def explore(fpath):
_, ext = splitext(fpath)
ftype = 'data' if ext in ('.h5', '.hdf5') else 'simulation'
print("Using {} file: '{}'".format(ftype, fpath))
if ftype == 'data':
globals_def, entities = entities_from_h5(fpath)
simulation = Simulation(globals_def, None, None, None, None,
entities.values(), 'h5', fpath, None)
period, entity_name = None, None
else:
simulation = Simulation.from_yaml(fpath)
# use output as input
simulation.data_source = H5Source(simulation.data_sink.output_path)
period = simulation.start_period + simulation.periods - 1
entity_name = simulation.default_entity
dataset = simulation.load()
data_source = simulation.data_source
data_source.as_fake_output(dataset, simulation.entities_map)
data_sink = simulation.data_sink
entities = simulation.entities_map
if entity_name is None and len(entities) == 1:
entity_name = entities.keys()[0]
if period is None and entity_name is not None:
entity = entities[entity_name]
period = max(entity.output_index.keys())
eval_ctx = EvaluationContext(simulation, entities, dataset['globals'],
period, entity_name)
try:
c = Console(eval_ctx)
c.run()
finally:
data_source.close()
if data_sink is not None:
data_sink.close()
def setUp(self):
data = {'person': {'age': array([20, 10, 35, 55]),
'dead': array([False, True, False, True])}}
self.eval_ctx = EvaluationContext(entity_name='person',
entities_data=data)
self.parse_ctx = {
'person': {'age': Variable('age'), 'dead': Variable('dead')},
'__entity__': 'person'
}
def setUp(self):
entities = {}
hh_link = links.Many2One('household', 'hh_id', 'household')
mother_link = links.Many2One('mother', 'mother_id', 'person')
child_link = links.One2Many('children', 'mother_id', 'person')
persons_link = links.One2Many('persons', 'hh_id', 'person')
dt = np.dtype([('period', int), ('id', int), ('age', int),
('dead', bool), ('mother_id', int), ('hh_id', int)])
# TODO: I can't use an EntityContext with an array containing several periods
# of data
# persons = array([(2000, 0, 53, False, -1, 0),
# (2000, 1, 23, False, 0, 1),
# (2000, 2, 20, False, 0, 2),
# (2000, 3, 43, False, -1, 3),
# (2001, 0, 54, True, -1, 0),
# (2001, 1, 24, False, 0, 1),
# (2001, 2, 21, False, 0, 2),
# (2001, 3, 44, False, -1, 0), # they got married
# (2001, 4, 0, False, 2, 2),
persons = array([(2002, 0, 55, True, -1, 0),
(2002, 1, 25, False, 0, 1),
(2002, 2, 22, False, 0, 2),
(2002, 3, 45, False, -1, 0),
(2002, 4, 1, False, 2, 2)],
dtype=dt)
person = Entity('person',
links={'household': hh_link,
'mother': mother_link,
'children': child_link},
array=persons)
dt = np.dtype([('period', int), ('id', int)])
# households = array([(2000, 0),
# (2000, 1),
# (2000, 2),
# (2000, 3),
#
# (2001, 0),
# (2001, 1),
# (2001, 2),
households = array([(2002, 0),
(2002, 1),
(2002, 2)],
dtype=dt)
household = Entity('household',
links={'persons': persons_link},
array=households)
entities['person'] = person
entities['household'] = household
self.entities = entities
parse_ctx = {'__globals__': {}, '__entities__': entities,
'__entity__': 'person'}
parse_ctx.update((entity.name, entity.all_symbols(parse_ctx))
for entity in entities.itervalues())
self.parse_ctx = parse_ctx
self.eval_ctx = EvaluationContext(entities=entities, period=2002,
entity_name='person')
def run(self, run_console=False):
start_time = time.time()
h5in, h5out, globals_data = timed(self.data_source.run,
self.globals_def,
entity_registry,
self.init_period)
if config.autodump or config.autodiff:
if config.autodump:
fname, _ = config.autodump
mode = 'w'
else: # config.autodiff
fname, _ = config.autodiff
mode = 'r'
fpath = os.path.join(config.output_directory, fname)
h5_autodump = tables.open_file(fpath, mode=mode)
config.autodump_file = h5_autodump
else:
h5_autodump = None
# input_dataset = self.data_source.run(self.globals_def,
# entity_registry)
# output_dataset = self.data_sink.prepare(self.globals_def,
# entity_registry)
# output_dataset.copy(input_dataset, self.init_period - 1)
# for entity in input_dataset:
# indexed_array = buildArrayForPeriod(entity)
# tell numpy we do not want warnings for x/0 and 0/0
np.seterr(divide='ignore', invalid='ignore')
process_time = defaultdict(float)
period_objects = {}
eval_ctx = EvaluationContext(self, self.entities_map, globals_data)
def simulate_period(period_idx, period, periods, processes, entities,
init=False):
period_start_time = time.time()
# set current period
eval_ctx.period = period
if config.log_level in ("procedures", "processes"):
print()
print("period", period,
end=" " if config.log_level == "periods" else "\n")
if init and config.log_level in ("procedures", "processes"):
for entity in entities:
print(" * %s: %d individuals" % (entity.name,
len(entity.array)))
else:
if config.log_level in ("procedures", "processes"):
print("- loading input data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.load_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.load_period_data(period)
for entity in entities:
entity.array_period = period
entity.array['period'] = period
if processes:
# build context for this period:
const_dict = {'period_idx': period_idx + 1,
'periods': periods,
'periodicity': time_period[self.time_scale] * (1 - 2 * (self.retro)),
'longitudinal': self.longitudinal,
'format_date': self.time_scale,
'pension': None,
'__simulation__': self,
'period': period,
'nan': float('nan'),
'__globals__': globals_data}
assert(periods[period_idx + 1] == period)
num_processes = len(processes)
for p_num, process_def in enumerate(processes, start=1):
process, periodicity, start = process_def
if config.log_level in ("procedures", "processes"):
print("- %d/%d" % (p_num, num_processes), process.name,
end=' ')
print("...", end=' ')
# TDOD: change that
if isinstance(periodicity, int):
if period_idx % periodicity == 0:
elapsed, _ = gettime(process.run_guarded, self,
const_dict)
else:
elapsed = 0
print("skipped (periodicity)")
else:
assert periodicity in time_period
periodicity_process = time_period[periodicity]
periodicity_simul = time_period[self.time_scale]
month_idx = period % 100
# first condition, to run a process with start == 12
# each year even if year are yyyy01
# modify start if periodicity_simul is not month
start = int(start / periodicity_simul - 0.01) * periodicity_simul + 1
if (periodicity_process <= periodicity_simul and self.time_scale != 'year0') or (
month_idx % periodicity_process == start % periodicity_process):
const_dict['periodicity'] = periodicity_process * (1 - 2 * (self.retro))
elapsed, _ = gettime(process.run_guarded, self, const_dict)
else:
elapsed = 0
if config.log_level in ("procedures", "processes"):
print("skipped (periodicity)")
process_time[process.name] += elapsed
if config.log_level in ("procedures", "processes"):
if config.show_timings:
print("done (%s elapsed)." % time2str(elapsed))
else:
print("done.")
self.start_console(eval_ctx)
# update longitudinal
person = [x for x in entities if x.name == 'person'][0]
# maybe we have a get_entity or anything more nice than that #TODO: check
id = person.array.columns['id']
for varname in ['sali', 'workstate']:
var = person.array.columns[varname]
if init:
fpath = self.data_source.input_path
input_file = HDFStore(fpath, mode="r")
if 'longitudinal' in input_file.root:
input_longitudinal = input_file.root.longitudinal
if varname in input_longitudinal:
self.longitudinal[varname] = input_file['/longitudinal/' + varname]
if period not in self.longitudinal[varname].columns:
table = DataFrame({'id': id, period: var})
self.longitudinal[varname] = self.longitudinal[varname].merge(
table, on='id', how='outer')
else:
# when one variable is not in the input_file
self.longitudinal[varname] = DataFrame({'id': id, period: var})
else:
# when there is no longitudinal in the dataset
self.longitudinal[varname] = DataFrame({'id': id, period: var})
else:
table = DataFrame({'id': id, period: var})
if period in self.longitudinal[varname]:
import pdb
pdb.set_trace()
self.longitudinal[varname] = self.longitudinal[varname].merge(table, on='id', how='outer')
if config.log_level in ("procedures", "processes"):
print("- storing period data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.store_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.store_period_data(period)
# print " - compressing period data"
# for entity in entities:
# print " *", entity.name, "...",
# for level in range(1, 10, 2):
# print " %d:" % level,
# timed(entity.compress_period_data, level)
period_objects[period] = sum(len(entity.array)
for entity in entities)
period_elapsed_time = time.time() - period_start_time
if config.log_level in ("procedures", "processes"):
print("period %d" % period, end=' ')
print("done", end=' ')
if config.show_timings:
print("(%s elapsed)" % time2str(period_elapsed_time), end="")
if init:
print(".")
else:
main_elapsed_time = time.time() - main_start_time
periods_done = period_idx + 1
remaining_periods = self.periods - periods_done
avg_time = main_elapsed_time / periods_done
# future_time = period_elapsed_time * 0.4 + avg_time * 0.6
remaining_time = avg_time * remaining_periods
print(" - estimated remaining time: %s."
% time2str(remaining_time))
else:
print()
print("""
=====================
starting simulation
=====================""")
try:
assert(self.time_scale in time_period)
month_periodicity = time_period[self.time_scale]
time_direction = 1 - 2 * (self.retro)
time_step = month_periodicity * time_direction
periods = [
self.init_period + int(t / 12) * 100 + t % 12
for t in range(0, (self.periods + 1) * time_step, time_step)
]
if self.time_scale == 'year0':
periods = [self.init_period + t for t in range(0, (self.periods + 1))]
print("simulated period are going to be: ", periods)
init_start_time = time.time()
simulate_period(0, self.init_period, [None, periods[0]], self.init_processes, self.entities, init=True)
time_init = time.time() - init_start_time
main_start_time = time.time()
for period_idx, period in enumerate(periods[1:]):
period_start_time = time.time()
simulate_period(period_idx, period, periods,
self.processes, self.entities)
# if self.legislation:
# if not self.legislation['ex_post']:
#
# elapsed, _ = gettime(liam2of.main,period)
# process_time['liam2of'] += elapsed
# elapsed, _ = gettime(of_on_liam.main,self.legislation['annee'],[period])
# process_time['legislation'] += elapsed
# elapsed, _ = gettime(merge_leg.merge_h5,self.data_source.output_path,
# "C:/Til/output/"+"simul_leg.h5",period)
# process_time['merge_leg'] += elapsed
time_elapsed = time.time() - period_start_time
print("period %d done" % period, end=' ')
if config.show_timings:
print("(%s elapsed)." % time2str(time_elapsed))
else:
print()
total_objects = sum(period_objects[period] for period in periods)
total_time = time.time() - main_start_time
# if self.legislation:
# if self.legislation['ex_post']:
#
# elapsed, _ = gettime(liam2of.main)
# process_time['liam2of'] += elapsed
# elapsed, _ = gettime(of_on_liam.main,self.legislation['annee'])
# process_time['legislation'] += elapsed
# # TODO: faire un programme a part, so far ca ne marche pas pour l'ensemble
# # adapter n'est pas si facile, comme on veut economiser une table,
# # on ne peut pas faire de append directement parce qu on met 2010 apres 2011
# # a un moment dans le calcul
# elapsed, _ = gettime(merge_leg.merge_h5,self.data_source.output_path,
# "C:/Til/output/"+"simul_leg.h5",None)
# process_time['merge_leg'] += elapsed
if self.final_stat:
elapsed, _ = gettime(start, period)
process_time['Stat'] += elapsed
total_time = time.time() - main_start_time
time_year = 0
if len(periods) > 1:
nb_year_approx = periods[-1] / 100 - periods[1] / 100
if nb_year_approx > 0:
time_year = total_time / nb_year_approx
try:
ind_per_sec = str(int(total_objects / total_time))
except ZeroDivisionError:
ind_per_sec = 'inf'
print("""
==========================================
simulation done
==========================================
* %s elapsed
* %d individuals on average
* %s individuals/s/period on average
* %s second for init_process
* %s time/period in average
* %s time/year in average
==========================================
""" % (
time2str(time.time() - start_time),
total_objects / self.periods,
ind_per_sec,
time2str(time_init),
time2str(total_time / self.periods),
time2str(time_year))
)
show_top_processes(process_time, 10)
# if config.debug:
# show_top_expr()
if run_console:
console_ctx = eval_ctx.clone(entity_name=self.default_entity)
c = console.Console(console_ctx)
c.run()
finally:
if h5in is not None:
h5in.close()
h5out.close()
if h5_autodump is not None:
h5_autodump.close()
def run_single(self, run_console=False, run_num=None):
start_time = time.time()
input_dataset = timed(self.data_source.load,
self.globals_def,
self.entities_map)
globals_data = input_dataset.get('globals')
timed(self.data_sink.prepare, self.globals_def, self.entities_map,
input_dataset, self.start_period - 1)
print(" * building arrays for first simulated period")
for ent_name, entity in self.entities_map.iteritems():
print(" -", ent_name, "...", end=' ')
# TODO: this whole process of merging all periods is very
# opinionated and does not allow individuals to die/disappear
# before the simulation starts. We couldn't for example,
# take the output of one of our simulation and
# re-simulate only some years in the middle, because the dead
# would be brought back to life. In conclusion, it should be
# optional.
timed(entity.build_period_array, self.start_period - 1)
print("done.")
if config.autodump or config.autodiff:
if config.autodump:
fname, _ = config.autodump
mode = 'w'
else: # config.autodiff
fname, _ = config.autodiff
mode = 'r'
fpath = os.path.join(config.output_directory, fname)
h5_autodump = tables.open_file(fpath, mode=mode)
config.autodump_file = h5_autodump
else:
h5_autodump = None
# tell numpy we do not want warnings for x/0 and 0/0
np.seterr(divide='ignore', invalid='ignore')
process_time = defaultdict(float)
period_objects = {}
eval_ctx = EvaluationContext(self, self.entities_map, globals_data)
def simulate_period(period_idx, period, processes, entities,
init=False):
period_start_time = time.time()
# set current period
eval_ctx.period = period
if config.log_level in ("functions", "processes"):
print()
print("period", period,
end=" " if config.log_level == "periods" else "\n")
if init and config.log_level in ("functions", "processes"):
for entity in entities:
print(" * %s: %d individuals" % (entity.name,
len(entity.array)))
else:
if config.log_level in ("functions", "processes"):
print("- loading input data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.load_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.load_period_data(period)
for entity in entities:
entity.array_period = period
entity.array['period'] = period
if processes:
num_processes = len(processes)
for p_num, process_def in enumerate(processes, start=1):
process, periodicity = process_def
# set current entity
eval_ctx.entity_name = process.entity.name
if config.log_level in ("functions", "processes"):
print("- %d/%d" % (p_num, num_processes), process.name,
end=' ')
print("...", end=' ')
if period_idx % periodicity == 0:
elapsed, _ = gettime(process.run_guarded, eval_ctx)
else:
elapsed = 0
if config.log_level in ("functions", "processes"):
print("skipped (periodicity)")
process_time[process.name] += elapsed
if config.log_level in ("functions", "processes"):
if config.show_timings:
print("done (%s elapsed)." % time2str(elapsed))
else:
print("done.")
self.start_console(eval_ctx)
if config.log_level in ("functions", "processes"):
print("- storing period data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.store_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.store_period_data(period)
# print " - compressing period data"
# for entity in entities:
# print " *", entity.name, "...",
# for level in range(1, 10, 2):
# print " %d:" % level,
# timed(entity.compress_period_data, level)
period_objects[period] = sum(len(entity.array)
for entity in entities)
period_elapsed_time = time.time() - period_start_time
if config.log_level in ("functions", "processes"):
print("period %d" % period, end=' ')
print("done", end=' ')
if config.show_timings:
print("(%s elapsed)" % time2str(period_elapsed_time), end="")
if init:
print(".")
else:
main_elapsed_time = time.time() - main_start_time
periods_done = period_idx + 1
remaining_periods = self.periods - periods_done
avg_time = main_elapsed_time / periods_done
# future_time = period_elapsed_time * 0.4 + avg_time * 0.6
remaining_time = avg_time * remaining_periods
print(" - estimated remaining time: %s."
% time2str(remaining_time))
else:
print()
print("""
=====================
starting simulation
=====================""")
try:
simulate_period(0, self.start_period - 1, self.init_processes,
self.entities, init=True)
main_start_time = time.time()
periods = range(self.start_period,
self.start_period + self.periods)
for period_idx, period in enumerate(periods):
simulate_period(period_idx, period,
self.processes, self.entities)
total_objects = sum(period_objects[period] for period in periods)
avg_objects = str(total_objects // self.periods) \
if self.periods else 'N/A'
main_elapsed_time = time.time() - main_start_time
ind_per_sec = str(int(total_objects / main_elapsed_time)) \
if main_elapsed_time else 'inf'
print("""
==========================================
simulation done
==========================================
* %s elapsed
* %s individuals on average
* %s individuals/s/period on average
==========================================
""" % (time2str(time.time() - start_time), avg_objects, ind_per_sec))
show_top_processes(process_time, 10)
# if config.debug:
# show_top_expr()
if run_console:
ent_name = self.default_entity
if ent_name is None and len(eval_ctx.entities) == 1:
ent_name = eval_ctx.entities.keys()[0]
# FIXME: fresh_data prevents the old (cloned) EvaluationContext
# to be referenced from each EntityContext, which lead to period
# being fixed to the last period of the simulation. This should
# be fixed in EvaluationContext.copy but the proper fix breaks
# stuff (see the comments there)
console_ctx = eval_ctx.clone(fresh_data=True,
entity_name=ent_name)
c = console.Console(console_ctx)
c.run()
finally:
self.close()
if h5_autodump is not None:
h5_autodump.close()
if self.minimal_output:
output_path = self.data_sink.output_path
dirname = os.path.dirname(output_path)
try:
os.remove(output_path)
os.rmdir(dirname)
except OSError:
print("WARNING: could not delete temporary directory: %r"
% dirname)
def run(self, run_console=False):
start_time = time.time()
h5in, h5out, globals_data = timed(self.data_source.run,
self.globals_def,
self.entities_map,
self.start_period - 1)
if config.autodump or config.autodiff:
if config.autodump:
fname, _ = config.autodump
mode = 'w'
else: # config.autodiff
fname, _ = config.autodiff
mode = 'r'
fpath = os.path.join(config.output_directory, fname)
h5_autodump = tables.open_file(fpath, mode=mode)
config.autodump_file = h5_autodump
else:
h5_autodump = None
# input_dataset = self.data_source.run(self.globals_def,
# entity_registry)
# output_dataset = self.data_sink.prepare(self.globals_def,
# entity_registry)
# output_dataset.copy(input_dataset, self.start_period - 1)
# for entity in input_dataset:
# indexed_array = build_period_array(entity)
# tell numpy we do not want warnings for x/0 and 0/0
np.seterr(divide='ignore', invalid='ignore')
process_time = defaultdict(float)
period_objects = {}
eval_ctx = EvaluationContext(self, self.entities_map, globals_data)
def simulate_period(period_idx, period, processes, entities,
init=False):
period_start_time = time.time()
# set current period
eval_ctx.period = period
if config.log_level in ("procedures", "processes"):
print()
print("period", period,
end=" " if config.log_level == "periods" else "\n")
if init and config.log_level in ("procedures", "processes"):
for entity in entities:
print(" * %s: %d individuals" % (entity.name,
len(entity.array)))
else:
if config.log_level in ("procedures", "processes"):
print("- loading input data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.load_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.load_period_data(period)
for entity in entities:
entity.array_period = period
entity.array['period'] = period
if processes:
num_processes = len(processes)
for p_num, process_def in enumerate(processes, start=1):
process, periodicity = process_def
# set current entity
eval_ctx.entity_name = process.entity.name
if config.log_level in ("procedures", "processes"):
print("- %d/%d" % (p_num, num_processes), process.name,
end=' ')
print("...", end=' ')
if period_idx % periodicity == 0:
elapsed, _ = gettime(process.run_guarded, eval_ctx)
else:
elapsed = 0
if config.log_level in ("procedures", "processes"):
print("skipped (periodicity)")
process_time[process.name] += elapsed
if config.log_level in ("procedures", "processes"):
if config.show_timings:
print("done (%s elapsed)." % time2str(elapsed))
else:
print("done.")
self.start_console(eval_ctx)
if config.log_level in ("procedures", "processes"):
print("- storing period data")
for entity in entities:
print(" *", entity.name, "...", end=' ')
timed(entity.store_period_data, period)
print(" -> %d individuals" % len(entity.array))
else:
for entity in entities:
entity.store_period_data(period)
# print " - compressing period data"
# for entity in entities:
# print " *", entity.name, "...",
# for level in range(1, 10, 2):
# print " %d:" % level,
# timed(entity.compress_period_data, level)
period_objects[period] = sum(len(entity.array)
for entity in entities)
period_elapsed_time = time.time() - period_start_time
if config.log_level in ("procedures", "processes"):
print("period %d" % period, end=' ')
print("done", end=' ')
if config.show_timings:
print("(%s elapsed)" % time2str(period_elapsed_time), end="")
if init:
print(".")
else:
main_elapsed_time = time.time() - main_start_time
periods_done = period_idx + 1
remaining_periods = self.periods - periods_done
avg_time = main_elapsed_time / periods_done
# future_time = period_elapsed_time * 0.4 + avg_time * 0.6
remaining_time = avg_time * remaining_periods
print(" - estimated remaining time: %s."
% time2str(remaining_time))
else:
print()
print("""
=====================
starting simulation
=====================""")
try:
simulate_period(0, self.start_period - 1, self.init_processes,
self.entities, init=True)
main_start_time = time.time()
periods = range(self.start_period,
self.start_period + self.periods)
for period_idx, period in enumerate(periods):
simulate_period(period_idx, period,
self.processes, self.entities)
total_objects = sum(period_objects[period] for period in periods)
total_time = time.time() - main_start_time
try:
ind_per_sec = str(int(total_objects / total_time))
except ZeroDivisionError:
ind_per_sec = 'inf'
print("""
==========================================
simulation done
==========================================
* %s elapsed
* %d individuals on average
* %s individuals/s/period on average
==========================================
""" % (time2str(time.time() - start_time),
total_objects / self.periods,
ind_per_sec))
show_top_processes(process_time, 10)
# if config.debug:
# show_top_expr()
if run_console:
console_ctx = eval_ctx.clone(entity_name=self.default_entity)
c = console.Console(console_ctx)
c.run()
finally:
if h5in is not None:
h5in.close()
h5out.close()
if h5_autodump is not None:
h5_autodump.close()
