fix timeout in FSM. Improve logs

.gitlab-ci.yml

@@ -1,6 +1,6 @@
 stages:
-  - build
   - test
+  - build
 
 build:
   stage: build
@@ -11,12 +11,15 @@ build:
     - docker
   script:
     - echo "{\"auths\":{\"$CI_REGISTRY\":{\"username\":\"$CI_REGISTRY_USER\",\"password\":\"$CI_REGISTRY_PASSWORD\"}}}" > /kaniko/.docker/config.json
-    - /kaniko/executor --context $CI_PROJECT_DIR --dockerfile $CI_PROJECT_DIR/Dockerfile --destination $CI_REGISTRY_IMAGE:$CI_COMMIT_TAG
+    # The skip-tls-verify flag is there because our registry certificate is self signed
+    - /kaniko/executor --context $CI_PROJECT_DIR --skip-tls-verify --dockerfile $CI_PROJECT_DIR/Dockerfile --destination $CI_REGISTRY_IMAGE:$CI_COMMIT_TAG
   only:
     - tags
 
 
 test:
+  except:
+    - tags  # Avoid running tests for tags, because they are already run for the branch
   tags:
     - docker
   image: python:3.7

CHANGELOG.md

@@ -0,0 +1,19 @@
+# Changelog
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+### Changed
+### Added
+### Fixed
+
+## [0.13.7]
+### Changed
+* History now defaults to not backing up! This makes it more intuitive to load the history for examination, at the expense of rewriting something. That should not happen because History is only created in the Environment, and that has `backup=True`.
+### Added
+* Agent names are assigned based on their agent types
+* Agent logging uses the agent name.
+* FSM agents can now return a timeout in addition to a new state. e.g. `return self.idle, self.env.timeout(2)` will execute the *different_state* in 2 *units of time* (`t_step=now+2`).
+* Example of using timeouts in FSM (custom_timeouts)
+* `network_agents` entries may include an `ids` entry. If set, it should be a list of node ids that should be assigned that agent type. This complements the previous behavior of setting agent type with `weights`.

docs/soil_tutorial.rst

@@ -26,7 +26,7 @@ But before that, let's import the soil module and networkx.
     %autoreload 2
     
     %pylab inline
-    # To display plots in the notebooed_
+    # To display plots in the notebook_
 
 
 .. parsed-literal::

examples/custom_generator/custom_generator.yml

@@ -0,0 +1,17 @@
+---
+name: custom-generator
+description: Using a custom generator for the network
+num_trials: 3
+dry_run: True
+max_time: 100
+interval: 1
+network_params:
+  generator: mymodule.mygenerator
+# These are custom parameters
+  n: 10
+  n_edges: 5  
+network_agents:
+  - agent_type: CounterModel
+    weight: 1
+    state:
+      id: 0

examples/custom_generator/mymodule.py

@@ -0,0 +1,27 @@
+from networkx import Graph
+import networkx as nx
+from random import choice
+
+def mygenerator(n=5, n_edges=5):
+    '''
+    Just a simple generator that creates a network with n nodes and
+    n_edges edges. Edges are assigned randomly, only avoiding self loops.
+    '''
+    G = nx.Graph()
+
+    for i in range(n):
+        G.add_node(i)
+    
+    for i in range(n_edges):
+        nodes = list(G.nodes)
+        n_in = choice(nodes)
+        nodes.remove(n_in)  # Avoid loops
+        n_out = choice(nodes)
+        G.add_edge(n_in, n_out)
+    return G
+    
+
+
+
+
+    

examples/custom_timeouts/custom_timeouts.py

@@ -0,0 +1,36 @@
+from soil.agents import FSM, state, default_state
+
+
+class Fibonacci(FSM):
+    '''Agent that only executes in t_steps that are Fibonacci numbers'''
+
+    defaults = {
+        'prev': 1
+    }
+
+    @default_state
+    @state
+    def counting(self):
+        self.log('Stopping at {}'.format(self.now))
+        prev, self['prev'] = self['prev'], max([self.now, self['prev']])
+        return None, self.env.timeout(prev)
+
+class Odds(FSM):
+    '''Agent that only executes in odd t_steps'''
+    @default_state
+    @state
+    def odds(self):
+        self.log('Stopping at {}'.format(self.now))
+        return None, self.env.timeout(1+self.now%2)
+
+if __name__ == '__main__':
+    import logging
+    logging.basicConfig(level=logging.INFO)
+    from soil import Simulation
+    s = Simulation(network_agents=[{'ids': [0], 'agent_type': Fibonacci},
+                                   {'ids': [1], 'agent_type': Odds}],
+                   dry_run=True,
+                   network_params={"generator": "complete_graph", "n": 2},
+                   max_time=100,
+                   )
+    s.run()

examples/programmatic/.gitignore

@@ -0,0 +1 @@
+Programmatic*

examples/programmatic/programmatic.py

@@ -0,0 +1,38 @@
+'''
+Example of a fully programmatic simulation, without definition files.
+'''
+from soil import Simulation, agents
+from networkx import Graph
+import logging
+
+
+def mygenerator():
+    # Add only a node
+    G = Graph()
+    G.add_node(1)
+    return G
+
+
+class MyAgent(agents.FSM):
+
+    @agents.default_state
+    @agents.state
+    def neutral(self):
+        self.info('I am running')
+
+
+s = Simulation(name='Programmatic',
+               network_params={'generator': mygenerator},
+               num_trials=1,
+               max_time=100,
+               agent_type=MyAgent,
+               dry_run=True)
+
+
+logging.basicConfig(level=logging.INFO)
+envs = s.run()
+
+s.dump_yaml()
+
+for env in envs:
+    env.dump_csv()

soil/VERSION

@@ -1 +1 @@
-0.13.4
+0.13.7

soil/__init__.py

@@ -14,6 +14,7 @@ except NameError:
 from . import agents
 from .simulation import *
 from .environment import Environment
+from .history import History
 from . import utils
 from . import analysis
 

soil/agents/__init__.py

@@ -25,13 +25,13 @@ class BaseAgent(nxsim.BaseAgent):
     defaults = {}
 
     def __init__(self, environment, agent_id, state=None,
-                 name='network_process', interval=None, **state_params):
+                 name=None, interval=None, **state_params):
         # Check for REQUIRED arguments
         assert environment is not None, TypeError('__init__ missing 1 required keyword argument: \'environment\'. '
                                                   'Cannot be NoneType.')
         # Initialize agent parameters
         self.id = agent_id
-        self.name = name
+        self.name = name or '{}[{}]'.format(type(self).__name__, self.id)
         self.state_params = state_params
 
         # Register agent to environment
@@ -46,7 +46,7 @@ class BaseAgent(nxsim.BaseAgent):
 
         if not hasattr(self, 'level'):
             self.level = logging.DEBUG
-        self.logger = logging.getLogger('{}-Agent-{}'.format(self.env.name,
+        self.logger = logging.getLogger('{}.{}'.format(self.env.name,
                                                        self.id))
         self.logger.setLevel(self.level)
 
@@ -174,7 +174,7 @@ class BaseAgent(nxsim.BaseAgent):
 
     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)
+        message = "\t{:10}@{:>5}:\t{}".format(self.name, self.now, message)
         for k, v in kwargs:
             message += " {k}={v} ".format(k, v)
         extra = {}
@@ -280,7 +280,7 @@ class FSM(BaseAgent, metaclass=MetaFSM):
             raise Exception('{} has no valid state id or default state'.format(self))
         if next_state not in self.states:
             raise Exception('{} is not a valid id for {}'.format(next_state, self))
-        self.states[next_state](self)
+        return self.states[next_state](self)
 
     def set_state(self, state):
         if hasattr(state, 'id'):
@@ -306,6 +306,9 @@ def prob(prob=1):
     return r < prob
 
 
+STATIC_THRESHOLD = (-1, -1)
+
+
 def calculate_distribution(network_agents=None,
                            agent_type=None):
     '''
@@ -343,6 +346,9 @@ def calculate_distribution(network_agents=None,
     total = sum(x.get('weight', 1) for x in network_agents)
     acc = 0
     for v in network_agents:
+        if 'ids' in v:
+            v['threshold'] = STATIC_THRESHOLD
+            continue
         upper = acc + (v.get('weight', 1)/total)
         v['threshold'] = [acc, upper]
         acc = upper
@@ -403,13 +409,16 @@ def _convert_agent_types(ind, to_string=False, **kwargs):
     return deserialize_distribution(ind, **kwargs)
 
 
-def _agent_from_distribution(distribution, value=-1):
+def _agent_from_distribution(distribution, value=-1, agent_id=None):
     """Used in the initialization of agents given an agent distribution."""
     if value < 0:
         value = random.random()
-    for d in distribution:
+    for d in sorted(distribution, key=lambda x: x['threshold']):
         threshold = d['threshold']
-        if value >= threshold[0] and value < threshold[1]:
+        # Check if the definition matches by id (first) or by threshold
+        if not ((agent_id is not None and threshold == STATIC_THRESHOLD and agent_id in d['ids']) or \
+                (value >= threshold[0] and value < threshold[1])):
+            continue
         state = {}
         if 'state' in d:
             state = deepcopy(d['state'])

soil/environment.py

@@ -4,9 +4,11 @@ import time
 import csv
 import random
 import simpy
+import yaml
 import tempfile
 import pandas as pd
 from copy import deepcopy
+from collections import Counter
 from networkx.readwrite import json_graph
 
 import networkx as nx
@@ -60,7 +62,8 @@ class Environment(nxsim.NetworkEnvironment):
         if not dry_run:
             self.get_path()
         self._history = history.History(name=self.name if not dry_run else None,
-                                        dir_path=self.dir_path)
+                                        dir_path=self.dir_path,
+                                        backup=True)
         # Add environment agents first, so their events get
         # executed before network agents
         self.environment_agents = environment_agents or []
@@ -111,7 +114,7 @@ class Environment(nxsim.NetworkEnvironment):
 
         agent_type = None
         if 'agent_type' in self.states.get(agent_id, {}):
-            agent_type = self.states[agent_id]
+            agent_type = self.states[agent_id]['agent_type']
         elif 'agent_type' in node:
             agent_type = node['agent_type']
         elif 'agent_type' in self.default_state:
@@ -119,8 +122,8 @@ class Environment(nxsim.NetworkEnvironment):
 
         if agent_type:
             agent_type = agents.deserialize_type(agent_type)
-        else:
+        elif agent_distribution:
-            agent_type, state = agents._agent_from_distribution(agent_distribution)
+            agent_type, state = agents._agent_from_distribution(agent_distribution, agent_id=agent_id)
         return self.set_agent(agent_id, agent_type, state)
 
     def set_agent(self, agent_id, agent_type, state=None):
@@ -130,6 +133,8 @@ class Environment(nxsim.NetworkEnvironment):
         defstate.update(node.get('state', {}))
         if state:
             defstate.update(state)
+        a = None
+        if agent_type:
             state = defstate
             a = agent_type(environment=self,
                            agent_id=agent_id,
@@ -153,8 +158,10 @@ class Environment(nxsim.NetworkEnvironment):
 
     def run(self, *args, **kwargs):
         self._save_state()
+        self.log_stats()
         super().run(*args, **kwargs)
         self._history.flush_cache()
+        self.log_stats()
 
     def _save_state(self, now=None):
         # for agent in self.agents:
@@ -327,6 +334,25 @@ class Environment(nxsim.NetworkEnvironment):
 
         return G
     
+    def stats(self):
+        stats = {}
+        stats['network'] = {}
+        stats['network']['n_nodes'] = self.G.number_of_nodes()
+        stats['network']['n_edges'] = self.G.number_of_edges()
+        c = Counter()
+        c.update(a.__class__.__name__ for a in self.network_agents)
+        stats['agents'] = {}
+        stats['agents']['model_count'] = dict(c)
+        c2 = Counter()
+        c2.update(a['id'] for a in self.network_agents)
+        stats['agents']['state_count'] = dict(c2)
+        stats['params'] = self.environment_params
+        return stats
+
+    def log_stats(self):
+        stats = self.stats()
+        utils.logger.info('Environment stats: \n{}'.format(yaml.dump(stats, default_flow_style=False)))
+    
     def __getstate__(self):
         state = {}
         for prop in _CONFIG_PROPS:

soil/history.py

@@ -3,6 +3,10 @@ import os
 import pandas as pd
 import sqlite3
 import copy
+import logging
+
+logger = logging.getLogger(__name__)
+
 from collections import UserDict, namedtuple
 
 from . import utils
@@ -13,7 +17,7 @@ class History:
     Store and retrieve values from a sqlite database.
     """
 
-    def __init__(self, db_path=None, name=None, dir_path=None, backup=True):
+    def __init__(self, db_path=None, name=None, dir_path=None, backup=False):
         if db_path is None and name:
             db_path = os.path.join(dir_path or os.getcwd(),
                                    '{}.db.sqlite'.format(name))
@@ -28,6 +32,7 @@ class History:
         self.db = db_path
 
         with self.db:
+            logger.debug('Creating database {}'.format(self.db_path))
             self.db.execute('''CREATE TABLE IF NOT EXISTS history (agent_id text, t_step int, key text, value text text)''')
             self.db.execute('''CREATE TABLE IF NOT EXISTS value_types (key text, value_type text)''')
             self.db.execute('''CREATE UNIQUE INDEX IF NOT EXISTS idx_history ON history (agent_id, t_step, key);''')
@@ -46,6 +51,7 @@ class History:
     def db(self, db_path=None):
         db_path = db_path or self.db_path
         if isinstance(db_path, str):
+            logger.debug('Connecting to database {}'.format(db_path))
             self._db = sqlite3.connect(db_path)
         else:
             self._db = db_path
@@ -110,6 +116,7 @@ class History:
         Use a cache to save state changes to avoid opening a session for every change.
         The cache will be flushed at the end of the simulation, and when history is accessed.
         '''
+        logger.debug('Flushing cache {}'.format(self.db_path))
         with self.db:
             for rec in self._tups:
                 self.db.execute("replace into history(agent_id, t_step, key, value) values (?, ?, ?, ?)", (rec.agent_id, rec.t_step, rec.key, rec.value))

soil/simulation.py

@@ -88,14 +88,8 @@ class Simulation(NetworkSimulation):
                  environment_agents=None, environment_params=None,
                  environment_class=None, **kwargs):
 
-        if topology is None:
+        self.seed = str(seed) or str(time.time())
-            topology = utils.load_network(network_params,
-                                          dir_path=dir_path)
-        elif isinstance(topology, basestring) or isinstance(topology, dict):
-            topology = json_graph.node_link_graph(topology)
-
         self.load_module = load_module
-        self.topology = nx.Graph(topology)
         self.network_params = network_params
         self.name = name or 'UnnamedSimulation'
         self.num_trials = num_trials
@@ -103,12 +97,19 @@ class Simulation(NetworkSimulation):
         self.default_state = default_state or {}
         self.dir_path = dir_path or os.getcwd()
         self.interval = interval
-        self.seed = str(seed) or str(time.time())
         self.dump = dump
         self.dry_run = dry_run
 
         sys.path += [self.dir_path, os.getcwd()]
 
+        if topology is None:
+            topology = utils.load_network(network_params,
+                                          dir_path=self.dir_path)
+        elif isinstance(topology, basestring) or isinstance(topology, dict):
+            topology = json_graph.node_link_graph(topology)
+        self.topology = nx.Graph(topology)
+
+
         self.environment_params = environment_params or {}
         self.environment_class = utils.deserialize(environment_class,
                                                    known_modules=['soil.environment', ]) or Environment

soil/utils.py

@@ -1,5 +1,6 @@
 import os
 import ast
+import sys
 import yaml
 import logging
 import importlib
@@ -36,9 +37,14 @@ def load_network(network_params, dir_path=None):
         return method(path, **kwargs)
 
     net_args = network_params.copy()
-    net_type = net_args.pop('generator')
+    net_gen = net_args.pop('generator')
+
+    if dir_path not in sys.path:
+        sys.path.append(dir_path)
+
+    method = deserializer(net_gen,
+                          known_modules=['networkx.generators',])
 
-    method = getattr(nx.generators, net_type)
     return method(**net_args)
 
 
@@ -114,6 +120,8 @@ def serialize(v, known_modules=[]):
     return func(v), tname
 
 def deserializer(type_, known_modules=[]):
+    if type(type_) != str:  # Already deserialized
+        return type_
     if type_ == 'str':
         return lambda x='': x
     if type_ == 'None':

tests/test_history.py

@@ -120,18 +120,18 @@ class TestHistory(TestCase):
         assert os.path.exists(db_path)
 
         # Recover the data
-        recovered = history.History(db_path=db_path, backup=False)
+        recovered = history.History(db_path=db_path)
         assert recovered['a_1', 0, 'id'] == 'v'
         assert recovered['a_1', 4, 'id'] == 'e'
 
-        # Using the same name should create a backup copy
+        # Using backup=True should create a backup copy, and initialize an empty history
         newhistory = history.History(db_path=db_path, backup=True)
         backuppaths = glob(db_path + '.backup*.sqlite')
         assert len(backuppaths) == 1
         backuppath = backuppaths[0]
         assert newhistory.db_path == h.db_path
         assert os.path.exists(backuppath)
-        assert not len(newhistory[None, None, None])
+        assert len(newhistory[None, None, None]) == 0
 
     def test_history_tuples(self):
         """