_type": "code", - "execution_count": 10, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:52.219072Z", - "start_time": "2017-07-03T16:42:52.196203+02:00" - }, - "cell_style": "split", - "collapsed": true - }, - "outputs": [], - "source": [ - "config = {\n", - " 'name': 'ExampleSimulation',\n", - " 'max_time': 20,\n", - " 'interval': 1,\n", - " 'num_trials': 1,\n", - " 'network_params': {\n", - " 'generator': 'complete_graph',\n", - " 'n': 500,\n", - " },\n", - " 'network_agents': [\n", - " {\n", - " 'agent_type': NewsSpread,\n", - " 'weight': 1,\n", - " 'state': {\n", - " 'has_tv': False\n", - " }\n", - " },\n", - " {\n", - " 'agent_type': NewsSpread,\n", - " 'weight': 2,\n", - " 'state': {\n", - " 'has_tv': True\n", - " }\n", - " }\n", - " ],\n", - " 'states': [ {'has_tv': True} ],\n", - " 'environment_params':{\n", - " 'prob_tv_spread': 0.01,\n", - " 'prob_neighbor_spread': 0.5\n", - " }\n", - "}" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T11:57:34.219618Z", - "start_time": "2017-07-03T13:57:34.213817+02:00" - }, - "cell_style": "split" - }, - "source": [ - "Let's run our simulation:" - ] - }, - { - "cell_type": "code", - "execution_count": 11, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:42:55.366288Z", - "start_time": "2017-07-03T16:42:52.295584+02:00" - }, - "cell_style": "split" - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using config(s): ExampleSimulation\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 1.4140360355377197 seconds\n", - "Finished simulation in 2.4056642055511475 seconds\n" - ] - } - ], - "source": [ - "soil.simulation.run_from_config(config, dump=False)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T12:03:32.183588Z", - "start_time": "2017-07-03T14:03:32.167797+02:00" - }, - "cell_style": "split", - "collapsed": true - }, - "source": [ - "In real life, you probably want to run several simulations, varying some of the parameters so that you can compare and answer your research questions.\n", - "\n", - "For instance:\n", - " \n", - "* Does the outcome depend on the structure of our network? We will use different generation algorithms to compare them (Barabasi-Albert and Erdos-Renyi)\n", - "* How does neighbor spreading probability affect my simulation? We will try probability values in the range of [0, 0.4], in intervals of 0.1." - ] - }, - { - "cell_type": "code", - "execution_count": 12, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:15.488799Z", - "start_time": "2017-07-03T16:42:55.368021+02:00" - }, - "cell_style": "split", - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using config(s): Spread_erdos_renyi_graph_prob_0.0\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.2691483497619629 seconds\n", - "Finished simulation in 0.3650345802307129 seconds\n", - "Using config(s): Spread_erdos_renyi_graph_prob_0.1\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.34261059761047363 seconds\n", - "Finished simulation in 0.44017767906188965 seconds\n", - "Using config(s): Spread_erdos_renyi_graph_prob_0.2\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.34417223930358887 seconds\n", - "Finished simulation in 0.4550771713256836 seconds\n", - "Using config(s): Spread_erdos_renyi_graph_prob_0.3\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.3237779140472412 seconds\n", - "Finished simulation in 0.42307496070861816 seconds\n", - "Using config(s): Spread_erdos_renyi_graph_prob_0.4\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.3507683277130127 seconds\n", - "Finished simulation in 0.45061564445495605 seconds\n", - "Using config(s): Spread_barabasi_albert_graph_prob_0.0\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.19115304946899414 seconds\n", - "Finished simulation in 0.20927715301513672 seconds\n", - "Using config(s): Spread_barabasi_albert_graph_prob_0.1\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.22086191177368164 seconds\n", - "Finished simulation in 0.2390913963317871 seconds\n", - "Using config(s): Spread_barabasi_albert_graph_prob_0.2\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.21225976943969727 seconds\n", - "Finished simulation in 0.23252630233764648 seconds\n", - "Using config(s): Spread_barabasi_albert_graph_prob_0.3\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.2853121757507324 seconds\n", - "Finished simulation in 0.30568504333496094 seconds\n", - "Using config(s): Spread_barabasi_albert_graph_prob_0.4\n", - "Trial: 0\n", - "\tRunning\n", - "Finished trial in 0.21434736251831055 seconds\n", - "Finished simulation in 0.23370599746704102 seconds\n" - ] - } - ], - "source": [ - "network_1 = {\n", - " 'generator': 'erdos_renyi_graph',\n", - " 'n': 500,\n", - " 'p': 0.1\n", - "}\n", - "network_2 = {\n", - " 'generator': 'barabasi_albert_graph',\n", - " 'n': 500,\n", - " 'm': 2\n", - "}\n", - "\n", - "\n", - "for net in [network_1, network_2]:\n", - " for i in range(5):\n", - " prob = i / 10\n", - " config['environment_params']['prob_neighbor_spread'] = prob\n", - " config['network_params'] = net\n", - " config['name'] = 'Spread_{}_prob_{}'.format(net['generator'], prob)\n", - " s = soil.simulation.run_from_config(config)" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T11:05:18.043194Z", - "start_time": "2017-07-03T13:05:18.034699+02:00" - }, - "cell_style": "split" - }, - "source": [ - "The results are conveniently stored in pickle (simulation), csv (history of agent and environment state) and gexf format." - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:15.721720Z", - "start_time": "2017-07-03T16:43:15.490854+02:00" - }, - "cell_style": "split", - "scrolled": true - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[01;34msoil_output\u001b[00m\n", - "├── \u001b[01;34mSim_prob_0\u001b[00m\n", - "│   ├── Sim_prob_0.dumped.yml\n", - "│   ├── Sim_prob_0.simulation.pickle\n", - "│   ├── Sim_prob_0_trial_0.environment.csv\n", - "│   └── Sim_prob_0_trial_0.gexf\n", - "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.0\u001b[00m\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.0.dumped.yml\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.0.simulation.pickle\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.0_trial_0.environment.csv\n", - "│   └── Spread_barabasi_albert_graph_prob_0.0_trial_0.gexf\n", - "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.1\u001b[00m\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.1.dumped.yml\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.1.simulation.pickle\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.1_trial_0.environment.csv\n", - "│   └── Spread_barabasi_albert_graph_prob_0.1_trial_0.gexf\n", - "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.2\u001b[00m\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.2.dumped.yml\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.2.simulation.pickle\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.2_trial_0.environment.csv\n", - "│   └── Spread_barabasi_albert_graph_prob_0.2_trial_0.gexf\n", - "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.3\u001b[00m\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.3.dumped.yml\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.3.simulation.pickle\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.3_trial_0.environment.csv\n", - "│   └── Spread_barabasi_albert_graph_prob_0.3_trial_0.gexf\n", - "├── \u001b[01;34mSpread_barabasi_albert_graph_prob_0.4\u001b[00m\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.4.dumped.yml\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.4.simulation.pickle\n", - "│   ├── Spread_barabasi_albert_graph_prob_0.4_trial_0.environment.csv\n", - "│   └── Spread_barabasi_albert_graph_prob_0.4_trial_0.gexf\n", - "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.0\u001b[00m\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.0.dumped.yml\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.0.simulation.pickle\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.0_trial_0.environment.csv\n", - "│   └── Spread_erdos_renyi_graph_prob_0.0_trial_0.gexf\n", - "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.1\u001b[00m\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.1.dumped.yml\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.1.simulation.pickle\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.1_trial_0.environment.csv\n", - "│   └── Spread_erdos_renyi_graph_prob_0.1_trial_0.gexf\n", - "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.2\u001b[00m\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.2.dumped.yml\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.2.simulation.pickle\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.2_trial_0.environment.csv\n", - "│   └── Spread_erdos_renyi_graph_prob_0.2_trial_0.gexf\n", - "├── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.3\u001b[00m\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.3.dumped.yml\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.3.simulation.pickle\n", - "│   ├── Spread_erdos_renyi_graph_prob_0.3_trial_0.environment.csv\n", - "│   └── Spread_erdos_renyi_graph_prob_0.3_trial_0.gexf\n", - "└── \u001b[01;34mSpread_erdos_renyi_graph_prob_0.4\u001b[00m\n", - " ├── Spread_erdos_renyi_graph_prob_0.4.dumped.yml\n", - " ├── Spread_erdos_renyi_graph_prob_0.4.simulation.pickle\n", - " ├── Spread_erdos_renyi_graph_prob_0.4_trial_0.environment.csv\n", - " └── Spread_erdos_renyi_graph_prob_0.4_trial_0.gexf\n", - "\n", - "11 directories, 44 files\n", - "1.8M\tsoil_output/Sim_prob_0\n", - "652K\tsoil_output/Spread_barabasi_albert_graph_prob_0.0\n", - "684K\tsoil_output/Spread_barabasi_albert_graph_prob_0.1\n", - "692K\tsoil_output/Spread_barabasi_albert_graph_prob_0.2\n", - "692K\tsoil_output/Spread_barabasi_albert_graph_prob_0.3\n", - "688K\tsoil_output/Spread_barabasi_albert_graph_prob_0.4\n", - "1.8M\tsoil_output/Spread_erdos_renyi_graph_prob_0.0\n", - "1.9M\tsoil_output/Spread_erdos_renyi_graph_prob_0.1\n", - "1.9M\tsoil_output/Spread_erdos_renyi_graph_prob_0.2\n", - "1.9M\tsoil_output/Spread_erdos_renyi_graph_prob_0.3\n", - "1.9M\tsoil_output/Spread_erdos_renyi_graph_prob_0.4\n" - ] - } - ], - "source": [ - "!tree soil_output\n", - "!du -xh soil_output/*" - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-02T10:40:14.384177Z", - "start_time": "2017-07-02T12:40:14.381885+02:00" - } - }, - "source": [ - "# Analysing the results" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "Once the simulations are over, we can use soil to analyse the results." - ] - }, - { - "cell_type": "markdown", - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:44:30.978223Z", - "start_time": "2017-07-03T16:44:30.971952+02:00" - } - }, - "source": [ - "First, let's load the stored results into a pandas dataframe." - ] - }, - { - "cell_type": "code", - "execution_count": 14, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:15.987794Z", - "start_time": "2017-07-03T16:43:15.724519+02:00" - } - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Populating the interactive namespace from numpy and matplotlib\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/usr/lib/python3.6/site-packages/IPython/core/magics/pylab.py:160: UserWarning: pylab import has clobbered these variables: ['random']\n", - "`%matplotlib` prevents importing * from pylab and numpy\n", - " \"\\n`%matplotlib` prevents importing * from pylab and numpy\"\n" - ] - } - ], - "source": [ - "%pylab inline\n", - "from soil import analysis" - ] - }, - { - "cell_type": "code", - "execution_count": 15, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:16.590910Z", - "start_time": "2017-07-03T16:43:15.990320+02:00" - }, - "scrolled": true - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
agent_idtstepattributevalue
0env0prob_tv_spread0.01
1env0prob_neighbor_spread0.1
2env1prob_tv_spread0.01
3env1prob_neighbor_spread0.1
4env2prob_tv_spread0.01
5env2prob_neighbor_spread0.1
6env3prob_tv_spread0.01
7env3prob_neighbor_spread0.1
8env4prob_tv_spread0.01
9env4prob_neighbor_spread0.1
10env5prob_tv_spread0.01
11env5prob_neighbor_spread0.1
12env6prob_tv_spread0.01
13env6prob_neighbor_spread0.1
14env7prob_tv_spread0.01
15env7prob_neighbor_spread0.1
16env8prob_tv_spread0.01
17env8prob_neighbor_spread0.1
18env9prob_tv_spread0.01
19env9prob_neighbor_spread0.1
20env10prob_tv_spread0.01
21env10prob_neighbor_spread0.1
22env11prob_tv_spread0.01
23env11prob_neighbor_spread0.1
24env12prob_tv_spread0.01
25env12prob_neighbor_spread0.1
26env13prob_tv_spread0.01
27env13prob_neighbor_spread0.1
28env14prob_tv_spread0.01
29env14prob_neighbor_spread0.1
...............
210124996has_tvTrue
210134996idneutral
210144997has_tvTrue
210154997idneutral
210164998has_tvTrue
210174998idneutral
210184999has_tvTrue
210194999idneutral
2102049910has_tvTrue
2102149910idneutral
2102249911has_tvTrue
2102349911idneutral
2102449912has_tvTrue
2102549912idneutral
2102649913has_tvTrue
2102749913idneutral
2102849914has_tvTrue
2102949914idneutral
2103049915has_tvTrue
2103149915idneutral
2103249916has_tvTrue
2103349916idneutral
2103449917has_tvTrue
2103549917idneutral
2103649918has_tvTrue
2103749918idneutral
2103849919has_tvTrue
2103949919idneutral
2104049920has_tvTrue
2104149920idinfected
\n", - "

21042 rows × 4 columns

\n", - "
" - ], - "text/plain": [ - " agent_id tstep attribute value\n", - "0 env 0 prob_tv_spread 0.01\n", - "1 env 0 prob_neighbor_spread 0.1\n", - "2 env 1 prob_tv_spread 0.01\n", - "3 env 1 prob_neighbor_spread 0.1\n", - "4 env 2 prob_tv_spread 0.01\n", - "5 env 2 prob_neighbor_spread 0.1\n", - "6 env 3 prob_tv_spread 0.01\n", - "7 env 3 prob_neighbor_spread 0.1\n", - "8 env 4 prob_tv_spread 0.01\n", - "9 env 4 prob_neighbor_spread 0.1\n", - "10 env 5 prob_tv_spread 0.01\n", - "11 env 5 prob_neighbor_spread 0.1\n", - "12 env 6 prob_tv_spread 0.01\n", - "13 env 6 prob_neighbor_spread 0.1\n", - "14 env 7 prob_tv_spread 0.01\n", - "15 env 7 prob_neighbor_spread 0.1\n", - "16 env 8 prob_tv_spread 0.01\n", - "17 env 8 prob_neighbor_spread 0.1\n", - "18 env 9 prob_tv_spread 0.01\n", - "19 env 9 prob_neighbor_spread 0.1\n", - "20 env 10 prob_tv_spread 0.01\n", - "21 env 10 prob_neighbor_spread 0.1\n", - "22 env 11 prob_tv_spread 0.01\n", - "23 env 11 prob_neighbor_spread 0.1\n", - "24 env 12 prob_tv_spread 0.01\n", - "25 env 12 prob_neighbor_spread 0.1\n", - "26 env 13 prob_tv_spread 0.01\n", - "27 env 13 prob_neighbor_spread 0.1\n", - "28 env 14 prob_tv_spread 0.01\n", - "29 env 14 prob_neighbor_spread 0.1\n", - "... ... ... ... ...\n", - "21012 499 6 has_tv True\n", - "21013 499 6 id neutral\n", - "21014 499 7 has_tv True\n", - "21015 499 7 id neutral\n", - "21016 499 8 has_tv True\n", - "21017 499 8 id neutral\n", - "21018 499 9 has_tv True\n", - "21019 499 9 id neutral\n", - "21020 499 10 has_tv True\n", - "21021 499 10 id neutral\n", - "21022 499 11 has_tv True\n", - "21023 499 11 id neutral\n", - "21024 499 12 has_tv True\n", - "21025 499 12 id neutral\n", - "21026 499 13 has_tv True\n", - "21027 499 13 id neutral\n", - "21028 499 14 has_tv True\n", - "21029 499 14 id neutral\n", - "21030 499 15 has_tv True\n", - "21031 499 15 id neutral\n", - "21032 499 16 has_tv True\n", - "21033 499 16 id neutral\n", - "21034 499 17 has_tv True\n", - "21035 499 17 id neutral\n", - "21036 499 18 has_tv True\n", - "21037 499 18 id neutral\n", - "21038 499 19 has_tv True\n", - "21039 499 19 id neutral\n", - "21040 499 20 has_tv True\n", - "21041 499 20 id infected\n", - "\n", - "[21042 rows x 4 columns]" - ] - }, - "execution_count": 15, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "config_file, df, config = list(analysis.get_data('soil_output/Spread_barabasi*prob_0.1*', process=False))[0]\n", - "df" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:17.192030Z", - "start_time": "2017-07-03T16:43:16.601046+02:00" - } - }, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
value0.010.1FalseTrueinfectedneutral
tstep
01.01.0163.0337.00.0500.0
11.01.0163.0337.03.0497.0
21.01.0163.0337.06.0494.0
31.01.0163.0337.012.0488.0
41.01.0163.0337.023.0477.0
51.01.0163.0337.036.0464.0
61.01.0163.0337.053.0447.0
71.01.0163.0337.079.0421.0
81.01.0163.0337.0119.0381.0
91.01.0163.0337.0164.0336.0
101.01.0163.0337.0204.0296.0
111.01.0163.0337.0254.0246.0
121.01.0163.0337.0293.0207.0
131.01.0163.0337.0336.0164.0
141.01.0163.0337.0365.0135.0
151.01.0163.0337.0391.0109.0
161.01.0163.0337.0407.093.0
171.01.0163.0337.0424.076.0
181.01.0163.0337.0442.058.0
191.01.0163.0337.0452.048.0
201.01.0163.0337.0464.036.0
\n", - "
" - ], - "text/plain": [ - "value 0.01 0.1 False True infected neutral\n", - "tstep \n", - "0 1.0 1.0 163.0 337.0 0.0 500.0\n", - "1 1.0 1.0 163.0 337.0 3.0 497.0\n", - "2 1.0 1.0 163.0 337.0 6.0 494.0\n", - "3 1.0 1.0 163.0 337.0 12.0 488.0\n", - "4 1.0 1.0 163.0 337.0 23.0 477.0\n", - "5 1.0 1.0 163.0 337.0 36.0 464.0\n", - "6 1.0 1.0 163.0 337.0 53.0 447.0\n", - "7 1.0 1.0 163.0 337.0 79.0 421.0\n", - "8 1.0 1.0 163.0 337.0 119.0 381.0\n", - "9 1.0 1.0 163.0 337.0 164.0 336.0\n", - "10 1.0 1.0 163.0 337.0 204.0 296.0\n", - "11 1.0 1.0 163.0 337.0 254.0 246.0\n", - "12 1.0 1.0 163.0 337.0 293.0 207.0\n", - "13 1.0 1.0 163.0 337.0 336.0 164.0\n", - "14 1.0 1.0 163.0 337.0 365.0 135.0\n", - "15 1.0 1.0 163.0 337.0 391.0 109.0\n", - "16 1.0 1.0 163.0 337.0 407.0 93.0\n", - "17 1.0 1.0 163.0 337.0 424.0 76.0\n", - "18 1.0 1.0 163.0 337.0 442.0 58.0\n", - "19 1.0 1.0 163.0 337.0 452.0 48.0\n", - "20 1.0 1.0 163.0 337.0 464.0 36.0" - ] - }, - "execution_count": 16, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "list(analysis.get_data('soil_output/Spread_barabasi*prob_0.1*', process=True))[0][1]" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "If you don't want to work with pandas, you can also use some pre-defined functions from soil to conveniently plot the results:" - ] - }, - { - "cell_type": "code", - "execution_count": 17, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:20.937324Z", - "start_time": "2017-07-03T16:43:17.193845+02:00" - }, - "scrolled": true - }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIhJxCgQiIhGnQCAiEnH/H+k3EVtiaGJ+AAAAAElFTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nESilVID7f/7YFJ+blHWwAAAAAElFTkSuQmCC\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\noUMmlSunJdAAAAAASUVORK5CYII=\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "analysis.plot_all('soil_output/Spread_barabasi*', attributes=['id'])" - ] - }, - { - "cell_type": "code", - "execution_count": 18, - "metadata": { - "ExecuteTime": { - "end_time": "2017-07-03T14:43:49.238790Z", - "start_time": "2017-07-03T16:43:20.939175+02:00" - } - }, - "outputs": [ - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAASUVORK5CYII=\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3XmcHHWd//HXZ64cPbkmMwOBIAmY5YgkgQQEgQXNcsrh\nrkGzZjmUw1W8FnVBWFf0pysr7uKyiwcIRjRyGBZBF1dYSAyGQxIIRzhMgCA5SGYmYZieJHNkPr8/\n6tuTzqR7umfS0zOpfj8fj350dVV11adreurT3++3vt8yd0dEREpX2WAHICIig0uJQESkxCkRiIiU\nOCUCEZESp0QgIlLilAhEREqcEoF0M7P5ZvbNuOxnoJnZ1Wb248GOI52ZXWRmfxgCcawxs78a7Dgk\nP0oEg8DMTjCzx8ys2cw2m9lSMzt6sOOSvnH3f3H3SwY7jjgxs9lm9rKZbTWzRWZ2YJb16s3sDjNb\nH/6PlprZe4sdb1woERSZmY0GfgP8J1AD7A98HWjr43bMzIb038/MKoZADOWDHUNfDIVjlstAxWhm\ntcB/A18l+t9YBtyVZfVq4ClgZlj3p8D/mFn1QMQWd0P6RBJTfwHg7ne4+w533+buD7r7c6FYv9TM\n/jP8ynnZzGan3mhmi83sW2a2FNgKHGRmY8zsVjPbYGbrzOybqZOfmR1sZo+YWZOZNZrZAjMbm7a9\nI83saTNrMbO7gOH5fAAzO8vMVpjZ26FkMy1t2Rozu9LMngNazawi137M7FIzWx1KR/eb2X5hvpnZ\nDWa2KRyP58zsPTlim29mPzCzB8ysFXi/mQ0zs++a2Z/NbKOZ/dDMRoT1TzaztWb2xbCfDWb28bDs\n6LB+Rdr2P2xmK8L0tWb28zyO1wVm9kb4O3w1vdokbGOhmf3czN4BLjKzY8zs8XB8N5jZf5lZVdr2\n3Mw+Z2avhb/r9T1/FITPu8XMXjezM/KIcbGZfdvM/hiO9X1mVhOWTQr7vNjM/gw8EuafY2YrQ5yL\nzeywHps92sxeDHH8xMxyfb/+Bljp7r909+3AtcB0Mzu054ru/pq7/7u7bwj/RzcDVcAhuT6rZODu\nehTxAYwGmoh+wZwBjEtbdhHQCfwDUAl8FGgGasLyxcCfgalARVjnV8CPgARQD/wR+GRY/93AKcAw\noA5YAnwvLKsC3kjb1xygA/hmjviPAjYB7wXKgQuBNcCwsHwNsAI4ABiRaz/AB4DGsN1hRCWlJWHZ\nacByYCxgwGHAhBzxzQ/H7HiiHzrDge8B9xP9chwF/Br4dlj/5HDMvxHiO5MoyY4Ly18Ezkjb/r3A\nF8P0tcDPc8RzOJAETgjH4rvh8/9V2jY6gA+FeEcQ/co9NvyNJwEvAV9I26YDi8LneRfwJ+CStO9Q\nB3Bp+Pt8ClgPWI44FwPrgPcQfZfuSX22EIMDt4dlI4h+0LQSfb8qgX8EVgNVad+DF8L3oAZYSu7v\n1n8AP+gx7wXgw3n8X80AtgNjBvt/fG98DHoApfgIJ7T5wNpwErof2Cf8E+/yT0t0Yj8/TC8GvpG2\nbB+iKqURafP+FliUZb8fAp4J03+ZYV+P5fHP+gPg//WY9wpwUpheA3wibVmv+wFuBb6Ttqw6nMgm\nESWJP4WTYlmex3Y+cHvaawsnrIPT5h0HvB6mTwa2ARVpyzcBx4bpK4EFYbqGKElMCK+vJXci+Gfg\njrTXI4F2dk0ES3Js4wvAvWmvHTg97fWngYfD9EXA6h77c2DfHPtYDFyX9vrwEGc5OxPBQWnLvwrc\nnfa6jCiRnJz2Pfj7tOVnAq/miOHW9BjCvKXARTneNxp4HvjKnv5vlupjyNdHxpG7v0T0D0so9v6c\n6Ffr74B1Hr7dwRvAfmmv30ybPpDo19gGM0vNK0utY2b1wI3AiUS/hMuALWG9/bLsK5cDgQvN7LNp\n86p6iTHXfvYDnk69cPekmTUB+7v7I2b2X8BNwLvM7F7gS+7+To4Y0/dfR3QyXJ52jIzoBJfS5O6d\naa+3EiUkiP42L1lU9/wR4FF335Bj/+n2S4/H3beGz5ctXszsL4B/B2aF2CuISkbZ3tPzO/JWj/2R\n9nl603OblUBtluX7kfZ3dPcuM3uTqM0rnxgzSRKd1NONBlqyvSFU8f0aeMLdv51j+5KF2ggGmbu/\nTPQrNlX3vb+lnbGIiv7r09+SNv0mUYmg1t3Hhsdod58aln87rD/N3UcDf0d0EgTYkGVfubwJfCtt\nf2PdfaS735Elxlz7WU+UXAAwswQwnujXJe5+o7vPJKoO+wvgy3nEmL7/RqJf/FPT4h3j7nk1Krr7\nOuBx4K+B84Gf5fO+NBuAiakX4cQ1vpd4ISp1vQxMCX+3q9n5d0s5IG2653ekv3pus4Po+GWKs+ff\nzcL71+1BjCuB6WnbTAAHh/m7MbNhRFWj64BP5ti29EKJoMjM7NDQMDkxvD6AqDrnibBKPfA5M6s0\ns/OIqpEeyLSt8Mv0QeDfzGy0mZVZ1EB8UlhlFNGvrLfNbH92PYk+TlQt9bnQoPs3wDF5fIRbgL83\ns/eGxtyEmX3QzEZlWT/Xfn4BfNzMZoR/7H8BnnT3NaGx9r1mVklUvbMd2JFHjN3cvSvEfEMoIWFm\n+5vZaX3YzO1EdeBHELUR9MVC4Gwze19o8P06u5/UexoFvAMkQ4nxUxnW+bKZjQvfn8+T/eqavvg7\nMzvczEYStZksdPdsx/tu4IMWXe5ZCXyR6EfJY2nrXG5mE0Oj89V5xHgv8J7QID+cqFrtufBjaRdh\nnwuJkvwF4e8s/aREUHwtRA2tT1p0VcsTRA1iXwzLnwSmEP0S+xYwx917ViWku4CoauZFomqfhcCE\nsOzrRI2wzcD/EF2aB4C7txNdpXFReN9H05dn4+7LiBoi/yu8b3XYRrb1e92Puz9MVN98D9Gv54OB\nuWHxaKKT+BaiqoUmosbWvroyxPlEuDLn/+jb1SX3Ev36vdfdW/uyY3dfCXwWuJPo87UQtUH0drnw\nl4CPhXVvIfMJ9D6i6qIVRH/bW/sSVxY/IyqdvkXUyP65bCu6+ytEJcz/JPqung2cHf7eKb8g+qHy\nWnj02onQ3RuADxN977cQ/Z+kvgtYdLXXD8PL9wFnAacS/dBJhseJ+X5Y2cl2rbqVwWRmFxFd/XHC\nYMciuzKzV4muxvq/PdxONfA2UbXP6/3chof3r96TWHpsczFRw/eQ6iktxaESgUgOZvZhovrxR/r5\n/rPNbGSo8/4u0RUuawoXocieUSKQ3Vg0hk4yw+O3gx0bQOjElCm+eQOwr8VEjbeXZ6uHNrN5WeJJ\nNXKeS9RQup6o2m+uD0JRPEuMRa1OGerfrVKlqiERkRKnEoGISIkbEh3KamtrfdKkSYMdhojIXmX5\n8uWN7l63p9sZEolg0qRJLFu2bLDDEBHZq5hZPqMB5KSqIRGREqdEICJS4pQIRERKnBKBiEiJUyIQ\nESlxeSUCi26t97xFtydcFubVmNlDZrYqPI8L883MbrTo1oPPmdlRA/kBRERkz/SlRPB+d5/h7rPC\n66uI7oo0BXg4vIbo9otTwuMyou75IiIyRO1JP4JziW7zB9H9dxcTDfd7LtGtAp1o2N+xZjah17s6\ntbwFj98EVQmoqg7PiQyvq6G8cg9CHjjL39jCkj81oCE7RGRvk28icODBMPztj9z9ZmCf1Mnd3Tek\nbvpBdKu69FvUrQ3zdkkEZnYZUYmBmRPK4HdX5xdJ+bDdE8SwajjhCjjopNzvL6DOHV08+OJGbnn0\nNZ7589sAWK5bjoiIDDH5JoLj3X19ONk/ZGa73TEoTaZT4W4/k0MyuRlg1qyZzpUPQ3treCR7mc6w\nbM1SGPPLoiWCZFsndz/1Jj957HXe3LyNA8eP5BvnTmXOzImMrBoSnbVFpATYdYXZTl5nLXdfH543\nWXQD8WOAjakqHzObQHTXJYhKAOn3Kp1IznuVGowYGz364wcnQGtj7vX20Ibmbcx/bA2/ePLPtGzv\nZNaB47jmzMM55fB9KC9TUUBE9k45E0G4mUaZu7eE6VOJ7md6P3AhcF14vi+85X7gM2Z2J9Gt5pp7\nbR8ohOo6aN2Ue71+Wrm+mR8/+jq/fnY9Xe6c8Z4JXHLiZI5817gB26eISLHkUyLYB7jXosrvCuAX\n7v6/ZvYUcLeZXQz8GTgvrP8AcCbRPWK3Ah8veNQ9JeqgsWB37QOgq8tZ/KdN3LLkdR5/rYlEVTnn\nH3cgnzh+MgfUjCzovkREBlPORODurwHTM8xvAmZnmO/A5QWJLl+JOmhtAPc9bq3d3rGDe59Zx61/\neJ3Vm5LsO3o4XznjUOYe8y7GjBiaVyyJiOyJeLRsVtdD57ao8XjYqH5toinZxs+eeIOfPf4GTa3t\nTN1vNN/76Aw+OG0CleXqgC0i8RWPRJAI92VIbupXItjUsp3Z//Z7WrZ38oFD67nkxMkcd9B4TNeC\nikgJiEkiCF0YWhth/MF9fvuf3krSsr2TH50/k9Om7lvg4EREhrZ41HkkaqPnfl451JhsA+Dd9dWF\nikhEZK8Rj0RQnSoRNPTr7alEUFs9rFARiYjsNeKRCEaGEkGyv4mgnaryMkYPj0dNmYhIX8QjEVRU\nwfCxe1Q1NL66So3DIlKS4pEIIKoe6mfVUFOyTdVCIlKy4pMIEvV7VDU0vrqqwAGJiOwdYpQIaveo\nakglAhEpVfFJBP2sGnJ3mpLtSgQiUrLikwgS9bC9GTrb+vS2d7Z30r6ji1pVDYlIiYpRIkh1Kuvb\nfQnUh0BESl18EkF3p7K+tRM0JdsBJQIRKV3xSQTdA8/1rZ0gVSLQVUMiUqrilwj62GDcpKohESlx\n8UkE/awaaki2YwbjRuqmMyJSmuKTCKoSUDmyX1VDNSOrqNDNZ0SkRMXr7Je6ZWUfaHgJESl18UoE\n1fV9rhrS8BIiUurilQgSdf2qGlKJQERKWfwSQZ+rhjS8hIiUtvglgq2N0LUjr9W3d+wg2dapqiER\nKWnxSgTV9eBdsG1LXqunOpPVqUQgIiUsXomgu3dxfg3GjWF4CZUIRKSUxTMR5HnlUGOLehWLiMQr\nEXT3Ls5vBNKm1pAIRikRiEjpilci6G/VUEJVQyJSuuKVCIaPhbKKvKuGGlraGDWsguGV5QMcmIjI\n0BWvRFBW1qe+BE2t7aoWEpGSF69EAH3qXdzY0qZqIREpeXknAjMrN7NnzOw34fVkM3vSzFaZ2V1m\nVhXmDwuvV4flkwYm9Cz6UCLQ8BIiIn0rEXweeCnt9b8CN7j7FGALcHGYfzGwxd3fDdwQ1iue6vo+\nVQ2pD4GIlLq8EoGZTQQ+CPw4vDbgA8DCsMpPgQ+F6XPDa8Ly2WH94kjURlcNufe6WueOLrZs1ThD\nIiL5lgi+B/wj0BVejwfedvfO8HotsH+Y3h94EyAsbw7r78LMLjOzZWa2rKGhbwPF9SpRDzvaoK2l\n19U2b23HXX0IRERyJgIzOwvY5O7L02dnWNXzWLZzhvvN7j7L3WfV1dXlFWxeujuV9Z5cGluiPgS1\naiwWkRJXkcc6xwPnmNmZwHBgNFEJYayZVYRf/ROB9WH9tcABwFozqwDGAJsLHnk2idroObkJxh+c\ndbXUgHMqEYhIqctZInD3r7j7RHefBMwFHnH3ecAiYE5Y7ULgvjB9f3hNWP6Ie44K+0JK5Fci6B5e\nQm0EIlLi9qQfwZXAFWa2mqgN4NYw/1ZgfJh/BXDVnoXYR91VQ733Lk5VDemqIREpdflUDXVz98XA\n4jD9GnBMhnW2A+cVILb+GRnapXMMPNeYbKOqooxRw/p0CEREYid+PYvLK2FETc6B5xqT7dQmqijm\nla0iIkNR/BIBhN7FuRJBmxqKRUSIayKors9ZNdTUquElREQgrokgUZe7aqilXQPOiYgQ50TQy+Wj\n7h6VCFQ1JCIS00RQXQdt70DH9oyL39nWSccOV9WQiAhxTQQ5OpU1pHoVqw+BiEhcE0EYuyhLIuge\nXkIlAhGRmCaCHAPPNYWb1isRiIjENRGkSgRZrhxKlQg0vISISNwTQS9VQ2UG40YqEYiIxDMRVI2E\nqupeEkE7NYkqyss0vISISDwTAey8ZWUGumm9iMhOMU4E2W9i36REICLSLb6JoDp7ImhMtquhWEQk\niG8iSNT22lisEoGISCTGiaAetjZB145dZm9t72Rr+w4lAhGRIL6JoLoevCtKBmlSnclUNSQiEolv\nIkjURs89qodS4wzVqUQgIgLEOhGEYSZ6XEKqEoGIyK5inAgy9y7WgHMiIruKbyKozpwImjTOkIjI\nLuKbCIaPhbLK3aqGGpPtjBpewbCK8kEKTERkaIlvIjALt6zc9Sb2Dck2NRSLiKSJbyKAqHqotWdj\nsTqTiYiki3ciSNRnrBpS+4CIyE4xTwS7Vw1peAkRkV3FOxGkqobcAejY0cXbWztUIhARSRPvRJCo\nhx3tsL0ZgM2tulexiEhPFYMdwIDq7lTWCCPG0tCizmQiQ0FHRwdr165l+/btgx3KXmH48OFMnDiR\nysrKAdl+zkRgZsOBJcCwsP5Cd/+amU0G7gRqgKeB89293cyGAbcDM4Em4KPuvmZAos+lu1PZJqh9\nN03dJQJVDYkMprVr1zJq1CgmTZqEmW4Z2xt3p6mpibVr1zJ58uQB2Uc+VUNtwAfcfTowAzjdzI4F\n/hW4wd2nAFuAi8P6FwNb3P3dwA1hvcHRY5iJRpUIRIaE7du3M378eCWBPJgZ48ePH9DSU85E4JFk\neFkZHg58AFgY5v8U+FCYPje8JiyfbYP11+4x8FxTa0gEo5QIRAabkkD+BvpY5dVYbGblZrYC2AQ8\nBLwKvO3unWGVtcD+YXp/4E2AsLwZGJ9hm5eZ2TIzW9bQkPlOYnts5HjAdpYIku0MqygjUaXhJURE\nUvJKBO6+w91nABOBY4DDMq0WnjOlLt9thvvN7j7L3WfV1dXlG2/flFfAyJpdqoZqq4fpl4iI7Ka6\nunqwQxg0fbp81N3fBhYDxwJjzSzV2DwRWB+m1wIHAITlY4DNhQi2X9J6Fze2tquhWESkh5yJwMzq\nzGxsmB4B/BXwErAImBNWuxC4L0zfH14Tlj/i7ruVCIqmum63EoGIxN+VV17J97///e7X1157LV//\n+teZPXs2Rx11FEcccQT33Xffbu9bvHgxZ511Vvfrz3zmM8yfPx+A5cuXc9JJJzFz5kxOO+00NmzY\nMOCfoxjyKRFMABaZ2XPAU8BD7v4b4ErgCjNbTdQGcGtY/1ZgfJh/BXBV4cPug0RaItDwEiIlY+7c\nudx1113dr++++24+/vGPc++99/L000+zaNEivvjFL5Lv79SOjg4++9nPsnDhQpYvX84nPvEJrrnm\nmoEKv6hy9iNw9+eAIzPMf42ovaDn/O3AeQWJrhAS9ZBsoKvL2dyqAedESsWRRx7Jpk2bWL9+PQ0N\nDYwbN44JEybwD//wDyxZsoSysjLWrVvHxo0b2XfffXNu75VXXuGFF17glFNOAWDHjh1MmDBhoD9G\nUcS7ZzFEN7Fvb6H5nXfo7HKVCERKyJw5c1i4cCFvvfUWc+fOZcGCBTQ0NLB8+XIqKyuZNGnSbtfn\nV1RU0NXV1f06tdzdmTp1Ko8//nhRP0MxxHusIYDqqC9Bc1PUlq0+BCKlY+7cudx5550sXLiQOXPm\n0NzcTH19PZWVlSxatIg33nhjt/cceOCBvPjii7S1tdHc3MzDDz8MwCGHHEJDQ0N3Iujo6GDlypVF\n/TwDpQRKBFEiaGmMGnVqE6oaEikVU6dOpaWlhf33358JEyYwb948zj77bGbNmsWMGTM49NBDd3vP\nAQccwEc+8hGmTZvGlClTOPLIqGa8qqqKhQsX8rnPfY7m5mY6Ozv5whe+wNSpU4v9sQquBBJB1Edh\n65YNwFiVCERKzPPPP989XVtbm7VqJ5lMdk9/5zvf4Tvf+c5u68yYMYMlS5YUPshBVgJVQ1Ei6Hxn\nIwDjVSIQEdlF/BNBKBF0tWyivMwYN1KJQEQkXfwTQeUIqBqFbW2kJlFFWZmGlxARSRf/RABQXUfl\n9kZVC4mIZFAaiSBRz4j2JurUUCwispsSSQS1VHduUWcyEZEMSiMRVNcztuttVQ2JSLf3ve99Odd5\n9NFHmTp1KjNmzGDbtm192v6vfvUrXnzxxT7HNRjDYZdEImgfNp6xJKlL6IY0IhJ57LHHcq6zYMEC\nvvSlL7FixQpGjBjRp+33NxEMhpJIBMmKGsrMmVC5dbBDEZEhIvXLe/HixZx88snMmTOHQw89lHnz\n5uHu/PjHP+buu+/mG9/4BvPmzQPg+uuv5+ijj2batGl87Wtf697W7bffzrRp05g+fTrnn38+jz32\nGPfffz9f/vKXmTFjBq+++iqvvvoqp59+OjNnzuTEE0/k5ZdfBuD111/nuOOO4+ijj+arX/1q8Q8E\npdCzGNhSNpYaYN+KdwY7FBHp4eu/XsmL6wv7v3n4fqP52tn5D/3wzDPPsHLlSvbbbz+OP/54li5d\nyiWXXMIf/vAHzjrrLObMmcODDz7IqlWr+OMf/4i7c84557BkyRLGjx/Pt771LZYuXUptbS2bN2+m\npqaGc845p/u9ALNnz+aHP/whU6ZM4cknn+TTn/40jzzyCJ///Of51Kc+xQUXXMBNN91U0OOQr5JI\nBI0+moOBOlMiEJHdHXPMMUycOBGIhpFYs2YNJ5xwwi7rPPjggzz44IPdYw8lk0lWrVrFs88+y5w5\nc6itrQWgpqZmt+0nk0kee+wxzjtv5wj9bW1tACxdupR77rkHgPPPP58rr7yy8B8wh5JIBJu6RgMw\nzt8e5EhEpKe+/HIfKMOG7byisLy8nM7Ozt3WcXe+8pWv8MlPfnKX+TfeeGPO+6B3dXUxduxYVqxY\nkXH5YN9HvSTaCNZ1jAKgunPLIEciInur0047jdtuu617cLp169axadMmZs+ezd13301TUxMAmzdH\nt2gfNWoULS0tAIwePZrJkyfzy1/+EoiSyrPPPgvA8ccfz5133glEjdODoSQSwfptFbRTQcW2xsEO\nRUT2Uqeeeiof+9jHOO644zjiiCOYM2cOLS0tTJ06lWuuuYaTTjqJ6dOnc8UVVwDRvRCuv/56jjzy\nSF599VUWLFjArbfeyvTp05k6dWr3/ZL/4z/+g5tuuomjjz6a5ubmQflsNpj3lU+ZNWuWL1u2bMC2\nf/mCp/nn1eexz7RT4a9/MGD7EZH8vPTSSxx22GGDHcZeJdMxM7Pl7j5rT7ddEiWChmQbyYpx3Tex\nFxGRnUoiETQl29hWWQOtmwY7FBGRIackEkFjsp324bWQVIlARKSn2CeC9s4umrd10DWyNqoaGgJt\nIiIiQ0nsE8Hm1nYArLoeujpgu/oSiIiki30iaExGvfcqx+wTzVD1kIjILmKfCBpCIhg+dt9ohq4c\nEpECWrNmDb/4xS/69d7BGHI6k9gngqZkVDVUXTMhmqErh0SkgHpLBJmGqhiKYp8IUlVDY+r2j2a0\nqnexiEQn8MMOO4xLL72UqVOncuqpp7Jt27asw0VfdNFFLFy4sPv9qV/zV111FY8++igzZszghhtu\nYP78+Zx33nmcffbZnHrqqSSTSWbPns1RRx3FEUcc0d2jeCiJ/aBzjS1tjKgsJzG2HqwMkioRiAwp\nv70K3nq+sNvc9wg447qcq61atYo77riDW265hY985CPcc889/OQnP8k4XHQ21113Hd/97nf5zW9+\nA8D8+fN5/PHHee6556ipqaGzs5N7772X0aNH09jYyLHHHss555wz6APNpYt9ImhqbWd8dRWUlcPI\n8aoaEpFukydPZsaMGQDMnDmTNWvWZB0uui9OOeWU7uGo3Z2rr76aJUuWUFZWxrp169i4cSP77rtv\nYT5EAcQ+ETQm23betD5Rp6ohkaEmj1/uA6Xn8NMbN27MOlx0RUUFXV1dQHRyb29vz7rdRCLRPb1g\nwQIaGhpYvnw5lZWVTJo0ie3btxfwU+y5nG0EZnaAmS0ys5fMbKWZfT7MrzGzh8xsVXgeF+abmd1o\nZqvN7DkzO2qgP0RvGpPt1FaHm9Yn6lQ1JCJZ9TZc9KRJk1i+fDkA9913Hx0dHcCuw01n0tzcTH19\nPZWVlSxatIg33nhjgD9F3+XTWNwJfNHdDwOOBS43s8OBq4CH3X0K8HB4DXAGMCU8LgMGdbjPXUoE\n1fWqGhKRXmUbLvrSSy/l97//PccccwxPPvlk96/+adOmUVFRwfTp07nhhht22968efNYtmwZs2bN\nYsGCBRx66KFF/Tz56PMw1GZ2H/Bf4XGyu28wswnAYnc/xMx+FKbvCOu/klov2zYHahjqri5nyj/9\nlk+ddDBfOu0Q+N+vwNO3w9XrCr4vEcmfhqHuuyEzDLWZTQKOBJ4E9kmd3MNzfVhtf+DNtLetDfN6\nbusyM1tmZssaGgamk9fb2zrY0eVRYzFEVUPtSWjfOiD7ExHZG+WdCMysGrgH+IK793YX+EzXRO1W\n7HD3m919lrvPqquryzeMPkn1IdilagjUu1hEJE1eicDMKomSwAJ3/+8we2OoEiI8pyrf1wIHpL19\nIrC+MOH2TWNLj0SQCAlHiUBk0A2FuyPuLQb6WOVz1ZABtwIvufu/py26H7gwTF8I3Jc2/4Jw9dCx\nQHNv7QMDqTGMPLrLVUOgK4dEBtnw4cNpampSMsiDu9PU1MTw4cMHbB/59CM4HjgfeN7MUhfXXg1c\nB9xtZhcDfwZSPTAeAM4EVgNbgY8XNOI+UIlAZGiaOHEia9euZaDaB+Nm+PDhTJw4ccC2nzMRuPsf\nyFzvDzA7w/oOXL6HcRVEU2sb5WXGmBGV0YzuRKASgchgqqysZPLkyYMdhgSxHnSusaWd8YkqyspC\nHqscDsPG6J4EIiJp4p0I0juTpSRqVTUkIpIm3okgNeBcuup6JQIRkTTxTgQtbdTtViKoUyIQEUkT\n20Tg7lHV0KgMiUCXj4qIdIttImht30FbZxfjExmqhrZthh0dgxOYiMgQE9tEsFsfgpTUJaRbm4oc\nkYjI0BTfRBDGGdqtsVi9i0VEdhHjRJAaXqJHiaB74DklAhERiHUiiEoEdZkai0G3rBQRCWKbCJpC\niaCmZ2PANeYjAAAOF0lEQVSxqoZERHYR20TQmGxj7MhKKst7fMRho6BiuPoSiIgEsU4Eu7UPAJip\nU5mISJrYJoKmZPvufQhS1KlMRKRbbBNBxl7FKRpvSESkW2wTQUOyjdqsJQKNQCoikhLLRNDWuYOW\n7Z2Z2wgAEqFE0NVV3MBERIagWCaC1KWjWauGEnXQ1Qnb3y5iVCIiQ1OsE0HWxuLu3sWqHhIRiWUi\nSPUq7rVEAEoEIiLENBE0pIaXyNpGoN7FIiIpsUwE3VVDPUceTVHVkIhIt1gmgsZkGyOryhlZVZF5\nhRE1YGVKBCIixDgRZC0NAJSVwchaVQ2JiBDTRNCUbM/ehyBFvYtFRICYJoKsA86l08BzIiJArBNB\nL1VDoIHnRESC2CWCHV3O5lZVDYmI5Ct2iWDL1na6PMO9intK1ELHVmhvLU5gIiJDVOwSQc4+BCmJ\n0JdA1UMiUuJyJgIzu83MNpnZC2nzaszsITNbFZ7HhflmZjea2Woze87MjhrI4DPpHl4in6oh0E3s\nRaTk5VMimA+c3mPeVcDD7j4FeDi8BjgDmBIelwE/KEyY+duZCHKVCGqj51aVCESktOVMBO6+BNjc\nY/a5wE/D9E+BD6XNv90jTwBjzWxCoYLNR2NqCOqcbQSqGhIRgf63Eezj7hsAwnM4q7I/8GbaemvD\nvN2Y2WVmtszMljU0FO7qncZkGxVlxpgRlb2v2D0CqaqGRKS0Fbqx2DLM80wruvvN7j7L3WfV1dUV\nLIDGlmh4CbNMoaSpqILhY1Q1JCIlr7+JYGOqyic8p86ma4ED0tabCKzvf3h915RPH4KURL2qhkSk\n5PU3EdwPXBimLwTuS5t/Qbh66FigOVWFVCx5DS+RkqhT1ZCIlLx8Lh+9A3gcOMTM1prZxcB1wClm\ntgo4JbwGeAB4DVgN3AJ8ekCi7kVTsj13H4KU6jpVDYlIycsyYP9O7v63WRbNzrCuA5fvaVD95e40\nJNuy35msp0Q9tC4Z2KBERIa4WPUsbmnrpL2zK/8SQaIOtm2BHR0DG5iIyBAWq0TQlG8fgpRq3cRe\nRCRWiSDv4SVSErp3sYhIvBJBS5QI+lQ1BJBUIhCR0hWvRNAaVQ3l3VjcXTWkK4dEpHTFKxGEEkFN\nIt8SgaqGRETilQiSbYwbWUlFeZ4fqyoBFSPUu1hESlqsEkFTsg/DSwCYhU5l6l0sIqUrVomgMdmW\nf0NxSkK9i0WktMUqEfRpwLmURL2uGhKRkharRNDY0ocB51Kq69RYLCIlLTaJYHvHDlraOnPforKn\nREgEXV0DE5iIyBAXm0TQ1NrH4SVSEvXgO6Ixh0RESlBsEkGqD0G/qoZA1UMiUrLikwiSfRxeIiWh\n3sUiUtpikwj6PPJoinoXi0iJi00iaOjryKMpGnhOREpcbBJBU7KdRFU5I6rK+/bGEePAylU1JCIl\nKzaJoDHZRu2oPpYGAMrKdl5CKiJSgmKVCMbnO+poT4k6VQ2JSMmKTSLo84Bz6ao13pCIlK7YJIJ+\nVw1BdOWQqoZEpETFIhF07uhi89Z2avtdNVQbVQ25FzYwEZG9QCwSwZatHbjT/xJBdT10boP21sIG\nJiKyF4hFImjsbx+ClO5OZWonEJHSE6tEsEdXDQG0vFWgiERE9h6xSATdw0v0t2qo9t1QVgG/+Cg8\n+E/QvLaA0YmIDG2xSATdVUOJfiaCcZPgkv+DKafA49+H702DhRfD+mcKF6SIyBAVk0TQTlV5GaNH\nVPR/I/sdCXNug8+vgGM/BX/6Hdx8Mvzkg/DKb3XjGhGJrZgkguim9Wa25xsb+y447VtwxUo49Zuw\nZQ3cMRduOhqeuhXat+75PkREhpBYJYKCGj4G3vfZqITw4Vth2Cj4nyvghqnwyLcgqSuMRCQeBiQR\nmNnpZvaKma02s6sGYh/p9mh4iVzKK+GIOXDpIrjoAXjXsbDkerjhPXDfZ2DTywOzXxGRItmDSvXM\nzKwcuAk4BVgLPGVm97v7i/m8v6vL2daxg9b2Tra2hef2HbS2ddKaet3WSWv7Dra2R/Neb2zlkH1H\nFfqj7MoMJh0fPRpXwxM3wYo74JmfwbtPgeMuh4NOjtYTEdmLFDwRAMcAq939NQAzuxM4F8iaCF55\nq4VZ3/w/toaTfr7KDBLDKhg1vIITp9Tuadz5q303nHUDvP+fYNlt8Meb4WcfgjEHQFWieHGIiBTA\nQCSC/YE3016vBd7bcyUzuwy4DGD0fgdxyuH7kKgqZ+Swil2fqypIDIueq4dVMLKqnER4HlZRVpgG\n4v5KjIeTvhy1JTz/S3j1YXBdXSQixfLHgmzFvMADrZnZecBp7n5JeH0+cIy7fzbbe2bNmuXLli0r\naBwiInFnZsvdfdaebmcgGovXAgekvZ4IrB+A/YiISAEMRCJ4CphiZpPNrAqYC9w/APsREZECKHgb\ngbt3mtlngN8B5cBt7r6y0PsREZHCGIjGYtz9AeCBgdi2iIgUVix6FouISP8pEYiIlDglAhGREqdE\nICJS4greoaxfQZi1AK8Mdhx5qAUaBzuIPCjOwtkbYgTFWWh7S5yHuPseD7Q2IFcN9cMrhegdN9DM\nbJniLJy9Ic69IUZQnIW2N8VZiO2oakhEpMQpEYiIlLihkghuHuwA8qQ4C2tviHNviBEUZ6GVVJxD\norFYREQGz1ApEYiIyCBRIhARKXFFTQS5bmpvZsPM7K6w/Ekzm1TM+EIMB5jZIjN7ycxWmtnnM6xz\nspk1m9mK8PjnYscZ4lhjZs+HGHa7jMwiN4bj+ZyZHVXk+A5JO0YrzOwdM/tCj3UG7Via2W1mtsnM\nXkibV2NmD5nZqvA8Lst7LwzrrDKzC4sc4/Vm9nL4m95rZmOzvLfX70cR4rzWzNal/W3PzPLeXs8L\nRYjzrrQY15jZiizvLebxzHgeGrDvp7sX5UE0JPWrwEFAFfAscHiPdT4N/DBMzwXuKlZ8aTFMAI4K\n06OAP2WI82TgN8WOLUOsa4DaXpafCfwWMOBY4MlBjLUceAs4cKgcS+AvgaOAF9LmfQe4KkxfBfxr\nhvfVAK+F53FhelwRYzwVqAjT/5opxny+H0WI81rgS3l8L3o9Lwx0nD2W/xvwz0PgeGY8Dw3U97OY\nJYLum9q7ezuQuql9unOBn4bphcBsK/JNid19g7s/HaZbgJeI7sO8NzoXuN0jTwBjzWzCIMUyG3jV\n3d8YpP3vxt2XAJt7zE7/Dv4U+FCGt54GPOTum919C/AQcHqxYnT3B929M7x8gugugIMqy7HMRz7n\nhYLpLc5wrvkIcMdA7T9fvZyHBuT7WcxEkOmm9j1PsN3rhC96MzC+KNFlEKqmjgSezLD4ODN71sx+\na2ZTixrYTg48aGbLzeyyDMvzOebFMpfs/2BD4Vim7OPuGyD6ZwTqM6wzlI7rJ4hKfZnk+n4Uw2dC\nFdZtWaoxhtKxPBHY6O6rsiwflOPZ4zw0IN/PYiaCTL/se167ms86RWFm1cA9wBfc/Z0ei58mquKY\nDvwn8Ktixxcc7+5HAWcAl5vZX/ZYPiSOp0W3LD0H+GWGxUPlWPbFUDmu1wCdwIIsq+T6fgy0HwAH\nAzOADUTVLj0NiWMZ/C29lwaKfjxznIeyvi3DvF6PaTETQT43te9ex8wqgDH0r7i5R8yskujgL3D3\n/+653N3fcfdkmH4AqDSz2iKHibuvD8+bgHuJitnp8jnmxXAG8LS7b+y5YKgcyzQbU9Vn4XlThnUG\n/biGBsCzgHkeKoZ7yuP7MaDcfaO773D3LuCWLPsf9GMJ3eebvwHuyrZOsY9nlvPQgHw/i5kI8rmp\n/f1AqoV7DvBIti/5QAn1hLcCL7n7v2dZZ99U24WZHUN0HJuKFyWYWcLMRqWmiRoQX+ix2v3ABRY5\nFmhOFSuLLOsvraFwLHtI/w5eCNyXYZ3fAaea2bhQ3XFqmFcUZnY6cCVwjrtvzbJOPt+PAdWjPeqv\ns+w/n/NCMfwV8LK7r820sNjHs5fz0MB8P4vRAp7Wmn0mUev3q8A1Yd43iL7QAMOJqg9WA38EDipm\nfCGGE4iKUc8BK8LjTODvgb8P63wGWEl0hcMTwPsGIc6Dwv6fDbGkjmd6nAbcFI7388CsQYhzJNGJ\nfUzavCFxLImS0wagg+hX1MVEbVIPA6vCc01Ydxbw47T3fiJ8T1cDHy9yjKuJ6oBT38/UlXb7AQ/0\n9v0ocpw/C9+754hOYBN6xhle73ZeKGacYf781Hcybd3BPJ7ZzkMD8v3UEBMiIiVOPYtFREqcEoGI\nSIlTIhARKXFKBCIiJU6JQESkxCkRSEkxs7Fm9ukc61xdrHhEhgJdPiolJYzb8ht3f08v6yTdvbpo\nQYkMsorBDkCkyK4DDg5jzj8FHAKMJvpf+BTwQWBEWL7S3eeZ2d8BnyMaJvlJ4NPuvsPMksCPgPcD\nW4C57t5Q9E8ksodUNSSl5iqi4bBnAC8DvwvT04EV7n4VsM3dZ4QkcBjwUaIBx2YAO4B5YVsJojGU\njgJ+D3yt2B9GpBBUIpBS9hRwWxjc61fununOVLOBmcBTYUikEewc6KuLnYOU/RzYbYBCkb2BSgRS\nsjy6SclfAuuAn5nZBRlWM+CnoYQww90Pcfdrs21ygEIVGVBKBFJqWohu/YeZHQhscvdbiEZ6TN3T\nuSOUEiAa2GuOmdWH99SE90H0/zMnTH8M+EMR4hcpOFUNSUlx9yYzWxpuXp4AWs2sA0gCqRLBzcBz\nZvZ0aCf4J6I7U5URjVp5OfAG0ApMNbPlRHfT+2ixP49IIejyUZF+0mWmEheqGhIRKXEqEYiIlDiV\nCERESpwSgYhIiVMiEBEpcUoEIiIlTolARKTE/X/B7HgwUKJkHAAAAABJRU5ErkJggg==\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhPdhAd1fv7EAAAAASUVORK5CYII=\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEWCAYAAABrDZDcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIjLK/X+WBgkuYDfsgAAAAABJRU5ErkJggg==\n", - "text/plain": [ - "" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "analysis.plot_all('soil_output/Spread_erdos*', attributes=['id'])" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.6.1" - }, - "toc": { - "colors": { - "hover_highlight": "#DAA520", - "navigate_num": "#000000", - "navigate_text": "#333333", - "running_highlight": "#FF0000", - "selected_highlight": "#FFD700", - "sidebar_border": "#EEEEEE", - "wrapper_background": "#FFFFFF" - }, - "moveMenuLeft": true, - "nav_menu": { - "height": "31px", - "width": "252px" - }, - "navigate_menu": true, - "number_sections": true, - "sideBar": true, - "threshold": 4, - "toc_cell": false, - "toc_section_display": "block", - "toc_window_display": true, - "widenNotebook": false - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/soil/__init__.py b/soil/__init__.py index fc0732b..ef3cf16 100644 --- a/soil/__init__.py +++ b/soil/__init__.py @@ -4,15 +4,20 @@ import os import pdb import logging -__version__ = "0.9.7" +__version__ = "0.10" try: basestring except NameError: basestring = str -logging.basicConfig()#format=FORMAT) +logging.basicConfig() + +from . import agents +from . import simulation +from . import environment from . import utils +from . import analysis def main(): diff --git a/soil/agents/BassModel.py b/soil/agents/BassModel.py index a9f3498..5d50102 100644 --- a/soil/agents/BassModel.py +++ b/soil/agents/BassModel.py @@ -1,8 +1,8 @@ import random -from . import NetworkAgent +from . import BaseAgent -class BassModel(NetworkAgent): +class BassModel(BaseAgent): """ Settings: innovation_prob diff --git a/soil/agents/BigMarketModel.py b/soil/agents/BigMarketModel.py index 0710691..934a89c 100644 --- a/soil/agents/BigMarketModel.py +++ b/soil/agents/BigMarketModel.py @@ -1,8 +1,8 @@ import random -from . import NetworkAgent +from . import BaseAgent -class BigMarketModel(NetworkAgent): +class BigMarketModel(BaseAgent): """ Settings: Names: diff --git a/soil/agents/CounterModel.py b/soil/agents/CounterModel.py index 851f3c2..55a852b 100644 --- a/soil/agents/CounterModel.py +++ b/soil/agents/CounterModel.py @@ -1,7 +1,7 @@ -from . import NetworkAgent +from . import BaseAgent -class CounterModel(NetworkAgent): +class CounterModel(BaseAgent): """ Dummy behaviour. It counts the number of nodes in the network and neighbors in each step and adds it to its state. @@ -16,7 +16,7 @@ class CounterModel(NetworkAgent): self.state['total'] = total -class AggregatedCounter(NetworkAgent): +class AggregatedCounter(BaseAgent): """ Dummy behaviour. It counts the number of nodes in the network and neighbors in each step and adds it to its state. @@ -28,4 +28,5 @@ class AggregatedCounter(NetworkAgent): neighbors = len(list(self.get_neighboring_agents())) self.state['times'] = self.state.get('times', 0) + 1 self.state['neighbors'] = self.state.get('neighbors', 0) + neighbors - self.state['total'] = self.state.get('total', 0) + total + self.state['total'] = total = self.state.get('total', 0) + total + self.debug('Running for step: {}. Total: {}'.format(self.now, total)) diff --git a/soil/agents/ModelM2.py b/soil/agents/ModelM2.py index 750dd4b..5d6b0db 100644 --- a/soil/agents/ModelM2.py +++ b/soil/agents/ModelM2.py @@ -1,9 +1,9 @@ import random import numpy as np -from . import NetworkAgent +from . import BaseAgent -class SpreadModelM2(NetworkAgent): +class SpreadModelM2(BaseAgent): """ Settings: prob_neutral_making_denier @@ -104,7 +104,7 @@ class SpreadModelM2(NetworkAgent): neighbor.state['id'] = 2 # Cured -class ControlModelM2(NetworkAgent): +class ControlModelM2(BaseAgent): """ Settings: prob_neutral_making_denier diff --git a/soil/agents/SISaModel.py b/soil/agents/SISaModel.py index d5281fc..9aa6c2e 100644 --- a/soil/agents/SISaModel.py +++ b/soil/agents/SISaModel.py @@ -1,9 +1,9 @@ import random import numpy as np -from . import FSM, NetworkAgent, state +from . import FSM, state -class SISaModel(FSM, NetworkAgent): +class SISaModel(FSM): """ Settings: neutral_discontent_spon_prob diff --git a/soil/agents/SentimentCorrelationModel.py b/soil/agents/SentimentCorrelationModel.py index 2e034cf..6294d7d 100644 --- a/soil/agents/SentimentCorrelationModel.py +++ b/soil/agents/SentimentCorrelationModel.py @@ -1,8 +1,8 @@ import random -from . import NetworkAgent +from . import BaseAgent -class SentimentCorrelationModel(NetworkAgent): +class SentimentCorrelationModel(BaseAgent): """ Settings: outside_effects_prob diff --git a/soil/agents/__init__.py b/soil/agents/__init__.py index 84d2e15..4d88d42 100644 --- a/soil/agents/__init__.py +++ b/soil/agents/__init__.py @@ -72,9 +72,10 @@ class BaseAgent(nxsim.BaseAgent, metaclass=MetaAgent): return None def run(self): + interval = self.env.interval while self.alive: res = self.step() - yield res or self.env.timeout(self.env.interval) + yield res or self.env.timeout(interval) def die(self, remove=False): self.alive = False @@ -99,7 +100,10 @@ class BaseAgent(nxsim.BaseAgent, metaclass=MetaAgent): count += 1 return count - def get_agents(self, state_id=None, limit_neighbors=False, **kwargs): + def count_neighboring_agents(self, state_id=None): + return len(super().get_agents(state_id, limit_neighbors=True)) + + def get_agents(self, state_id=None, limit_neighbors=False, iterator=False, **kwargs): if limit_neighbors: agents = super().get_agents(state_id, limit_neighbors) else: @@ -113,9 +117,13 @@ class BaseAgent(nxsim.BaseAgent, metaclass=MetaAgent): return False return True - return filter(matches_all, agents) + f = filter(matches_all, agents) + if iterator: + return f + return list(f) - def log(self, message, level=logging.INFO, **kwargs): + def log(self, message, *args, level=logging.INFO, **kwargs): + message = message + " ".join(str(i) for i in args) message = "\t@{:>5}:\t{}".format(self.now, message) for k, v in kwargs: message += " {k}={v} ".format(k, v) @@ -130,11 +138,6 @@ class BaseAgent(nxsim.BaseAgent, metaclass=MetaAgent): def info(self, *args, **kwargs): return self.log(*args, level=logging.INFO, **kwargs) -class NetworkAgent(BaseAgent, nxsim.BaseNetworkAgent): - - def count_neighboring_agents(self, state_id=None): - return self.count_agents(state_id, limit_neighbors=True) - def state(func): @@ -150,7 +153,7 @@ def state(func): try: self.state['id'] = next_state.id except AttributeError: - raise NotImplemented('State id %s is not valid.' % next_state) + raise ValueError('State id %s is not valid.' % next_state) return when func_wrapper.id = func.__name__ diff --git a/soil/analysis.py b/soil/analysis.py index 6a5789b..a99ed04 100644 --- a/soil/analysis.py +++ b/soil/analysis.py @@ -4,20 +4,175 @@ import glob import yaml from os.path import join +from . import utils -def get_data(pattern, process=True, attributes=None): + +def read_data(*args, group=False, **kwargs): + iterable = _read_data(*args, **kwargs) + if group: + return group_trials(iterable) + else: + return list(iterable) + + +def _read_data(pattern, keys=None, convert_types=False, + process=None, from_csv=False, **kwargs): for folder in glob.glob(pattern): config_file = glob.glob(join(folder, '*.yml'))[0] config = yaml.load(open(config_file)) - for trial_data in sorted(glob.glob(join(folder, '*.environment.csv'))): - df = pd.read_csv(trial_data) - if process: - if attributes is not None: - df = df[df['attribute'].isin(attributes)] - df = df.pivot_table(values='attribute', index='tstep', columns=['value'], aggfunc='count').fillna(0) - yield config_file, df, config + df = None + if from_csv: + for trial_data in sorted(glob.glob(join(folder, + '*.environment.csv'))): + df = read_csv(trial_data, convert_types=convert_types) + if process: + df = process(df, **kwargs) + yield config_file, df, config + else: + for trial_data in sorted(glob.glob(join(folder, '*.db.sqlite'))): + df = read_sql(trial_data, convert_types=convert_types, + keys=keys) + if process: + df = process(df, **kwargs) + yield config_file, df, config + + +def read_csv(filename, keys=None, convert_types=False, **kwargs): + ''' + Read a CSV in canonical form: :: + + + + ''' + df = pd.read_csv(filename) + if convert_types: + df = convert_types_slow(df) + if keys: + df = df[df['key'].isin(keys)] + return df + + +def read_sql(filename, keys=None, convert_types=False, limit=-1): + condition = '' + if keys: + k = map(lambda x: "\'{}\'".format(x), keys) + condition = 'where key in ({})'.format(','.join(k)) + query = 'select * from history {} limit {}'.format(condition, limit) + df = pd.read_sql_query(query, 'sqlite:///{}'.format(filename)) + if convert_types: + df = convert_types_slow(df) + return df + + +def convert_row(row): + row['value'] = utils.convert(row['value'], row['value_type']) + return row + + +def convert_types_slow(df): + '''This is a slow operation.''' + dtypes = get_types(df) + for k, v in dtypes.items(): + t = df[df['key']==k] + t['value'] = t['value'].astype(v) + df = df.apply(convert_row, axis=1) + return df + +def split_df(df): + ''' + Split a dataframe in two dataframes: one with the history of agents, + and one with the environment history + ''' + envmask = (df['agent_id'] == 'env') + n_env = envmask.sum() + if n_env == len(df): + return df, None + elif n_env == 0: + return None, df + agents, env = [x for _, x in df.groupby(envmask)] + return env, agents + + +def process(df, **kwargs): + ''' + Process a dataframe in canonical form ``(t_step, agent_id, key, value, value_type)`` into + two dataframes with a column per key: one with the history of the agents, and one for the + history of the environment. + ''' + env, agents = split_df(df) + return process_one(env, **kwargs), process_one(agents, **kwargs) + + +def get_types(df): + dtypes = df.groupby(by=['key'])['value_type'].unique() + return {k:v[0] for k,v in dtypes.iteritems()} + + +def process_one(df, *keys, columns=['key'], values='value', + index=['t_step', 'agent_id'], aggfunc='first', **kwargs): + ''' + Process a dataframe in canonical form ``(t_step, agent_id, key, value, value_type)`` into + a dataframe with a column per key + ''' + if df is None: + return df + if keys: + df = df[df['key'].isin(keys)] + + dtypes = get_types(df) + + df = df.pivot_table(values=values, index=index, columns=columns, + aggfunc=aggfunc, **kwargs) + df = df.fillna(0).astype(dtypes) + return df + + +def get_count_processed(df, *keys): + if keys: + df = df[list(keys)] + # p = df.groupby(level=0).apply(pd.Series.value_counts) + p = df.unstack().apply(pd.Series.value_counts, axis=1) + return p + + +def get_count(df, *keys): + if keys: + df = df[df['key'].isin(keys)] + p = df.groupby(by=['t_step', 'key', 'value']).size().unstack(level=[1,2]).fillna(0) + return p + + +def get_value(df, *keys, aggfunc='sum'): + if keys: + df = df[df['key'].isin(keys)] + p = process_one(df, *keys) + p = p.groupby(level='t_step').agg(aggfunc) + return p def plot_all(*args, **kwargs): - for config_file, df, config in sorted(get_data(*args, **kwargs)): + ''' + Read all the trial data and plot the result of applying a function on them. + ''' + dfs = do_all(*args, **kwargs) + ps = [] + for line in dfs: + f, df, config = line df.plot(title=config['name']) + ps.append(df) + return ps + +def do_all(pattern, func, *keys, include_env=False, **kwargs): + for config_file, df, config in read_data(pattern, keys=keys): + p = func(df, *keys, **kwargs) + p.plot(title=config['name']) + yield config_file, p, config + + +def group_trials(trials, aggfunc=['mean', 'min', 'max', 'std']): + trials = list(trials) + trials = list(map(lambda x: x[1] if isinstance(x, tuple) else x, trials)) + return pd.concat(trials).groupby(level=0).agg(aggfunc).reorder_levels([2, 0,1] ,axis=1) + + + diff --git a/soil/environment.py b/soil/environment.py index 9fb06c4..d7216cb 100644 --- a/soil/environment.py +++ b/soil/environment.py @@ -41,17 +41,20 @@ class SoilEnvironment(nxsim.NetworkEnvironment): # executed before network agents self['SEED'] = seed or time.time() random.seed(self['SEED']) + self.process(self.save_state()) self.environment_agents = environment_agents or [] self.network_agents = network_agents or [] - self.process(self.save_state()) if self.dump: - self._db_path = os.path.join(self.get_path(), 'db.sqlite') + self._db_path = os.path.join(self.get_path(), '{}.db.sqlite'.format(self.name)) else: self._db_path = ":memory:" self.create_db(self._db_path) def create_db(self, db_path=None): db_path = db_path or self._db_path + if os.path.exists(db_path): + newname = db_path.replace('db.sqlite', 'backup{}.sqlite'.format(time.time())) + os.rename(db_path, newname) self._db = sqlite3.connect(db_path) with self._db: self._db.execute('''CREATE TABLE IF NOT EXISTS history (agent_id text, t_step int, key text, value text, value_type text)''') @@ -118,24 +121,25 @@ class SoilEnvironment(nxsim.NetworkEnvironment): return self.G.add_edge(agent1, agent2) def run(self, *args, **kwargs): - self._save_state() super().run(*args, **kwargs) - self._save_state() def _save_state(self, now=None): # for agent in self.agents: # agent.save_state() + utils.logger.debug('Saving state @{}'.format(self.now)) with self._db: self._db.executemany("insert into history(agent_id, t_step, key, value, value_type) values (?, ?, ?, ?, ?)", self.state_to_tuples(now=now)) def save_state(self): + self._save_state() while self.peek() != simpy.core.Infinity: - utils.logger.info('Step: {}'.format(self.now)) + delay = max(self.peek() - self.now, self.interval) + utils.logger.debug('Step: {}'.format(self.now)) ev = self.event() ev._ok = True # Schedule the event with minimum priority so - # that it executes after all agents are done - self.schedule(ev, -1, self.peek()) + # that it executes before all agents + self.schedule(ev, -999, delay) yield ev self._save_state() @@ -215,7 +219,7 @@ class SoilEnvironment(nxsim.NetworkEnvironment): with open(csv_name, 'w') as f: cr = csv.writer(f) - cr.writerow(('agent_id', 'tstep', 'attribute', 'value')) + cr.writerow(('agent_id', 't_step', 'key', 'value', 'value_type')) for i in self.history_to_tuples(): cr.writerow(i) @@ -229,14 +233,16 @@ class SoilEnvironment(nxsim.NetworkEnvironment): if now is None: now = self.now for k, v in self.environment_params.items(): - yield 'env', now, k, v, type(v).__name__ + v, v_t = utils.repr(v) + yield 'env', now, k, v, v_t for agent in self.agents: for k, v in agent.state.items(): - yield agent.id, now, k, v, type(v).__name__ + v, v_t = utils.repr(v) + yield agent.id, now, k, v, v_t def history_to_tuples(self): with self._db: - res = self._db.execute("select agent_id, t_step, key, value from history ").fetchall() + res = self._db.execute("select agent_id, t_step, key, value, value_type from history ").fetchall() yield from res def history_to_graph(self): diff --git a/soil/simulation.py b/soil/simulation.py index 8a9285c..bb345f2 100644 --- a/soil/simulation.py +++ b/soil/simulation.py @@ -67,7 +67,7 @@ class SoilSimulation(NetworkSimulation): self.default_state = default_state or {} self.dir_path = dir_path or os.getcwd() self.interval = interval - self.seed = seed + self.seed = str(seed) or str(time.time()) self.dump = dump self.environment_params = environment_params or {} @@ -168,7 +168,7 @@ class SoilSimulation(NetworkSimulation): env_name = '{}_trial_{}'.format(self.name, trial_id) env = environment.SoilEnvironment(name=env_name, topology=self.topology.copy(), - seed=self.seed, + seed=self.seed+env_name, initial_time=0, dump=self.dump, interval=self.interval, diff --git a/soil/utils.py b/soil/utils.py index 4c5f4fb..0d31ff1 100644 --- a/soil/utils.py +++ b/soil/utils.py @@ -13,7 +13,6 @@ from contextlib import contextmanager logger = logging.getLogger(__name__) logger.setLevel(logging.INFO) -logger.addHandler(logging.StreamHandler()) def load_network(network_params, dir_path=None): @@ -86,6 +85,12 @@ def agent_from_distribution(distribution, value=-1): raise Exception('Distribution for value {} not found in: {}'.format(value, distribution)) +def repr(v): + if isinstance(v, bool): + v = "true" if v else "" + return v, bool.__name__ + return v, type(v).__name__ + def convert(value, type_): import importlib try: diff --git a/tests/test_main.py b/tests/test_main.py index 55d1c9b..94e4033 100644 --- a/tests/test_main.py +++ b/tests/test_main.py @@ -60,7 +60,7 @@ class TestMain(TestCase): 'network_params': { 'path': join(ROOT, 'test.gexf') }, - 'agent_type': 'NetworkAgent', + 'agent_type': 'BaseAgent', 'environment_params': { } } @@ -119,7 +119,7 @@ class TestMain(TestCase): def test_custom_agent(self): """Allow for search of neighbors with a certain state_id""" - class CustomAgent(agents.NetworkAgent): + class CustomAgent(agents.BaseAgent): def step(self): self.state['neighbors'] = self.count_agents(state_id=0, limit_neighbors=True) @@ -208,7 +208,7 @@ class TestMain(TestCase): res = list(env.history_to_tuples()) assert len(res) == len(env.environment_params) - assert ('env', 0, 'test', 'test_value') in res + assert ('env', 0, 'test', 'test_value', 'str') in res env['test'] = 'second_value' env._save_state(now=1)