def mandatory_tour_frequency(persons_merged, chunk_size, trace_hh_id): """ This model predicts the frequency of making mandatory trips (see the alternatives above) - these trips include work and school in some combination. """ trace_label = 'mandatory_tour_frequency' model_settings = config.read_model_settings( 'mandatory_tour_frequency.yaml') model_spec = simulate.read_model_spec( file_name='mandatory_tour_frequency.csv') alternatives = simulate.read_model_alts( config.config_file_path('mandatory_tour_frequency_alternatives.csv'), set_index='alt') choosers = persons_merged.to_frame() # filter based on results of CDAP choosers = choosers[choosers.cdap_activity == 'M'] logger.info("Running mandatory_tour_frequency with %d persons", len(choosers)) # - if no mandatory tours if choosers.shape[0] == 0: add_null_results(trace_label, model_settings) return # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = {} expressions.assign_columns(df=choosers, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) nest_spec = config.get_logit_model_settings(model_settings) constants = config.get_model_constants(model_settings) choices = simulate.simple_simulate( choosers=choosers, spec=model_spec, nest_spec=nest_spec, locals_d=constants, chunk_size=chunk_size, trace_label=trace_label, trace_choice_name='mandatory_tour_frequency') # convert indexes to alternative names choices = pd.Series(model_spec.columns[choices.values], index=choices.index).reindex( persons_merged.local.index) # - create mandatory tours """ This reprocesses the choice of index of the mandatory tour frequency alternatives into an actual dataframe of tours. Ending format is the same as got non_mandatory_tours except trip types are "work" and "school" """ choosers['mandatory_tour_frequency'] = choices mandatory_tours = process_mandatory_tours( persons=choosers, mandatory_tour_frequency_alts=alternatives) tours = pipeline.extend_table("tours", mandatory_tours) tracing.register_traceable_table('tours', mandatory_tours) pipeline.get_rn_generator().add_channel('tours', mandatory_tours) # - annotate persons persons = inject.get_table('persons').to_frame() # need to reindex as we only handled persons with cdap_activity == 'M' persons['mandatory_tour_frequency'] = choices.reindex( persons.index).fillna('').astype(str) expressions.assign_columns( df=persons, model_settings=model_settings.get('annotate_persons'), trace_label=tracing.extend_trace_label(trace_label, 'annotate_persons')) pipeline.replace_table("persons", persons) tracing.print_summary('mandatory_tour_frequency', persons.mandatory_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df(mandatory_tours, label="mandatory_tour_frequency.mandatory_tours", warn_if_empty=True) tracing.trace_df(persons, label="mandatory_tour_frequency.persons", warn_if_empty=True)
def non_mandatory_tour_frequency(persons, persons_merged, chunk_size, trace_hh_id): """ This model predicts the frequency of making non-mandatory trips (alternatives for this model come from a separate csv file which is configured by the user) - these trips include escort, shopping, othmaint, othdiscr, eatout, and social trips in various combination. """ trace_label = 'non_mandatory_tour_frequency' model_settings_file_name = 'non_mandatory_tour_frequency.yaml' model_settings = config.read_model_settings(model_settings_file_name) # FIXME kind of tacky both that we know to add this here and del it below # 'tot_tours' is used in model_spec expressions alternatives = simulate.read_model_alts( 'non_mandatory_tour_frequency_alternatives.csv', set_index=None) alternatives['tot_tours'] = alternatives.sum(axis=1) # filter based on results of CDAP choosers = persons_merged.to_frame() choosers = choosers[choosers.cdap_activity.isin(['M', 'N'])] # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = {'person_max_window': person_max_window} expressions.assign_columns(df=choosers, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) logger.info("Running non_mandatory_tour_frequency with %d persons", len(choosers)) constants = config.get_model_constants(model_settings) model_spec = simulate.read_model_spec(file_name=model_settings['SPEC']) spec_segments = model_settings.get('SPEC_SEGMENTS', {}) # segment by person type and pick the right spec for each person type choices_list = [] for segment_settings in spec_segments: segment_name = segment_settings['NAME'] ptype = segment_settings['PTYPE'] # pick the spec column for the segment segment_spec = model_spec[[segment_name]] chooser_segment = choosers[choosers.ptype == ptype] logger.info("Running segment '%s' of size %d", segment_name, len(chooser_segment)) if len(chooser_segment) == 0: # skip empty segments continue estimator = \ estimation.manager.begin_estimation(model_name=segment_name, bundle_name='non_mandatory_tour_frequency') coefficients_df = simulate.read_model_coefficients(segment_settings) segment_spec = simulate.eval_coefficients(segment_spec, coefficients_df, estimator) if estimator: estimator.write_spec(model_settings, bundle_directory=True) estimator.write_model_settings(model_settings, model_settings_file_name, bundle_directory=True) # preserving coefficients file name makes bringing back updated coefficients more straightforward estimator.write_coefficients(coefficients_df, segment_settings) estimator.write_choosers(chooser_segment) estimator.write_alternatives(alternatives, bundle_directory=True) # FIXME #interaction_simulate_estimation_requires_chooser_id_in_df_column # shuold we do it here or have interaction_simulate do it? # chooser index must be duplicated in column or it will be omitted from interaction_dataset # estimation requires that chooser_id is either in index or a column of interaction_dataset # so it can be reformatted (melted) and indexed by chooser_id and alt_id assert chooser_segment.index.name == 'person_id' assert 'person_id' not in chooser_segment.columns chooser_segment['person_id'] = chooser_segment.index # FIXME set_alt_id - do we need this for interaction_simulate estimation bundle tables? estimator.set_alt_id('alt_id') estimator.set_chooser_id(chooser_segment.index.name) choices = interaction_simulate( chooser_segment, alternatives, spec=segment_spec, locals_d=constants, chunk_size=chunk_size, trace_label='non_mandatory_tour_frequency.%s' % segment_name, trace_choice_name='non_mandatory_tour_frequency', estimator=estimator) if estimator: estimator.write_choices(choices) choices = estimator.get_survey_values( choices, 'persons', 'non_mandatory_tour_frequency') estimator.write_override_choices(choices) estimator.end_estimation() choices_list.append(choices) # FIXME - force garbage collection? force_garbage_collect() del alternatives['tot_tours'] # del tot_tours column we added above # The choice value 'non_mandatory_tour_frequency' assigned by interaction_simulate # is the index value of the chosen alternative in the alternatives table. choices = pd.concat(choices_list).sort_index() # add non_mandatory_tour_frequency column to persons persons = persons.to_frame() # we expect there to be an alt with no tours - which we can use to backfill non-travelers no_tours_alt = (alternatives.sum(axis=1) == 0).index[0] # need to reindex as we only handled persons with cdap_activity in ['M', 'N'] persons['non_mandatory_tour_frequency'] = \ choices.reindex(persons.index).fillna(no_tours_alt).astype(np.int8) """ We have now generated non-mandatory tour frequencies, but they are attributes of the person table Now we create a "tours" table which has one row per tour that has been generated (and the person id it is associated with) But before we do that, we run an additional probablilistic step to extend/increase tour counts beyond the strict limits of the tour_frequency alternatives chosen above (which are currently limited to at most 2 escort tours and 1 each of shopping, othmaint, othdiscr, eatout, and social tours) The choice value 'non_mandatory_tour_frequency' assigned by interaction_simulate is simply the index value of the chosen alternative in the alternatives table. get counts of each of the tour type alternatives (so we can extend) escort shopping othmaint othdiscr eatout social parent_id 2588676 2 0 0 1 1 0 2588677 0 1 0 1 0 0 """ # counts of each of the tour type alternatives (so we can extend) modeled_tour_counts = alternatives.loc[choices] modeled_tour_counts.index = choices.index # assign person ids to the index # - extend_tour_counts - probabalistic extended_tour_counts = \ extend_tour_counts(choosers, modeled_tour_counts.copy(), alternatives, trace_hh_id, tracing.extend_trace_label(trace_label, 'extend_tour_counts')) num_modeled_tours = modeled_tour_counts.sum().sum() num_extended_tours = extended_tour_counts.sum().sum() logger.info("extend_tour_counts increased tour count by %s from %s to %s" % (num_extended_tours - num_modeled_tours, num_modeled_tours, num_extended_tours)) """ create the non_mandatory tours based on extended_tour_counts """ if estimator: override_tour_counts = \ estimation.manager.get_survey_values(extended_tour_counts, table_name='persons', column_names=['_%s' % c for c in extended_tour_counts.columns]) override_tour_counts = \ override_tour_counts.rename(columns={('_%s' % c): c for c in extended_tour_counts.columns}) logger.info( "estimation get_survey_values override_tour_counts %s changed cells" % (override_tour_counts != extended_tour_counts).sum().sum()) extended_tour_counts = override_tour_counts """ create the non_mandatory tours based on extended_tour_counts """ non_mandatory_tours = process_non_mandatory_tours(persons, extended_tour_counts) assert len(non_mandatory_tours) == extended_tour_counts.sum().sum() if estimator: # make sure they created the right tours survey_tours = estimation.manager.get_survey_table( 'tours').sort_index() non_mandatory_survey_tours = survey_tours[survey_tours.tour_category == 'non_mandatory'] assert len(non_mandatory_survey_tours) == len(non_mandatory_tours) assert non_mandatory_survey_tours.index.equals( non_mandatory_tours.sort_index().index) # make sure they created tours with the expected tour_ids columns = ['person_id', 'household_id', 'tour_type', 'tour_category'] survey_tours = \ estimation.manager.get_survey_values(non_mandatory_tours, table_name='tours', column_names=columns) tours_differ = (non_mandatory_tours[columns] != survey_tours[columns]).any(axis=1) if tours_differ.any(): print("tours_differ\n%s" % tours_differ) print("%s of %s tours differ" % (tours_differ.sum(), len(tours_differ))) print("differing survey_tours\n%s" % survey_tours[tours_differ]) print("differing modeled_tours\n%s" % non_mandatory_tours[columns][tours_differ]) assert (not tours_differ.any()) pipeline.extend_table("tours", non_mandatory_tours) tracing.register_traceable_table('tours', non_mandatory_tours) pipeline.get_rn_generator().add_channel('tours', non_mandatory_tours) expressions.assign_columns( df=persons, model_settings=model_settings.get('annotate_persons'), trace_label=trace_label) pipeline.replace_table("persons", persons) tracing.print_summary('non_mandatory_tour_frequency', persons.non_mandatory_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df( non_mandatory_tours, label="non_mandatory_tour_frequency.non_mandatory_tours", warn_if_empty=True) tracing.trace_df(choosers, label="non_mandatory_tour_frequency.choosers", warn_if_empty=True) tracing.trace_df( persons, label="non_mandatory_tour_frequency.annotated_persons", warn_if_empty=True)
def joint_tour_frequency(households, persons, chunk_size, trace_hh_id): """ This model predicts the frequency of making fully joint trips (see the alternatives above). """ trace_label = 'joint_tour_frequency' model_settings_file_name = 'joint_tour_frequency.yaml' estimator = estimation.manager.begin_estimation('joint_tour_frequency') model_settings = config.read_model_settings(model_settings_file_name) alternatives = simulate.read_model_alts( 'joint_tour_frequency_alternatives.csv', set_index='alt') # - only interested in households with more than one cdap travel_active person and # - at least one non-preschooler households = households.to_frame() multi_person_households = households[ households.participates_in_jtf_model].copy() # - only interested in persons in multi_person_households # FIXME - gratuitous pathological efficiency move, just let yaml specify persons? persons = persons.to_frame() persons = persons[persons.household_id.isin(multi_person_households.index)] logger.info( "Running joint_tour_frequency with %d multi-person households" % multi_person_households.shape[0]) # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = { 'persons': persons, 'hh_time_window_overlap': hh_time_window_overlap } expressions.assign_columns(df=multi_person_households, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) model_spec = simulate.read_model_spec(file_name=model_settings['SPEC']) coefficients_df = simulate.read_model_coefficients(model_settings) model_spec = simulate.eval_coefficients(model_spec, coefficients_df, estimator) nest_spec = config.get_logit_model_settings(model_settings) constants = config.get_model_constants(model_settings) if estimator: estimator.write_spec(model_settings) estimator.write_model_settings(model_settings, model_settings_file_name) estimator.write_coefficients(coefficients_df, model_settings) estimator.write_choosers(multi_person_households) choices = simulate.simple_simulate( choosers=multi_person_households, spec=model_spec, nest_spec=nest_spec, locals_d=constants, chunk_size=chunk_size, trace_label=trace_label, trace_choice_name='joint_tour_frequency', estimator=estimator) # convert indexes to alternative names choices = pd.Series(model_spec.columns[choices.values], index=choices.index) if estimator: estimator.write_choices(choices) choices = estimator.get_survey_values(choices, 'households', 'joint_tour_frequency') estimator.write_override_choices(choices) estimator.end_estimation() # - create joint_tours based on joint_tour_frequency choices # - we need a person_id in order to generate the tour index (and for register_traceable_table) # - but we don't know the tour participants yet # - so we arbitrarily choose the first person in the household # - to be point person for the purpose of generating an index and setting origin temp_point_persons = persons.loc[persons.PNUM == 1] temp_point_persons['person_id'] = temp_point_persons.index temp_point_persons = temp_point_persons.set_index('household_id') temp_point_persons = temp_point_persons[['person_id', 'home_zone_id']] joint_tours = \ process_joint_tours(choices, alternatives, temp_point_persons) tours = pipeline.extend_table("tours", joint_tours) tracing.register_traceable_table('tours', joint_tours) pipeline.get_rn_generator().add_channel('tours', joint_tours) # - annotate households # we expect there to be an alt with no tours - which we can use to backfill non-travelers no_tours_alt = (alternatives.sum(axis=1) == 0).index[0] households['joint_tour_frequency'] = choices.reindex( households.index).fillna(no_tours_alt).astype(str) households['num_hh_joint_tours'] = joint_tours.groupby('household_id').size().\ reindex(households.index).fillna(0).astype(np.int8) pipeline.replace_table("households", households) tracing.print_summary('joint_tour_frequency', households.joint_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df(households, label="joint_tour_frequency.households") tracing.trace_df(joint_tours, label="joint_tour_frequency.joint_tours", slicer='household_id') if estimator: survey_tours = estimation.manager.get_survey_table('tours') survey_tours = survey_tours[survey_tours.tour_category == 'joint'] print(f"len(survey_tours) {len(survey_tours)}") print(f"len(joint_tours) {len(joint_tours)}") different = False survey_tours_not_in_tours = survey_tours[~survey_tours.index. isin(joint_tours.index)] if len(survey_tours_not_in_tours) > 0: print(f"survey_tours_not_in_tours\n{survey_tours_not_in_tours}") different = True tours_not_in_survey_tours = joint_tours[~joint_tours.index. isin(survey_tours.index)] if len(survey_tours_not_in_tours) > 0: print(f"tours_not_in_survey_tours\n{tours_not_in_survey_tours}") different = True assert not different
def atwork_subtour_frequency(tours, persons_merged, chunk_size, trace_hh_id): """ This model predicts the frequency of making at-work subtour tours (alternatives for this model come from a separate csv file which is configured by the user). """ trace_label = 'atwork_subtour_frequency' model_settings = config.read_model_settings( 'atwork_subtour_frequency.yaml') model_spec = simulate.read_model_spec( file_name='atwork_subtour_frequency.csv') alternatives = simulate.read_model_alts( config.config_file_path('atwork_subtour_frequency_alternatives.csv'), set_index='alt') tours = tours.to_frame() persons_merged = persons_merged.to_frame() work_tours = tours[tours.tour_type == 'work'] # - if no work_tours if len(work_tours) == 0: add_null_results(trace_label, tours) return # merge persons into work_tours work_tours = pd.merge(work_tours, persons_merged, left_on='person_id', right_index=True) logger.info("Running atwork_subtour_frequency with %d work tours", len(work_tours)) nest_spec = config.get_logit_model_settings(model_settings) constants = config.get_model_constants(model_settings) # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: assign_columns(df=work_tours, model_settings=preprocessor_settings, trace_label=trace_label) choices = simulate.simple_simulate( choosers=work_tours, spec=model_spec, nest_spec=nest_spec, locals_d=constants, chunk_size=chunk_size, trace_label=trace_label, trace_choice_name='atwork_subtour_frequency') # convert indexes to alternative names choices = pd.Series(model_spec.columns[choices.values], index=choices.index) tracing.print_summary('atwork_subtour_frequency', choices, value_counts=True) # add atwork_subtour_frequency column to tours # reindex since we are working with a subset of tours tours['atwork_subtour_frequency'] = choices.reindex(tours.index) pipeline.replace_table("tours", tours) # - create atwork_subtours based on atwork_subtour_frequency choice names work_tours = tours[tours.tour_type == 'work'] assert not work_tours.atwork_subtour_frequency.isnull().any() subtours = process_atwork_subtours(work_tours, alternatives) tours = pipeline.extend_table("tours", subtours) tracing.register_traceable_table('tours', subtours) pipeline.get_rn_generator().add_channel('tours', subtours) if trace_hh_id: tracing.trace_df(tours, label='atwork_subtour_frequency.tours')
def joint_tour_frequency(households, persons, chunk_size, trace_hh_id): """ This model predicts the frequency of making fully joint trips (see the alternatives above). """ trace_label = 'joint_tour_frequency' model_settings = config.read_model_settings('joint_tour_frequency.yaml') model_spec = simulate.read_model_spec(file_name='joint_tour_frequency.csv') alternatives = simulate.read_model_alts( config.config_file_path('joint_tour_frequency_alternatives.csv'), set_index='alt') # - only interested in households with more than one cdap travel_active person households = households.to_frame() multi_person_households = households[ households.num_travel_active > 1].copy() # - only interested in persons in multi_person_households # FIXME - gratuitous pathological efficiency move, just let yaml specify persons? persons = persons.to_frame() persons = persons[persons.household_id.isin(multi_person_households.index)] logger.info( "Running joint_tour_frequency with %d multi-person households" % multi_person_households.shape[0]) # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = { 'persons': persons, 'hh_time_window_overlap': hh_time_window_overlap } expressions.assign_columns(df=multi_person_households, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) # - simple_simulate nest_spec = config.get_logit_model_settings(model_settings) constants = config.get_model_constants(model_settings) choices = simulate.simple_simulate( choosers=multi_person_households, spec=model_spec, nest_spec=nest_spec, locals_d=constants, chunk_size=chunk_size, trace_label=trace_label, trace_choice_name='joint_tour_frequency') # convert indexes to alternative names choices = pd.Series(model_spec.columns[choices.values], index=choices.index) # - create joint_tours based on joint_tour_frequency choices # - we need a person_id in order to generate the tour index (and for register_traceable_table) # - but we don't know the tour participants yet # - so we arbitrarily choose the first person in the household # - to be point person for the purpose of generating an index and setting origin temp_point_persons = persons.loc[persons.PNUM == 1] temp_point_persons['person_id'] = temp_point_persons.index temp_point_persons = temp_point_persons.set_index('household_id') temp_point_persons = temp_point_persons[['person_id', 'home_taz']] joint_tours = \ process_joint_tours(choices, alternatives, temp_point_persons) tours = pipeline.extend_table("tours", joint_tours) tracing.register_traceable_table('tours', joint_tours) pipeline.get_rn_generator().add_channel('tours', joint_tours) # - annotate households # add joint_tour_frequency and num_hh_joint_tours columns to households # reindex since we ran model on a subset of households households['joint_tour_frequency'] = choices.reindex( households.index).fillna('').astype(str) households['num_hh_joint_tours'] = joint_tours.groupby('household_id').size().\ reindex(households.index).fillna(0).astype(np.int8) pipeline.replace_table("households", households) tracing.print_summary('joint_tour_frequency', households.joint_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df(households, label="joint_tour_frequency.households") tracing.trace_df(joint_tours, label="joint_tour_frequency.joint_tours", slicer='household_id')
def mandatory_tour_frequency(persons_merged, chunk_size, trace_hh_id): """ This model predicts the frequency of making mandatory trips (see the alternatives above) - these trips include work and school in some combination. """ trace_label = 'mandatory_tour_frequency' model_settings = config.read_model_settings('mandatory_tour_frequency.yaml') model_spec = simulate.read_model_spec(file_name='mandatory_tour_frequency.csv') alternatives = simulate.read_model_alts( config.config_file_path('mandatory_tour_frequency_alternatives.csv'), set_index='alt') choosers = persons_merged.to_frame() # filter based on results of CDAP choosers = choosers[choosers.cdap_activity == 'M'] logger.info("Running mandatory_tour_frequency with %d persons", len(choosers)) # - if no mandatory tours if choosers.shape[0] == 0: add_null_results(trace_label, model_settings) return # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = {} expressions.assign_columns( df=choosers, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) nest_spec = config.get_logit_model_settings(model_settings) constants = config.get_model_constants(model_settings) choices = simulate.simple_simulate( choosers=choosers, spec=model_spec, nest_spec=nest_spec, locals_d=constants, chunk_size=chunk_size, trace_label=trace_label, trace_choice_name='mandatory_tour_frequency') # convert indexes to alternative names choices = pd.Series( model_spec.columns[choices.values], index=choices.index).reindex(persons_merged.local.index) # - create mandatory tours """ This reprocesses the choice of index of the mandatory tour frequency alternatives into an actual dataframe of tours. Ending format is the same as got non_mandatory_tours except trip types are "work" and "school" """ choosers['mandatory_tour_frequency'] = choices mandatory_tours = process_mandatory_tours( persons=choosers, mandatory_tour_frequency_alts=alternatives ) tours = pipeline.extend_table("tours", mandatory_tours) tracing.register_traceable_table('tours', mandatory_tours) pipeline.get_rn_generator().add_channel('tours', mandatory_tours) # - annotate persons persons = inject.get_table('persons').to_frame() # need to reindex as we only handled persons with cdap_activity == 'M' persons['mandatory_tour_frequency'] = choices.reindex(persons.index).fillna('').astype(str) expressions.assign_columns( df=persons, model_settings=model_settings.get('annotate_persons'), trace_label=tracing.extend_trace_label(trace_label, 'annotate_persons')) pipeline.replace_table("persons", persons) tracing.print_summary('mandatory_tour_frequency', persons.mandatory_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df(mandatory_tours, label="mandatory_tour_frequency.mandatory_tours", warn_if_empty=True) tracing.trace_df(persons, label="mandatory_tour_frequency.persons", warn_if_empty=True)
def non_mandatory_tour_frequency(persons, persons_merged, chunk_size, trace_hh_id): """ This model predicts the frequency of making non-mandatory trips (alternatives for this model come from a separate csv file which is configured by the user) - these trips include escort, shopping, othmaint, othdiscr, eatout, and social trips in various combination. """ trace_label = 'non_mandatory_tour_frequency' model_settings = config.read_model_settings('non_mandatory_tour_frequency.yaml') model_spec = simulate.read_model_spec(file_name='non_mandatory_tour_frequency.csv') alternatives = simulate.read_model_alts( config.config_file_path('non_mandatory_tour_frequency_alternatives.csv'), set_index=None) choosers = persons_merged.to_frame() # FIXME kind of tacky both that we know to add this here and del it below # 'tot_tours' is used in model_spec expressions alternatives['tot_tours'] = alternatives.sum(axis=1) # - preprocessor preprocessor_settings = model_settings.get('preprocessor', None) if preprocessor_settings: locals_dict = { 'person_max_window': person_max_window } expressions.assign_columns( df=choosers, model_settings=preprocessor_settings, locals_dict=locals_dict, trace_label=trace_label) # filter based on results of CDAP choosers = choosers[choosers.cdap_activity.isin(['M', 'N'])] logger.info("Running non_mandatory_tour_frequency with %d persons", len(choosers)) constants = config.get_model_constants(model_settings) choices_list = [] # segment by person type and pick the right spec for each person type for ptype, segment in choosers.groupby('ptype'): name = PTYPE_NAME[ptype] # pick the spec column for the segment spec = model_spec[[name]] # drop any zero-valued rows spec = spec[spec[name] != 0] logger.info("Running segment '%s' of size %d", name, len(segment)) choices = interaction_simulate( segment, alternatives, spec=spec, locals_d=constants, chunk_size=chunk_size, trace_label='non_mandatory_tour_frequency.%s' % name, trace_choice_name='non_mandatory_tour_frequency') choices_list.append(choices) # FIXME - force garbage collection? # force_garbage_collect() choices = pd.concat(choices_list) del alternatives['tot_tours'] # del tot_tours column we added above # - add non_mandatory_tour_frequency column to persons persons = persons.to_frame() # need to reindex as we only handled persons with cdap_activity in ['M', 'N'] # (we expect there to be an alt with no tours - which we can use to backfill non-travelers) no_tours_alt = (alternatives.sum(axis=1) == 0).index[0] persons['non_mandatory_tour_frequency'] = \ choices.reindex(persons.index).fillna(no_tours_alt).astype(np.int8) """ We have now generated non-mandatory tours, but they are attributes of the person table Now we create a "tours" table which has one row per tour that has been generated (and the person id it is associated with) """ # - get counts of each of the alternatives (so we can extend) # (choices is just the index values for the chosen alts) """ escort shopping othmaint othdiscr eatout social parent_id 2588676 2 0 0 1 1 0 2588677 0 1 0 1 0 0 """ tour_counts = alternatives.loc[choices] tour_counts.index = choices.index # assign person ids to the index prev_tour_count = tour_counts.sum().sum() # - extend_tour_counts tour_counts = extend_tour_counts(choosers, tour_counts, alternatives, trace_hh_id, tracing.extend_trace_label(trace_label, 'extend_tour_counts')) extended_tour_count = tour_counts.sum().sum() logging.info("extend_tour_counts increased nmtf tour count by %s from %s to %s" % (extended_tour_count - prev_tour_count, prev_tour_count, extended_tour_count)) # - create the non_mandatory tours non_mandatory_tours = process_non_mandatory_tours(persons, tour_counts) assert len(non_mandatory_tours) == extended_tour_count pipeline.extend_table("tours", non_mandatory_tours) tracing.register_traceable_table('tours', non_mandatory_tours) pipeline.get_rn_generator().add_channel('tours', non_mandatory_tours) expressions.assign_columns( df=persons, model_settings=model_settings.get('annotate_persons'), trace_label=trace_label) pipeline.replace_table("persons", persons) tracing.print_summary('non_mandatory_tour_frequency', persons.non_mandatory_tour_frequency, value_counts=True) if trace_hh_id: tracing.trace_df(non_mandatory_tours, label="non_mandatory_tour_frequency.non_mandatory_tours", warn_if_empty=True) tracing.trace_df(choosers, label="non_mandatory_tour_frequency.choosers", warn_if_empty=True) tracing.trace_df(persons, label="non_mandatory_tour_frequency.annotated_persons", warn_if_empty=True)