def iterate_location_choice(
model_settings,
persons_merged, persons, households,
skim_dict, skim_stack,
chunk_size, trace_hh_id, locutor,
trace_label):
"""
iterate run_location_choice updating shadow pricing until convergence criteria satisfied
or max_iterations reached.
(If use_shadow_pricing not enabled, then just iterate once)
Parameters
----------
model_settings : dict
persons_merged : injected table
persons : injected table
skim_dict : skim.SkimDict
skim_stack : skim.SkimStack
chunk_size : int
trace_hh_id : int
locutor : bool
whether this process is the privileged logger of shadow_pricing when multiprocessing
trace_label : str
Returns
-------
adds choice column model_settings['DEST_CHOICE_COLUMN_NAME'] and annotations to persons table
"""
# column containing segment id
chooser_segment_column = model_settings['CHOOSER_SEGMENT_COLUMN_NAME']
# boolean to filter out persons not needing location modeling (e.g. is_worker, is_student)
chooser_filter_column = model_settings['CHOOSER_FILTER_COLUMN_NAME']
persons_merged_df = persons_merged.to_frame()
persons_merged_df = persons_merged_df[persons_merged[chooser_filter_column]]
spc = shadow_pricing.load_shadow_price_calculator(model_settings)
max_iterations = spc.max_iterations
logging.debug("%s max_iterations: %s" % (trace_label, max_iterations))
choices = None
for iteration in range(1, max_iterations + 1):
if spc.use_shadow_pricing and iteration > 1:
spc.update_shadow_prices()
choices = run_location_choice(
persons_merged_df,
skim_dict, skim_stack,
spc,
model_settings,
chunk_size, trace_hh_id,
trace_label=tracing.extend_trace_label(trace_label, 'i%s' % iteration))
choices_df = choices.to_frame('dest_choice')
choices_df['segment_id'] = \
persons_merged_df[chooser_segment_column].reindex(choices_df.index)
spc.set_choices(choices_df)
if locutor:
spc.write_trace_files(iteration)
if spc.use_shadow_pricing and spc.check_fit(iteration):
logging.info("%s converged after iteration %s" % (trace_label, iteration,))
break
# - shadow price table
if locutor:
if spc.use_shadow_pricing and 'SHADOW_PRICE_TABLE' in model_settings:
inject.add_table(model_settings['SHADOW_PRICE_TABLE'], spc.shadow_prices)
if 'MODELED_SIZE_TABLE' in model_settings:
inject.add_table(model_settings['MODELED_SIZE_TABLE'], spc.modeled_size)
dest_choice_column_name = model_settings['DEST_CHOICE_COLUMN_NAME']
tracing.print_summary(dest_choice_column_name, choices, value_counts=True)
persons_df = persons.to_frame()
# We only chose school locations for the subset of persons who go to school
# so we backfill the empty choices with -1 to code as no school location
NO_DEST_TAZ = -1
persons_df[dest_choice_column_name] = \
choices.reindex(persons_df.index).fillna(NO_DEST_TAZ).astype(int)
# - annotate persons table
if 'annotate_persons' in model_settings:
expressions.assign_columns(
df=persons_df,
model_settings=model_settings.get('annotate_persons'),
trace_label=tracing.extend_trace_label(trace_label, 'annotate_persons'))
pipeline.replace_table("persons", persons_df)
if trace_hh_id:
tracing.trace_df(persons_df,
label=trace_label,
warn_if_empty=True)
# - annotate households table
if 'annotate_households' in model_settings:
households_df = households.to_frame()
expressions.assign_columns(
df=households_df,
model_settings=model_settings.get('annotate_households'),
trace_label=tracing.extend_trace_label(trace_label, 'annotate_households'))
pipeline.replace_table("households", households_df)
if trace_hh_id:
tracing.trace_df(households_df,
label=trace_label,
warn_if_empty=True)
return persons_df
def iterate_location_choice(model_settings, persons_merged, persons,
households, network_los, estimator, chunk_size,
trace_hh_id, locutor, trace_label):
"""
iterate run_location_choice updating shadow pricing until convergence criteria satisfied
or max_iterations reached.
(If use_shadow_pricing not enabled, then just iterate once)
Parameters
----------
model_settings : dict
persons_merged : injected table
persons : injected table
network_los : los.Network_LOS
chunk_size : int
trace_hh_id : int
locutor : bool
whether this process is the privileged logger of shadow_pricing when multiprocessing
trace_label : str
Returns
-------
adds choice column model_settings['DEST_CHOICE_COLUMN_NAME']
adds logsum column model_settings['DEST_CHOICE_LOGSUM_COLUMN_NAME']- if provided
adds annotations to persons table
"""
chunk_tag = trace_label
# boolean to filter out persons not needing location modeling (e.g. is_worker, is_student)
chooser_filter_column = model_settings['CHOOSER_FILTER_COLUMN_NAME']
dest_choice_column_name = model_settings['DEST_CHOICE_COLUMN_NAME']
logsum_column_name = model_settings.get('DEST_CHOICE_LOGSUM_COLUMN_NAME')
sample_table_name = model_settings.get('DEST_CHOICE_SAMPLE_TABLE_NAME')
want_sample_table = config.setting(
'want_dest_choice_sample_tables') and sample_table_name is not None
persons_merged_df = persons_merged.to_frame()
persons_merged_df = persons_merged_df[
persons_merged[chooser_filter_column]]
persons_merged_df.sort_index(
inplace=True
) # interaction_sample expects chooser index to be monotonic increasing
# chooser segmentation allows different sets coefficients for e.g. different income_segments or tour_types
chooser_segment_column = model_settings['CHOOSER_SEGMENT_COLUMN_NAME']
assert chooser_segment_column in persons_merged_df, \
f"CHOOSER_SEGMENT_COLUMN '{chooser_segment_column}' not in persons_merged table."
spc = shadow_pricing.load_shadow_price_calculator(model_settings)
max_iterations = spc.max_iterations
assert not (spc.use_shadow_pricing and estimator)
logger.debug("%s max_iterations: %s" % (trace_label, max_iterations))
for iteration in range(1, max_iterations + 1):
if spc.use_shadow_pricing and iteration > 1:
spc.update_shadow_prices()
choices_df, save_sample_df = run_location_choice(
persons_merged_df,
network_los,
shadow_price_calculator=spc,
want_logsums=logsum_column_name is not None,
want_sample_table=want_sample_table,
estimator=estimator,
model_settings=model_settings,
chunk_size=chunk_size,
chunk_tag=chunk_tag,
trace_hh_id=trace_hh_id,
trace_label=tracing.extend_trace_label(trace_label,
'i%s' % iteration))
# choices_df is a pandas DataFrame with columns 'choice' and (optionally) 'logsum'
if choices_df is None:
break
spc.set_choices(
choices=choices_df['choice'],
segment_ids=persons_merged_df[chooser_segment_column].reindex(
choices_df.index))
if locutor:
spc.write_trace_files(iteration)
if spc.use_shadow_pricing and spc.check_fit(iteration):
logging.info("%s converged after iteration %s" % (
trace_label,
iteration,
))
break
# - shadow price table
if locutor:
if spc.use_shadow_pricing and 'SHADOW_PRICE_TABLE' in model_settings:
inject.add_table(model_settings['SHADOW_PRICE_TABLE'],
spc.shadow_prices)
if 'MODELED_SIZE_TABLE' in model_settings:
inject.add_table(model_settings['MODELED_SIZE_TABLE'],
spc.modeled_size)
persons_df = persons.to_frame()
# add the choice values to the dest_choice_column in persons dataframe
# We only chose school locations for the subset of persons who go to school
# so we backfill the empty choices with -1 to code as no school location
# names for location choice and (optional) logsums columns
NO_DEST_ZONE = -1
persons_df[dest_choice_column_name] = \
choices_df['choice'].reindex(persons_df.index).fillna(NO_DEST_ZONE).astype(int)
# add the dest_choice_logsum column to persons dataframe
if logsum_column_name:
persons_df[logsum_column_name] = \
choices_df['logsum'].reindex(persons_df.index).astype('float')
if save_sample_df is not None:
# might be None for tiny samples even if sample_table_name was specified
assert len(save_sample_df.index.get_level_values(0).unique()) == len(
choices_df)
# lest they try to put school and workplace samples into the same table
if pipeline.is_table(sample_table_name):
raise RuntimeError("dest choice sample table %s already exists" %
sample_table_name)
pipeline.extend_table(sample_table_name, save_sample_df)
# - annotate persons table
if 'annotate_persons' in model_settings:
expressions.assign_columns(
df=persons_df,
model_settings=model_settings.get('annotate_persons'),
trace_label=tracing.extend_trace_label(trace_label,
'annotate_persons'))
pipeline.replace_table("persons", persons_df)
if trace_hh_id:
tracing.trace_df(persons_df, label=trace_label, warn_if_empty=True)
# - annotate households table
if 'annotate_households' in model_settings:
households_df = households.to_frame()
expressions.assign_columns(
df=households_df,
model_settings=model_settings.get('annotate_households'),
trace_label=tracing.extend_trace_label(trace_label,
'annotate_households'))
pipeline.replace_table("households", households_df)
if trace_hh_id:
tracing.trace_df(households_df,
label=trace_label,
warn_if_empty=True)
if logsum_column_name:
tracing.print_summary(logsum_column_name,
choices_df['logsum'],
value_counts=True)
return persons_df