From 9bc036d18527388a8bc814573a2d8a110c4897e8 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=2E=20Fernando=20S=C3=A1nchez?= Date: Fri, 26 Apr 2019 19:22:45 +0200 Subject: [PATCH] WIP: exporters --- CHANGELOG.md | 13 +++ examples/complete.yml | 1 + examples/template.yml | 29 ++++++ requirements.txt | 8 +- soil/__init__.py | 7 +- soil/agents/__init__.py | 6 +- soil/analysis.py | 4 +- soil/environment.py | 40 ++++---- soil/exporters.py | 43 +++++++++ soil/history.py | 16 ++-- soil/serialization.py | 199 ++++++++++++++++++++++++++++++++++++++++ soil/simulation.py | 177 +++++++++++++++++++++-------------- soil/utils.py | 140 ---------------------------- soil/web/__init__.py | 6 +- tests/test_examples.py | 45 ++++----- tests/test_main.py | 34 ++++--- 16 files changed, 485 insertions(+), 283 deletions(-) create mode 100644 examples/template.yml create mode 100644 soil/exporters.py create mode 100644 soil/serialization.py diff --git a/CHANGELOG.md b/CHANGELOG.md index 7c317d4..fee5fc6 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -3,6 +3,19 @@ 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). +## [0.14.0] +### Added +* Loading configuration from template definitions in the yaml, in preparation for SALib support. +The definition of the variables and their possible values (i.e., a problem in SALib terms), as well as a sampler function, can be provided. +Soil uses this definition and the template to generate a set of configurations. +* Simulation group names, to link related simulations. For now, they are only used to group all simulations in the same group under the same folder. + +### Changed +* `dir_path` is now the directory for resources (modules, files), and the output dir has been renamed to `outdir` + +## Fixed +* Modules with custom agents/environments failed to load when they were run from outside the directory of the definition file. Modules are now loaded from the directory of the simulation file in addition to the working directory + ## [0.13.8] ### Changed * Moved TerroristNetworkModel to examples diff --git a/examples/complete.yml b/examples/complete.yml index a3f88e1..0bd0383 100644 --- a/examples/complete.yml +++ b/examples/complete.yml @@ -1,5 +1,6 @@ --- name: simple +group: tests dir_path: "/tmp/" num_trials: 3 dry_run: True diff --git a/examples/template.yml b/examples/template.yml new file mode 100644 index 0000000..f1c304c --- /dev/null +++ b/examples/template.yml @@ -0,0 +1,29 @@ +--- +vars: + bounds: + x1: [0, 1] + x2: [1, 2] + fixed: + x3: ["a", "b", "c"] +sampler: "SALib.sample.morris.sample" +samples: 10 +template: | + group: simple + num_trials: 1 + interval: 1 + max_time: 2 + seed: "CompleteSeed!" + dump: false + network_params: + generator: complete_graph + n: 10 + network_agents: + - agent_type: CounterModel + weight: {{ x1 }} + state: + id: 0 + - agent_type: AggregatedCounter + weight: {{ 1 - x1 }} + environment_params: + name: {{ x3 }} + skip_test: true diff --git a/requirements.txt b/requirements.txt index 6797dad..3ae22d3 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,8 +1,10 @@ -nxsim +nxsim>=0.1.2 simpy networkx>=2.0 numpy matplotlib pyyaml -pandas -scipy +pandas>=0.23 +scipy>=1.2 +SALib>=1.3 +Jinja2 diff --git a/soil/__init__.py b/soil/__init__.py index a6ea97d..9b4b0c6 100644 --- a/soil/__init__.py +++ b/soil/__init__.py @@ -15,7 +15,7 @@ from . import agents from .simulation import * from .environment import Environment from .history import History -from . import utils +from . import serialization from . import analysis def main(): @@ -44,6 +44,8 @@ def main(): help='folder to write results to. It defaults to the current directory.') parser.add_argument('--synchronous', action='store_true', help='Run trials serially and synchronously instead of in parallel. Defaults to false.') + parser.add_argument('-e', '--exporter', action='append', + help='Export environment and/or simulations using this exporter') args = parser.parse_args() @@ -64,8 +66,9 @@ def main(): simulation.run_from_config(args.file, dry_run=args.dry_run, dump=dump, + exporters=args.exporter, parallel=(not args.synchronous), - results_dir=args.output) + outdir=args.output) except Exception: if args.pdb: pdb.post_mortem() diff --git a/soil/agents/__init__.py b/soil/agents/__init__.py index 69799f5..fb90548 100644 --- a/soil/agents/__init__.py +++ b/soil/agents/__init__.py @@ -15,7 +15,7 @@ import json from functools import wraps -from .. import utils, history +from .. import serialization, history def as_node(agent): @@ -388,7 +388,7 @@ def serialize_type(agent_type, known_modules=[], **kwargs): if isinstance(agent_type, str): return agent_type known_modules += ['soil.agents'] - return utils.serialize(agent_type, known_modules=known_modules, **kwargs)[1] # Get the name of the class + return serialization.serialize(agent_type, known_modules=known_modules, **kwargs)[1] # Get the name of the class def serialize_distribution(network_agents, known_modules=[]): @@ -409,7 +409,7 @@ def deserialize_type(agent_type, known_modules=[]): if not isinstance(agent_type, str): return agent_type known = known_modules + ['soil.agents', 'soil.agents.custom' ] - agent_type = utils.deserializer(agent_type, known_modules=known) + agent_type = serialization.deserializer(agent_type, known_modules=known) return agent_type diff --git a/soil/analysis.py b/soil/analysis.py index d68f0c4..01d45a8 100644 --- a/soil/analysis.py +++ b/soil/analysis.py @@ -4,7 +4,7 @@ import glob import yaml from os.path import join -from . import utils, history +from . import serialization, history def read_data(*args, group=False, **kwargs): @@ -56,7 +56,7 @@ def read_csv(filename, keys=None, convert_types=False, **kwargs): def convert_row(row): - row['value'] = utils.deserialize(row['value_type'], row['value']) + row['value'] = serialization.deserialize(row['value_type'], row['value']) return row diff --git a/soil/environment.py b/soil/environment.py index e7f092e..7efda1f 100644 --- a/soil/environment.py +++ b/soil/environment.py @@ -14,7 +14,7 @@ from networkx.readwrite import json_graph import networkx as nx import nxsim -from . import utils, agents, analysis, history +from . import serialization, agents, analysis, history # These properties will be copied when pickling/unpickling the environment _CONFIG_PROPS = [ 'name', @@ -22,7 +22,7 @@ _CONFIG_PROPS = [ 'name', 'default_state', 'interval', 'dry_run', - 'dir_path', + 'outdir', ] class Environment(nxsim.NetworkEnvironment): @@ -44,7 +44,7 @@ class Environment(nxsim.NetworkEnvironment): interval=1, seed=None, dry_run=False, - dir_path=None, + outdir=None, topology=None, *args, **kwargs): self.name = name or 'UnnamedEnvironment' @@ -58,11 +58,11 @@ class Environment(nxsim.NetworkEnvironment): self._env_agents = {} self.dry_run = dry_run self.interval = interval - self.dir_path = dir_path or tempfile.mkdtemp('soil-env') + self.outdir = outdir or tempfile.mkdtemp('soil-env') 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, + outdir=self.outdir, backup=True) # Add environment agents first, so their events get # executed before network agents @@ -124,7 +124,7 @@ class Environment(nxsim.NetworkEnvironment): elif agent_distribution: agent_type, state = agents._agent_from_distribution(agent_distribution, agent_id=agent_id) else: - utils.logger.debug('Skipping node {}'.format(agent_id)) + serialization.logger.debug('Skipping node {}'.format(agent_id)) return return self.set_agent(agent_id, agent_type, state) @@ -169,7 +169,7 @@ class Environment(nxsim.NetworkEnvironment): def _save_state(self, now=None): # for agent in self.agents: # agent.save_state() - utils.logger.debug('Saving state @{}'.format(self.now)) + serialization.logger.debug('Saving state @{}'.format(self.now)) self._history.save_records(self.state_to_tuples(now=now)) def save_state(self): @@ -180,7 +180,7 @@ class Environment(nxsim.NetworkEnvironment): self._save_state() while self.peek() != simpy.core.Infinity: delay = max(self.peek() - self.now, self.interval) - utils.logger.debug('Step: {}'.format(self.now)) + serialization.logger.debug('Step: {}'.format(self.now)) ev = self.event() ev._ok = True # Schedule the event with minimum priority so @@ -222,14 +222,14 @@ class Environment(nxsim.NetworkEnvironment): ''' return self[key] if key in self else default - def get_path(self, dir_path=None): - dir_path = dir_path or self.dir_path - if not os.path.exists(dir_path): + def get_path(self, outdir=None): + outdir = outdir or self.outdir + if not os.path.exists(outdir): try: - os.makedirs(dir_path) + os.makedirs(outdir) except FileExistsError: pass - return dir_path + return outdir def get_agent(self, agent_id): return self.G.node[agent_id]['agent'] @@ -239,8 +239,8 @@ class Environment(nxsim.NetworkEnvironment): return list(self.agents) return [self.G.node[i]['agent'] for i in nodes] - def dump_csv(self, dir_path=None): - csv_name = os.path.join(self.get_path(dir_path), + def dump_csv(self, outdir=None): + csv_name = os.path.join(self.get_path(outdir), '{}.environment.csv'.format(self.name)) with open(csv_name, 'w') as f: @@ -249,9 +249,9 @@ class Environment(nxsim.NetworkEnvironment): for i in self.history_to_tuples(): cr.writerow(i) - def dump_gexf(self, dir_path=None): + def dump_gexf(self, outdir=None): G = self.history_to_graph() - graph_path = os.path.join(self.get_path(dir_path), + graph_path = os.path.join(self.get_path(outdir), self.name+".gexf") # Workaround for geometric models # See soil/soil#4 @@ -262,7 +262,7 @@ class Environment(nxsim.NetworkEnvironment): nx.write_gexf(G, graph_path, version="1.2draft") - def dump(self, dir_path=None, formats=None): + def dump(self, outdir=None, formats=None): if not formats: return functions = { @@ -271,7 +271,7 @@ class Environment(nxsim.NetworkEnvironment): } for f in formats: if f in functions: - functions[f](dir_path) + functions[f](outdir) else: raise ValueError('Unknown format: {}'.format(f)) @@ -356,7 +356,7 @@ class Environment(nxsim.NetworkEnvironment): def log_stats(self): stats = self.stats() - utils.logger.info('Environment stats: \n{}'.format(yaml.dump(stats, default_flow_style=False))) + serialization.logger.info('Environment stats: \n{}'.format(yaml.dump(stats, default_flow_style=False))) def __getstate__(self): state = {} diff --git a/soil/exporters.py b/soil/exporters.py new file mode 100644 index 0000000..16bcd86 --- /dev/null +++ b/soil/exporters.py @@ -0,0 +1,43 @@ +from .serialization import deserialize +import os +import time + + +def for_sim(simulation, names, dir_path=None): + exporters = [] + for name in names: + mod = deserialize(name, known_modules=['soil.exporters']) + exporters.append(mod(simulation)) + return exporters + + +class Base: + + def __init__(self, simulation): + self.sim = simulation + + def start(self): + pass + + def end(self): + pass + + def env(self): + pass + + +class Dummy(Base): + + def start(self): + with open(os.path.join(self.sim.outdir, 'dummy')) as f: + f.write('simulation started @ {}'.format(time.time())) + + def env(self, env): + with open(os.path.join(self.sim.outdir, 'dummy-trial-{}'.format(env.name))) as f: + for i in env.history_to_tuples(): + f.write(','.join(i)) + + + def end(self): + with open(os.path.join(self.sim.outdir, 'dummy')) as f: + f.write('simulation ended @ {}'.format(time.time())) diff --git a/soil/history.py b/soil/history.py index 39ecdc1..7be5ad3 100644 --- a/soil/history.py +++ b/soil/history.py @@ -9,7 +9,7 @@ logger = logging.getLogger(__name__) from collections import UserDict, namedtuple -from . import utils +from . import serialization class History: @@ -17,9 +17,9 @@ class History: Store and retrieve values from a sqlite database. """ - def __init__(self, db_path=None, name=None, dir_path=None, backup=False): + def __init__(self, db_path=None, name=None, outdir=None, backup=False): if db_path is None and name: - db_path = os.path.join(dir_path or os.getcwd(), + db_path = os.path.join(outdir or os.getcwd(), '{}.db.sqlite'.format(name)) if db_path: if backup and os.path.exists(db_path): @@ -94,9 +94,9 @@ class History: if key not in self._dtypes: self.read_types() if key not in self._dtypes: - name = utils.name(value) - serializer = utils.serializer(name) - deserializer = utils.deserializer(name) + name = serialization.name(value) + serializer = serialization.serializer(name) + deserializer = serialization.deserializer(name) self._dtypes[key] = (name, serializer, deserializer) with self.db: self.db.execute("replace into value_types (key, value_type) values (?, ?)", (key, name)) @@ -135,8 +135,8 @@ class History: with self.db: res = self.db.execute("select key, value_type from value_types ").fetchall() for k, v in res: - serializer = utils.serializer(v) - deserializer = utils.deserializer(v) + serializer = serialization.serializer(v) + deserializer = serialization.deserializer(v) self._dtypes[k] = (v, serializer, deserializer) def __getitem__(self, key): diff --git a/soil/serialization.py b/soil/serialization.py new file mode 100644 index 0000000..f00cf72 --- /dev/null +++ b/soil/serialization.py @@ -0,0 +1,199 @@ +import os +import logging +import ast +import sys +import yaml +import importlib +from glob import glob +from random import random +from copy import deepcopy +from itertools import product, chain + +from jinja2 import Template + +import networkx as nx + +logger = logging.getLogger('soil') +logger.setLevel(logging.INFO) + + +def load_network(network_params, dir_path=None): + if network_params is None: + return nx.Graph() + path = network_params.get('path', None) + if path: + if dir_path and not os.path.isabs(path): + path = os.path.join(dir_path, path) + extension = os.path.splitext(path)[1][1:] + kwargs = {} + if extension == 'gexf': + kwargs['version'] = '1.2draft' + kwargs['node_type'] = int + try: + method = getattr(nx.readwrite, 'read_' + extension) + except AttributeError: + raise AttributeError('Unknown format') + return method(path, **kwargs) + + net_args = network_params.copy() + 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',]) + + return method(**net_args) + + +def load_file(infile): + with open(infile, 'r') as f: + return list(chain.from_iterable(map(expand_template, load_string(f)))) + +def load_string(string): + yield from yaml.load_all(string) + + +def expand_template(config): + if 'template' not in config: + yield config + return + if 'vars' not in config: + raise ValueError(('You must provide a definition of variables' + ' for the template.')) + + template = Template(config['template']) + + sampler_name = config.get('sampler', 'SALib.sample.morris.sample') + n_samples = int(config.get('samples', 100)) + sampler = deserializer(sampler_name) + bounds = config['vars']['bounds'] + + problem = { + 'num_vars': len(bounds), + 'names': list(bounds.keys()), + 'bounds': list(v for v in bounds.values()) + } + samples = sampler(problem, n_samples) + + lists = config['vars'].get('lists', {}) + names = list(lists.keys()) + values = list(lists.values()) + combs = list(product(*values)) + + allnames = names + problem['names'] + allvalues = [(list(i[0])+list(i[1])) for i in product(combs, samples)] + params = list(map(lambda x: dict(zip(allnames, x)), allvalues)) + + + blank_str = template.render({k: 0 for k in allnames}) + blank = list(load_string(blank_str)) + if len(blank) > 1: + raise ValueError('Templates must not return more than one configuration') + + if 'name' in blank[0]: + raise ValueError('Templates cannot be named, use group instead') + + confs = [] + for ps in params: + string = template.render(ps) + for c in load_string(string): + yield c + + +def load_files(*patterns, **kwargs): + for pattern in patterns: + for i in glob(pattern, **kwargs): + for config in load_file(i): + path = os.path.abspath(i) + if 'dir_path' not in config: + config['dir_path'] = os.path.dirname(path) + yield config, path + + +def load_config(config): + if isinstance(config, dict): + yield config, None + else: + yield from load_files(config) + + +builtins = importlib.import_module('builtins') + +def name(value, known_modules=[]): + '''Return a name that can be imported, to serialize/deserialize an object''' + if value is None: + return 'None' + if not isinstance(value, type): # Get the class name first + value = type(value) + tname = value.__name__ + if hasattr(builtins, tname): + return tname + modname = value.__module__ + if modname == '__main__': + return tname + if known_modules and modname in known_modules: + return tname + for kmod in known_modules: + if not kmod: + continue + module = importlib.import_module(kmod) + if hasattr(module, tname): + return tname + return '{}.{}'.format(modname, tname) + + +def serializer(type_): + if type_ != 'str' and hasattr(builtins, type_): + return repr + return lambda x: x + + +def serialize(v, known_modules=[]): + '''Get a text representation of an object.''' + tname = name(v, known_modules=known_modules) + func = serializer(tname) + 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': + return lambda x=None: None + if hasattr(builtins, type_): # Check if it's a builtin type + cls = getattr(builtins, type_) + return lambda x=None: ast.literal_eval(x) if x is not None else cls() + # Otherwise, see if we can find the module and the class + modules = known_modules or [] + options = [] + + for mod in modules: + if mod: + options.append((mod, type_)) + + if '.' in type_: # Fully qualified module + module, type_ = type_.rsplit(".", 1) + options.append ((module, type_)) + + errors = [] + for modname, tname in options: + try: + module = importlib.import_module(modname) + cls = getattr(module, tname) + return getattr(cls, 'deserialize', cls) + except (ModuleNotFoundError, AttributeError) as ex: + errors.append((modname, tname, ex)) + raise Exception('Could not find type {}. Tried: {}'.format(type_, errors)) + + +def deserialize(type_, value=None, **kwargs): + '''Get an object from a text representation''' + if not isinstance(type_, str): + return type_ + des = deserializer(type_, **kwargs) + if value is None: + return des + return des(value) diff --git a/soil/simulation.py b/soil/simulation.py index dc487d3..a008e74 100644 --- a/soil/simulation.py +++ b/soil/simulation.py @@ -13,9 +13,10 @@ import pickle from nxsim import NetworkSimulation -from . import utils, basestring, agents +from . import serialization, utils, basestring, agents from .environment import Environment -from .utils import logger +from .serialization import logger +from .exporters import for_sim as exporters_for_sim class Simulation(NetworkSimulation): @@ -50,6 +51,8 @@ class Simulation(NetworkSimulation): --------- name : str, optional name of the Simulation + group : str, optional + a group name can be used to link simulations topology : networkx.Graph instance, optional network_params : dict parameters used to create a topology with networkx, if no topology is given @@ -60,8 +63,10 @@ class Simulation(NetworkSimulation): states : list, optional List of initial states corresponding to the nodes in the topology. Basic form is a list of integers whose value indicates the state - dir_path : str, optional - Directory path where to save pickled objects + dir_path: str, optional + Directory path to load simulation assets (files, modules...) + outdir : str, optional + Directory path to save simulation results seed : str, optional Seed to use for the random generator num_trials : int, optional @@ -80,38 +85,45 @@ class Simulation(NetworkSimulation): """ - def __init__(self, name=None, topology=None, network_params=None, + def __init__(self, name=None, group=None, topology=None, network_params=None, network_agents=None, agent_type=None, states=None, default_state=None, interval=1, dump=None, dry_run=False, - dir_path=None, num_trials=1, max_time=100, - load_module=None, seed=None, + outdir=None, num_trials=1, max_time=100, + load_module=None, seed=None, dir_path=None, environment_agents=None, environment_params=None, environment_class=None, **kwargs): self.seed = str(seed) or str(time.time()) self.load_module = load_module self.network_params = network_params - self.name = name or 'UnnamedSimulation' + self.name = name or 'Unnamed_' + time.strftime("%Y-%m-%d_%H:%M:%S") + self.group = group or None self.num_trials = num_trials self.max_time = max_time self.default_state = default_state or {} + if not outdir: + outdir = os.path.join(os.getcwd(), + 'soil_output') + self.outdir = os.path.join(outdir, + self.group or '', + self.name) self.dir_path = dir_path or os.getcwd() self.interval = interval self.dump = dump self.dry_run = dry_run - sys.path += [self.dir_path, os.getcwd()] + sys.path += list(x for x in [self.outdir, os.getcwd(), self.dir_path] if x not in sys.path) if topology is None: - topology = utils.load_network(network_params, - dir_path=self.dir_path) + topology = serialization.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, + self.environment_class = serialization.deserialize(environment_class, known_modules=['soil.environment', ]) or Environment environment_agents = environment_agents or [] @@ -130,34 +142,51 @@ class Simulation(NetworkSimulation): return self.run(*args, **kwargs) def run(self, *args, **kwargs): - return list(self.run_simulation_gen(*args, **kwargs)) - - def run_simulation_gen(self, *args, parallel=False, dry_run=False, - **kwargs): - p = Pool() + return list(self._run_simulation_gen(*args, **kwargs)) + + def _run_sync_or_async(self, parallel=False, *args, **kwargs): + if parallel: + p = Pool() + func = partial(self.run_trial_exceptions, + *args, + **kwargs) + for i in p.imap_unordered(func, range(self.num_trials)): + if isinstance(i, Exception): + logger.error('Trial failed:\n\t{}'.format(i.message)) + continue + yield i + else: + for i in range(self.num_trials): + yield self.run_trial(i, + *args, + **kwargs) + + def _run_simulation_gen(self, *args, parallel=False, dry_run=False, + exporters=None, **kwargs): + exporters = exporters_for_sim(self, + exporters or []) with utils.timer('simulation {}'.format(self.name)): - if parallel: - func = partial(self.run_trial_exceptions, dry_run=dry_run or self.dry_run, - return_env=True, - **kwargs) - for i in p.imap_unordered(func, range(self.num_trials)): - if isinstance(i, Exception): - logger.error('Trial failed:\n\t{}'.format(i.message)) - continue - yield i - else: - for i in range(self.num_trials): - yield self.run_trial(i, dry_run = dry_run or self.dry_run, **kwargs) if not (dry_run or self.dry_run): - logger.info('Dumping results to {}'.format(self.dir_path)) - self.dump_pickle(self.dir_path) - self.dump_yaml(self.dir_path) + logger.info('Dumping results to {}'.format(self.outdir)) + self.dump_pickle(self.outdir) + self.dump_yaml(self.outdir) else: logger.info('NOT dumping results') + for exporter in exporters: + exporter.start() + + for env in self._run_sync_or_async(*args, parallel=parallel, + dry_run=dry_run, **kwargs): + for exporter in exporters: + exporter.env(env) + yield env + + for exporter in exporters: + exporter.end() def get_env(self, trial_id = 0, **kwargs): - opts=self.environment_params.copy() - env_name='{}_trial_{}'.format(self.name, trial_id) + opts = self.environment_params.copy() + env_name = '{}_trial_{}'.format(self.name, trial_id) opts.update({ 'name': env_name, 'topology': self.topology.copy(), @@ -169,13 +198,13 @@ class Simulation(NetworkSimulation): 'states': self.states, 'default_state': self.default_state, 'environment_agents': self.environment_agents, - 'dir_path': self.dir_path, + 'outdir': self.outdir, }) opts.update(kwargs) - env=self.environment_class(**opts) + env = self.environment_class(**opts) return env - def run_trial(self, trial_id = 0, until = None, return_env = True, **opts): + def run_trial(self, trial_id=0, until=None, dry_run=False, **opts): """Run a single trial of the simulation Parameters @@ -183,16 +212,16 @@ class Simulation(NetworkSimulation): trial_id : int """ # Set-up trial environment and graph - until=until or self.max_time - env=self.get_env(trial_id = trial_id, **opts) + until = until or self.max_time + env = self.get_env(trial_id = trial_id, **opts) + dry_run = self.dry_run or dry_run # Set up agents on nodes with utils.timer('Simulation {} trial {}'.format(self.name, trial_id)): env.run(until) - if self.dump and not self.dry_run: + if self.dump and not dry_run: with utils.timer('Dumping simulation {} trial {}'.format(self.name, trial_id)): env.dump(formats = self.dump) - if return_env: - return env + return env def run_trial_exceptions(self, *args, **kwargs): ''' A wrapper for run_trial that catches exceptions and returns them. @@ -211,22 +240,22 @@ class Simulation(NetworkSimulation): def to_yaml(self): return yaml.dump(self.to_dict()) - def dump_yaml(self, dir_path = None, file_name = None): - dir_path=dir_path or self.dir_path - if not os.path.exists(dir_path): - os.makedirs(dir_path) + def dump_yaml(self, outdir = None, file_name = None): + outdir = outdir or self.outdir + if not os.path.exists(outdir): + os.makedirs(outdir) if not file_name: - file_name=os.path.join(dir_path, + file_name=os.path.join(outdir, '{}.dumped.yml'.format(self.name)) with open(file_name, 'w') as f: f.write(self.to_yaml()) - def dump_pickle(self, dir_path = None, pickle_name = None): - dir_path=dir_path or self.dir_path - if not os.path.exists(dir_path): - os.makedirs(dir_path) + def dump_pickle(self, outdir = None, pickle_name = None): + outdir = outdir or self.outdir + if not os.path.exists(outdir): + os.makedirs(outdir) if not pickle_name: - pickle_name=os.path.join(dir_path, + pickle_name=os.path.join(outdir, '{}.simulation.pickle'.format(self.name)) with open(pickle_name, 'wb') as f: pickle.dump(self, f) @@ -235,14 +264,14 @@ class Simulation(NetworkSimulation): state={} for k, v in self.__dict__.items(): if k[0] != '_': - state[k]=v - state['topology']=json_graph.node_link_data(self.topology) - state['network_agents']=agents.serialize_distribution(self.network_agents, - known_modules = []) - state['environment_agents']=agents.serialize_distribution(self.environment_agents, - known_modules = []) - state['environment_class']=utils.serialize(self.environment_class, - known_modules=['soil.environment'])[1] # func, name + state[k] = v + state['topology'] = json_graph.node_link_data(self.topology) + state['network_agents'] = agents.serialize_distribution(self.network_agents, + known_modules = []) + state['environment_agents'] = agents.serialize_distribution(self.environment_agents, + known_modules = []) + state['environment_class'] = serialization.serialize(self.environment_class, + known_modules=['soil.environment'])[1] # func, name if state['load_module'] is None: del state['load_module'] return state @@ -250,19 +279,28 @@ class Simulation(NetworkSimulation): def __setstate__(self, state): self.__dict__ = state self.load_module = getattr(self, 'load_module', None) + if self.outdir not in sys.path: + sys.path += [self.outdir, os.getcwd()] if self.dir_path not in sys.path: sys.path += [self.dir_path, os.getcwd()] self.topology = json_graph.node_link_graph(state['topology']) self.network_agents = agents.calculate_distribution(agents._convert_agent_types(self.network_agents)) self.environment_agents = agents._convert_agent_types(self.environment_agents, known_modules=[self.load_module]) - self.environment_class = utils.deserialize(self.environment_class, + self.environment_class = serialization.deserialize(self.environment_class, known_modules=[self.load_module, 'soil.environment', ]) # func, name return state -def from_config(config): - config = list(utils.load_config(config)) +def all_from_config(config): + configs = list(serialization.load_config(config)) + for config, _ in configs: + sim = Simulation(**config) + yield sim + + +def from_config(conf_or_path): + config = list(serialization.load_config(conf_or_path)) if len(config) > 1: raise AttributeError('Provide only one configuration') config = config[0][0] @@ -270,10 +308,10 @@ def from_config(config): return sim -def run_from_config(*configs, results_dir='soil_output', dump=None, timestamp=False, **kwargs): +def run_from_config(*configs, outdir=None, dump=None, timestamp=False, **kwargs): for config_def in configs: # logger.info("Found {} config(s)".format(len(ls))) - for config, _ in utils.load_config(config_def): + for config, path in serialization.load_config(config_def): name = config.get('name', 'unnamed') logger.info("Using config(s): {name}".format(name=name)) @@ -282,9 +320,12 @@ def run_from_config(*configs, results_dir='soil_output', dump=None, timestamp=Fa time.strftime("%Y-%m-%d_%H:%M:%S")) else: sim_folder = name - dir_path = os.path.join(results_dir, sim_folder) if dump is not None: config['dump'] = dump - sim = Simulation(dir_path=dir_path, **config) - logger.info('Dumping results to {} : {}'.format(sim.dir_path, sim.dump)) + dir_path = config.pop('dir_path', os.path.dirname(path)) + outdir = config.pop('outdir', outdir) + sim = Simulation(dir_path=dir_path, + outdir=outdir, + **config) + logger.info('Dumping results to {} : {}'.format(sim.outdir, sim.dump)) sim.run_simulation(**kwargs) diff --git a/soil/utils.py b/soil/utils.py index eae9a2f..a965a93 100644 --- a/soil/utils.py +++ b/soil/utils.py @@ -1,72 +1,12 @@ -import os -import ast -import sys -import yaml import logging -import importlib import time -from glob import glob -from random import random -from copy import deepcopy - -import networkx as nx from contextlib import contextmanager - logger = logging.getLogger('soil') logger.setLevel(logging.INFO) -def load_network(network_params, dir_path=None): - if network_params is None: - return nx.Graph() - path = network_params.get('path', None) - if path: - if dir_path and not os.path.isabs(path): - path = os.path.join(dir_path, path) - extension = os.path.splitext(path)[1][1:] - kwargs = {} - if extension == 'gexf': - kwargs['version'] = '1.2draft' - kwargs['node_type'] = int - try: - method = getattr(nx.readwrite, 'read_' + extension) - except AttributeError: - raise AttributeError('Unknown format') - return method(path, **kwargs) - - net_args = network_params.copy() - 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',]) - - return method(**net_args) - - -def load_file(infile): - with open(infile, 'r') as f: - return list(yaml.load_all(f)) - - -def load_files(*patterns): - for pattern in patterns: - for i in glob(pattern): - for config in load_file(i): - yield config, os.path.abspath(i) - - -def load_config(config): - if isinstance(config, dict): - yield config, None - else: - yield from load_files(config) - - @contextmanager def timer(name='task', pre="", function=logger.info, to_object=None): start = time.time() @@ -80,83 +20,3 @@ def timer(name='task', pre="", function=logger.info, to_object=None): if to_object: to_object.start = start to_object.end = end - - -builtins = importlib.import_module('builtins') - -def name(value, known_modules=[]): - '''Return a name that can be imported, to serialize/deserialize an object''' - if value is None: - return 'None' - if not isinstance(value, type): # Get the class name first - value = type(value) - tname = value.__name__ - if hasattr(builtins, tname): - return tname - modname = value.__module__ - if modname == '__main__': - return tname - if known_modules and modname in known_modules: - return tname - for kmod in known_modules: - if not kmod: - continue - module = importlib.import_module(kmod) - if hasattr(module, tname): - return tname - return '{}.{}'.format(modname, tname) - - -def serializer(type_): - if type_ != 'str' and hasattr(builtins, type_): - return repr - return lambda x: x - - -def serialize(v, known_modules=[]): - '''Get a text representation of an object.''' - tname = name(v, known_modules=known_modules) - func = serializer(tname) - 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': - return lambda x=None: None - if hasattr(builtins, type_): # Check if it's a builtin type - cls = getattr(builtins, type_) - return lambda x=None: ast.literal_eval(x) if x is not None else cls() - # Otherwise, see if we can find the module and the class - modules = known_modules or [] - options = [] - - for mod in modules: - if mod: - options.append((mod, type_)) - - if '.' in type_: # Fully qualified module - module, type_ = type_.rsplit(".", 1) - options.append ((module, type_)) - - errors = [] - for modname, tname in options: - try: - module = importlib.import_module(modname) - cls = getattr(module, tname) - return getattr(cls, 'deserialize', cls) - except (ModuleNotFoundError, AttributeError) as ex: - errors.append((modname, tname, ex)) - raise Exception('Could not find type {}. Tried: {}'.format(type_, errors)) - - -def deserialize(type_, value=None, **kwargs): - '''Get an object from a text representation''' - if not isinstance(type_, str): - return type_ - des = deserializer(type_, **kwargs) - if value is None: - return des - return des(value) diff --git a/soil/web/__init__.py b/soil/web/__init__.py index 3db60bc..4586238 100644 --- a/soil/web/__init__.py +++ b/soil/web/__init__.py @@ -180,7 +180,7 @@ class SocketHandler(tornado.websocket.WebSocketHandler): with self.logging(self.simulation_name): try: config = dict(**self.config) - config['dir_path'] = os.path.join(self.application.dir_path, config['name']) + config['outdir'] = os.path.join(self.application.outdir, config['name']) config['dump'] = self.application.dump self.trials = yield self.nonblocking(config) @@ -232,12 +232,12 @@ class ModularServer(tornado.web.Application): settings = {'debug': True, 'template_path': ROOT + '/templates'} - def __init__(self, dump=False, dir_path='output', name='SOIL', verbose=True, *args, **kwargs): + def __init__(self, dump=False, outdir='output', name='SOIL', verbose=True, *args, **kwargs): self.verbose = verbose self.name = name self.dump = dump - self.dir_path = dir_path + self.outdir = outdir # Initializing the application itself: super().__init__(self.handlers, **self.settings) diff --git a/tests/test_examples.py b/tests/test_examples.py index 2936808..7e4b994 100644 --- a/tests/test_examples.py +++ b/tests/test_examples.py @@ -2,7 +2,7 @@ from unittest import TestCase import os from os.path import join -from soil import utils, simulation +from soil import serialization, simulation ROOT = os.path.abspath(os.path.dirname(__file__)) EXAMPLES = join(ROOT, '..', 'examples') @@ -17,31 +17,32 @@ class TestExamples(TestCase): def make_example_test(path, config): def wrapped(self): root = os.getcwd() - os.chdir(os.path.dirname(path)) - s = simulation.from_config(config) - iterations = s.max_time * s.num_trials - if iterations > 1000: - s.max_time = 100 - s.num_trials = 1 - if config.get('skip_test', False) and not FORCE_TESTS: - self.skipTest('Example ignored.') - envs = s.run_simulation(dry_run=True) - assert envs - for env in envs: - assert env - try: - n = config['network_params']['n'] - assert len(list(env.network_agents)) == n - assert env.now > 2 # It has run - assert env.now <= config['max_time'] # But not further than allowed - except KeyError: - pass - os.chdir(root) + for s in simulation.all_from_config(path): + iterations = s.max_time * s.num_trials + if iterations > 1000: + s.max_time = 100 + s.num_trials = 1 + if config.get('skip_test', False) and not FORCE_TESTS: + self.skipTest('Example ignored.') + envs = s.run_simulation(dry_run=True) + assert envs + for env in envs: + assert env + try: + n = config['network_params']['n'] + assert len(list(env.network_agents)) == n + assert env.now > 2 # It has run + assert env.now <= config['max_time'] # But not further than allowed + except KeyError: + pass return wrapped def add_example_tests(): - for config, path in utils.load_config(join(EXAMPLES, '**', '*.yml')): + for config, path in serialization.load_files( + join(EXAMPLES, '*', '*.yml'), + join(EXAMPLES, '*.yml'), + ): p = make_example_test(path=path, config=config) fname = os.path.basename(path) p.__name__ = 'test_example_file_%s' % fname diff --git a/tests/test_main.py b/tests/test_main.py index 8e8ee71..44a8150 100644 --- a/tests/test_main.py +++ b/tests/test_main.py @@ -7,7 +7,8 @@ import networkx as nx from functools import partial from os.path import join -from soil import simulation, Environment, agents, utils, history +from soil import (simulation, Environment, agents, serialization, + history, utils) ROOT = os.path.abspath(os.path.dirname(__file__)) @@ -32,7 +33,7 @@ class TestMain(TestCase): 'path': join(ROOT, 'test.gexf') } } - G = utils.load_network(config['network_params']) + G = serialization.load_network(config['network_params']) assert G assert len(G) == 2 with self.assertRaises(AttributeError): @@ -42,7 +43,7 @@ class TestMain(TestCase): 'path': join(ROOT, 'unknown.extension') } } - G = utils.load_network(config['network_params']) + G = serialization.load_network(config['network_params']) print(G) def test_generate_barabasi(self): @@ -57,10 +58,10 @@ class TestMain(TestCase): } } with self.assertRaises(TypeError): - G = utils.load_network(config['network_params']) + G = serialization.load_network(config['network_params']) config['network_params']['n'] = 100 config['network_params']['m'] = 10 - G = utils.load_network(config['network_params']) + G = serialization.load_network(config['network_params']) assert len(G) == 100 def test_empty_simulation(self): @@ -153,7 +154,7 @@ class TestMain(TestCase): def test_torvalds_example(self): """A complete example from a documentation should work.""" - config = utils.load_file(join(EXAMPLES, 'torvalds.yml'))[0] + config = serialization.load_file(join(EXAMPLES, 'torvalds.yml'))[0] config['network_params']['path'] = join(EXAMPLES, config['network_params']['path']) s = simulation.from_config(config) @@ -180,7 +181,7 @@ class TestMain(TestCase): should be equivalent to the configuration file used """ with utils.timer('loading'): - config = utils.load_file(join(EXAMPLES, 'complete.yml'))[0] + config = serialization.load_file(join(EXAMPLES, 'complete.yml'))[0] s = simulation.from_config(config) s.dry_run = True with utils.timer('serializing'): @@ -189,6 +190,7 @@ class TestMain(TestCase): recovered = yaml.load(serial) with utils.timer('deleting'): del recovered['topology'] + del recovered['outdir'] assert config == recovered def test_configuration_changes(self): @@ -196,13 +198,14 @@ class TestMain(TestCase): The configuration should not change after running the simulation. """ - config = utils.load_file(join(EXAMPLES, 'complete.yml'))[0] + config = serialization.load_file(join(EXAMPLES, 'complete.yml'))[0] s = simulation.from_config(config) s.dry_run = True for i in range(5): s.run_simulation(dry_run=True) nconfig = s.to_dict() del nconfig['topology'] + del nconfig['outdir'] assert config == nconfig def test_row_conversion(self): @@ -245,11 +248,11 @@ class TestMain(TestCase): assert ('finish', 10, None) in values def test_serialize_class(self): - ser, name = utils.serialize(agents.BaseAgent) + ser, name = serialization.serialize(agents.BaseAgent) assert name == 'soil.agents.BaseAgent' assert ser == agents.BaseAgent - ser, name = utils.serialize(CustomAgent) + ser, name = serialization.serialize(CustomAgent) assert name == 'test_main.CustomAgent' assert ser == CustomAgent pickle.dumps(ser) @@ -257,9 +260,9 @@ class TestMain(TestCase): def test_serialize_builtin_types(self): for i in [1, None, True, False, {}, [], list(), dict()]: - ser, name = utils.serialize(i) + ser, name = serialization.serialize(i) assert type(ser) == str - des = utils.deserialize(name, ser) + des = serialization.deserialize(name, ser) assert i == des def test_serialize_agent_type(self): @@ -336,3 +339,10 @@ class TestMain(TestCase): assert len(a3.subgraph(limit_neighbors=True)) == 1 assert len(a3.subgraph(limit_neighbors=True, center=False)) == 0 assert len(a3.subgraph(agent_type=agents.NetworkAgent)) == 3 + + def test_templates(self): + '''Loading a template should result in several configs''' + configs = serialization.load_file(join(EXAMPLES, 'template.yml')) + assert len(configs) > 0 + +