def load_map_clean_fba(method, attr, fba_sourcename, df_year, flowclass, geoscale_from, geoscale_to, **kwargs): """ Load, clean, and map a FlowByActivity df :param method: dictionary, FBS method yaml :param attr: dictionary, attribute data from method yaml for activity set :param fba_sourcename: str, source name :param df_year: str, year :param flowclass: str, flowclass to subset df with :param geoscale_from: str, geoscale to use :param geoscale_to: str, geoscale to aggregate to :param kwargs: dictionary, can include parameters: 'allocation_flow', 'allocation_compartment','clean_allocation_fba', 'clean_allocation_fba_w_sec' :return: df, fba format """ log.info("Loading allocation flowbyactivity %s for year %s", fba_sourcename, str(df_year)) fba = load_fba_w_standardized_units(datasource=fba_sourcename, year=df_year, flowclass=flowclass) # check if allocation data exists at specified geoscale to use log.info("Checking if allocation data exists at the %s level", geoscale_from) check_if_data_exists_at_geoscale(fba, geoscale_from) # aggregate geographically to the scale of the flowbyactivty source, if necessary fba = subset_df_by_geoscale(fba, geoscale_from, geoscale_to) # subset based on yaml settings if 'flowname_subset' in kwargs: if kwargs['flowname_subset'] != 'None': fba = fba.loc[fba['FlowName'].isin(kwargs['flowname_subset'])] if 'compartment_subset' in kwargs: if kwargs['compartment_subset'] != 'None': fba = fba.loc[fba['Compartment'].isin(kwargs['compartment_subset'])] # cleanup the fba allocation df, if necessary if 'clean_fba' in kwargs: log.info("Cleaning %s", fba_sourcename) fba = dynamically_import_fxn(fba_sourcename, kwargs["clean_fba"])(fba, attr=attr) # reset index fba = fba.reset_index(drop=True) # assign sector to allocation dataset log.info("Adding sectors to %s", fba_sourcename) fba_wsec = add_sectors_to_flowbyactivity(fba, sectorsourcename=method['target_sector_source']) # call on fxn to further clean up/disaggregate the fba allocation data, if exists if 'clean_fba_w_sec' in kwargs: log.info("Further disaggregating sectors in %s", fba_sourcename) fba_wsec = dynamically_import_fxn(fba_sourcename, kwargs['clean_fba_w_sec'])(fba_wsec, attr=attr, method=method, sourcename=fba_sourcename) return fba_wsec
def compare_fba_geo_subset_and_fbs_output_totals(fba_load, fbs_load, activity_set, source_name, source_attr, activity_attr, method): """ Function to compare the loaded flowbyactivity total after subsetting by activity and geography with the final flowbysector output total. Not a direct comparison of the loaded FBA because FBAs are modified before being subset by activity for the target sector level :param fba_load: df, FBA loaded, before being mapped :param fbs_load: df, final FBS df at target sector level :param activity_set: str, activity set :param source_name: str, source name :param source_attr: dictionary, attribute data from method yaml for source data :param activity_attr: dictionary, attribute data from method yaml for activity set :param method: dictionary, FBS method yaml :return: printout data differences between loaded FBA and FBS output totals by location, save results as csv in local directory """ vLog.info('Comparing Flow-By-Activity subset by activity and geography to ' 'the subset Flow-By-Sector FlowAmount total.') # determine from scale if fips_number_key[source_attr['geoscale_to_use']] < \ fips_number_key[activity_attr['allocation_from_scale']]: from_scale = source_attr['geoscale_to_use'] else: from_scale = activity_attr['allocation_from_scale'] # extract relevant geoscale data or aggregate existing data fba = subset_df_by_geoscale(fba_load, from_scale, method['target_geoscale']) if check_activities_sector_like(source_name): # if activities are sector-like, run sector aggregation and then # subset df to only keep NAICS2 fba = fba[[ 'Class', 'FlowAmount', 'Unit', 'Context', 'ActivityProducedBy', 'ActivityConsumedBy', 'Location', 'LocationSystem' ]] # rename the activity cols to sector cols for purposes of aggregation fba = fba.rename( columns={ 'ActivityProducedBy': 'SectorProducedBy', 'ActivityConsumedBy': 'SectorConsumedBy' }) group_cols_agg = [ 'Class', 'Context', 'Unit', 'Location', 'LocationSystem', 'SectorProducedBy', 'SectorConsumedBy' ] fba = sector_aggregation(fba, group_cols_agg) # subset fba to only include NAICS2 fba = replace_NoneType_with_empty_cells(fba) fba = fba[fba['SectorConsumedBy'].apply(lambda x: len(x) == 2) | fba['SectorProducedBy'].apply(lambda x: len(x) == 2)] # subset/agg dfs col_subset = [ 'Class', 'FlowAmount', 'Unit', 'Context', 'Location', 'LocationSystem' ] group_cols = ['Class', 'Unit', 'Context', 'Location', 'LocationSystem'] # check units compare_df_units(fba, fbs_load) # fba fba = fba[col_subset] fba_agg = aggregator(fba, group_cols).reset_index(drop=True) fba_agg.rename(columns={ 'FlowAmount': 'FBA_amount', 'Unit': 'FBA_unit' }, inplace=True) # fbs fbs = fbs_load[col_subset] fbs_agg = aggregator(fbs, group_cols) fbs_agg.rename(columns={ 'FlowAmount': 'FBS_amount', 'Unit': 'FBS_unit' }, inplace=True) try: # merge FBA and FBS totals df_merge = fba_agg.merge(fbs_agg, how='left') df_merge['FlowAmount_difference'] = \ df_merge['FBA_amount'] - df_merge['FBS_amount'] df_merge['Percent_difference'] = \ (df_merge['FlowAmount_difference']/df_merge['FBA_amount']) * 100 # reorder df_merge = df_merge[[ 'Class', 'Context', 'Location', 'LocationSystem', 'FBA_amount', 'FBA_unit', 'FBS_amount', 'FBS_unit', 'FlowAmount_difference', 'Percent_difference' ]] df_merge = replace_NoneType_with_empty_cells(df_merge) # list of contexts and locations context_list = df_merge[['Context', 'Location']].values.tolist() # loop through the contexts and print results of comparison vLog.info( 'Comparing FBA %s %s subset to FBS results. ' 'Details in Validation Log', activity_set, source_attr['geoscale_to_use']) for i, j in context_list: df_merge_subset = \ df_merge[(df_merge['Context'] == i) & (df_merge['Location'] == j)].reset_index(drop=True) diff_per = df_merge_subset['Percent_difference'][0] if np.isnan(diff_per): vLog.info( 'FlowBySector FlowAmount for %s %s %s ' 'does not exist in the FBS', source_name, activity_set, i) continue # make reporting more manageable if abs(diff_per) > 0.01: diff_per = round(diff_per, 2) else: diff_per = round(diff_per, 6) # diff_units = df_merge_subset['FBS_unit'][0] if diff_per > 0: vLog.info( 'FlowBySector FlowAmount for %s %s %s at %s is %s%% ' 'less than the FlowByActivity FlowAmount', source_name, activity_set, i, j, str(abs(diff_per))) elif diff_per < 0: vLog.info( 'FlowBySector FlowAmount for %s %s %s at %s is %s%% ' 'more than the FlowByActivity FlowAmount', source_name, activity_set, i, j, str(abs(diff_per))) elif diff_per == 0: vLogDetailed.info( 'FlowBySector FlowAmount for ' '%s %s %s at %s is equal to the ' 'FlowByActivity FlowAmount', source_name, activity_set, i, j) # subset the df to include in the validation log # only print rows where the percent difference does not round to 0 df_v = df_merge[df_merge['Percent_difference'].apply( lambda x: round(x, 3) != 0)].reset_index(drop=True) # log output log.info( 'Save the comparison of FlowByActivity load to FlowBySector ' 'total FlowAmounts for %s in validation log file', activity_set) # if df not empty, print, if empty, print string if df_v.empty: vLogDetailed.info('Percent difference for %s all round to 0', activity_set) else: vLogDetailed.info( 'Comparison of FBA load to FBS total ' 'FlowAmounts for %s: ' '\n {}'.format(df_v.to_string()), activity_set) except: vLog.info('Error occurred when comparing total FlowAmounts ' 'for FlowByActivity and FlowBySector')
def main(method_name): """ Creates a flowbysector dataset :param method_name: Name of method corresponding to flowbysector method yaml name :return: flowbysector """ log.info("Initiating flowbysector creation for " + method_name) # call on method method = load_method(method_name) # create dictionary of data and allocation datasets fb = method['source_names'] # Create empty list for storing fbs files fbs_list = [] for k, v in fb.items(): # pull fba data for allocation flows = load_source_dataframe(k, v) if v['data_format'] == 'FBA': # ensure correct datatypes and that all fields exist flows = clean_df(flows, flow_by_activity_fields, fba_fill_na_dict, drop_description=False) # clean up fba, if specified in yaml if v["clean_fba_df_fxn"] != 'None': log.info("Cleaning up " + k + " FlowByActivity") flows = getattr(sys.modules[__name__], v["clean_fba_df_fxn"])(flows) # if activity_sets are specified in a file, call them here if 'activity_set_file' in v: aset_names = pd.read_csv(flowbysectoractivitysetspath + v['activity_set_file'], dtype=str) # create dictionary of allocation datasets for different activities activities = v['activity_sets'] # subset activity data and allocate to sector for aset, attr in activities.items(): # subset by named activities if 'activity_set_file' in v: names = aset_names[aset_names['activity_set'] == aset]['name'] else: names = attr['names'] log.info("Preparing to handle subset of flownames " + ', '.join(map(str, names)) + " in " + k) # subset fba data by activity flows_subset = flows[ (flows[fba_activity_fields[0]].isin(names)) | (flows[fba_activity_fields[1]].isin(names))].reset_index( drop=True) # extract relevant geoscale data or aggregate existing data log.info("Subsetting/aggregating dataframe to " + attr['allocation_from_scale'] + " geoscale") flows_subset_geo = subset_df_by_geoscale( flows_subset, v['geoscale_to_use'], attr['allocation_from_scale']) # Add sectors to df activity, depending on level of specified sector aggregation log.info("Adding sectors to " + k) flow_subset_wsec = add_sectors_to_flowbyactivity( flows_subset_geo, sectorsourcename=method['target_sector_source'], allocationmethod=attr['allocation_method']) # clean up fba with sectors, if specified in yaml if v["clean_fba_w_sec_df_fxn"] != 'None': log.info("Cleaning up " + k + " FlowByActivity with sectors") flow_subset_wsec = getattr(sys.modules[__name__], v["clean_fba_w_sec_df_fxn"])( flow_subset_wsec, attr=attr) # map df to elementary flows log.info("Mapping flows in " + k + ' to federal elementary flow list') if 'fedefl_mapping' in v: mapping_files = v['fedefl_mapping'] else: mapping_files = k flow_subset_mapped = map_elementary_flows( flow_subset_wsec, mapping_files) # clean up mapped fba with sectors, if specified in yaml if "clean_mapped_fba_w_sec_df_fxn" in v: log.info("Cleaning up " + k + " FlowByActivity with sectors") flow_subset_mapped = getattr( sys.modules[__name__], v["clean_mapped_fba_w_sec_df_fxn"])(flow_subset_mapped, attr, method) # if allocation method is "direct", then no need to create alloc ratios, else need to use allocation # dataframe to create sector allocation ratios if attr['allocation_method'] == 'direct': log.info('Directly assigning ' + ', '.join(map(str, names)) + ' to sectors') fbs = flow_subset_mapped.copy() # for each activity, if activities are not sector like, check that there is no data loss if load_source_catalog( )[k]['sector-like_activities'] is False: activity_list = [] for n in names: log.info('Checking for ' + n + ' at ' + method['target_sector_level']) fbs_subset = fbs[( (fbs[fba_activity_fields[0]] == n) & (fbs[fba_activity_fields[1]] == n)) | (fbs[fba_activity_fields[0]] == n) | (fbs[fba_activity_fields[1]] == n )].reset_index(drop=True) fbs_subset = check_if_losing_sector_data( fbs_subset, method['target_sector_level']) activity_list.append(fbs_subset) fbs = pd.concat(activity_list, ignore_index=True) # if allocation method for an activity set requires a specific function due to the complicated nature # of the allocation, call on function here elif attr['allocation_method'] == 'allocation_function': log.info( 'Calling on function specified in method yaml to allocate ' + ', '.join(map(str, names)) + ' to sectors') fbs = getattr(sys.modules[__name__], attr['allocation_source'])( flow_subset_mapped, attr, fbs_list) else: # determine appropriate allocation dataset log.info("Loading allocation flowbyactivity " + attr['allocation_source'] + " for year " + str(attr['allocation_source_year'])) fba_allocation = flowsa.getFlowByActivity( flowclass=[attr['allocation_source_class']], datasource=attr['allocation_source'], years=[attr['allocation_source_year'] ]).reset_index(drop=True) # clean df and harmonize unites fba_allocation = clean_df(fba_allocation, flow_by_activity_fields, fba_fill_na_dict) fba_allocation = harmonize_units(fba_allocation) # check if allocation data exists at specified geoscale to use log.info("Checking if allocation data exists at the " + attr['allocation_from_scale'] + " level") check_if_data_exists_at_geoscale( fba_allocation, attr['allocation_from_scale']) # aggregate geographically to the scale of the flowbyactivty source, if necessary fba_allocation = subset_df_by_geoscale( fba_allocation, attr['allocation_from_scale'], v['geoscale_to_use']) # subset based on yaml settings if attr['allocation_flow'] != 'None': fba_allocation = fba_allocation.loc[ fba_allocation['FlowName'].isin( attr['allocation_flow'])] if attr['allocation_compartment'] != 'None': fba_allocation = fba_allocation.loc[ fba_allocation['Compartment'].isin( attr['allocation_compartment'])] # cleanup the fba allocation df, if necessary if 'clean_allocation_fba' in attr: log.info("Cleaning " + attr['allocation_source']) fba_allocation = getattr(sys.modules[__name__], attr["clean_allocation_fba"])( fba_allocation, attr=attr) # reset index fba_allocation = fba_allocation.reset_index(drop=True) # assign sector to allocation dataset log.info("Adding sectors to " + attr['allocation_source']) fba_allocation_wsec = add_sectors_to_flowbyactivity( fba_allocation, sectorsourcename=method['target_sector_source']) # call on fxn to further clean up/disaggregate the fba allocation data, if exists if 'clean_allocation_fba_w_sec' in attr: log.info("Further disaggregating sectors in " + attr['allocation_source']) fba_allocation_wsec = getattr( sys.modules[__name__], attr["clean_allocation_fba_w_sec"])( fba_allocation_wsec, attr=attr, method=method) # subset fba datasets to only keep the sectors associated with activity subset log.info("Subsetting " + attr['allocation_source'] + " for sectors in " + k) fba_allocation_subset = get_fba_allocation_subset( fba_allocation_wsec, k, names, flowSubsetMapped=flow_subset_mapped, allocMethod=attr['allocation_method']) # if there is an allocation helper dataset, modify allocation df if attr['allocation_helper'] == 'yes': log.info( "Using the specified allocation help for subset of " + attr['allocation_source']) fba_allocation_subset = allocation_helper( fba_allocation_subset, attr, method, v) # create flow allocation ratios for each activity # if load_source_catalog()[k]['sector-like_activities'] flow_alloc_list = [] group_cols = fba_mapped_default_grouping_fields group_cols = [ e for e in group_cols if e not in ('ActivityProducedBy', 'ActivityConsumedBy') ] for n in names: log.info("Creating allocation ratios for " + n) fba_allocation_subset_2 = get_fba_allocation_subset( fba_allocation_subset, k, [n], flowSubsetMapped=flow_subset_mapped, allocMethod=attr['allocation_method']) if len(fba_allocation_subset_2) == 0: log.info("No data found to allocate " + n) else: flow_alloc = allocate_by_sector( fba_allocation_subset_2, k, attr['allocation_source'], attr['allocation_method'], group_cols, flowSubsetMapped=flow_subset_mapped) flow_alloc = flow_alloc.assign(FBA_Activity=n) flow_alloc_list.append(flow_alloc) flow_allocation = pd.concat(flow_alloc_list, ignore_index=True) # generalize activity field names to enable link to main fba source log.info("Generalizing activity columns in subset of " + attr['allocation_source']) flow_allocation = collapse_activity_fields(flow_allocation) # check for issues with allocation ratios check_allocation_ratios(flow_allocation, aset, k, method_name) # create list of sectors in the flow allocation df, drop any rows of data in the flow df that \ # aren't in list sector_list = flow_allocation['Sector'].unique().tolist() # subset fba allocation table to the values in the activity list, based on overlapping sectors flow_subset_mapped = flow_subset_mapped.loc[ (flow_subset_mapped[fbs_activity_fields[0]]. isin(sector_list)) | (flow_subset_mapped[fbs_activity_fields[1]]. isin(sector_list))] # check if fba and allocation dfs have the same LocationSystem log.info( "Checking if flowbyactivity and allocation dataframes use the same location systems" ) check_if_location_systems_match(flow_subset_mapped, flow_allocation) # merge fba df w/flow allocation dataset log.info("Merge " + k + " and subset of " + attr['allocation_source']) fbs = flow_subset_mapped.merge( flow_allocation[[ 'Location', 'Sector', 'FlowAmountRatio', 'FBA_Activity' ]], left_on=[ 'Location', 'SectorProducedBy', 'ActivityProducedBy' ], right_on=['Location', 'Sector', 'FBA_Activity'], how='left') fbs = fbs.merge( flow_allocation[[ 'Location', 'Sector', 'FlowAmountRatio', 'FBA_Activity' ]], left_on=[ 'Location', 'SectorConsumedBy', 'ActivityConsumedBy' ], right_on=['Location', 'Sector', 'FBA_Activity'], how='left') # merge the flowamount columns fbs.loc[:, 'FlowAmountRatio'] = fbs[ 'FlowAmountRatio_x'].fillna(fbs['FlowAmountRatio_y']) # fill null rows with 0 because no allocation info fbs['FlowAmountRatio'] = fbs['FlowAmountRatio'].fillna(0) # check if fba and alloc dfs have data for same geoscales - comment back in after address the 'todo' # log.info("Checking if flowbyactivity and allocation dataframes have data at the same locations") # check_if_data_exists_for_same_geoscales(fbs, k, attr['names']) # drop rows where there is no allocation data fbs = fbs.dropna(subset=['Sector_x', 'Sector_y'], how='all').reset_index() # calculate flow amounts for each sector log.info("Calculating new flow amounts using flow ratios") fbs.loc[:, 'FlowAmount'] = fbs['FlowAmount'] * fbs[ 'FlowAmountRatio'] # drop columns log.info("Cleaning up new flow by sector") fbs = fbs.drop(columns=[ 'Sector_x', 'FlowAmountRatio_x', 'Sector_y', 'FlowAmountRatio_y', 'FlowAmountRatio', 'FBA_Activity_x', 'FBA_Activity_y' ]) # drop rows where flowamount = 0 (although this includes dropping suppressed data) fbs = fbs[fbs['FlowAmount'] != 0].reset_index(drop=True) # define grouping columns dependent on sectors being activity-like or not if load_source_catalog()[k]['sector-like_activities'] is False: groupingcols = fbs_grouping_fields_w_activities groupingdict = flow_by_sector_fields_w_activity else: groupingcols = fbs_default_grouping_fields groupingdict = flow_by_sector_fields # clean df fbs = clean_df(fbs, groupingdict, fbs_fill_na_dict) # aggregate df geographically, if necessary # todo: replace with fxn return_from_scale log.info("Aggregating flowbysector to " + method['target_geoscale'] + " level") if fips_number_key[v['geoscale_to_use']] < fips_number_key[ attr['allocation_from_scale']]: from_scale = v['geoscale_to_use'] else: from_scale = attr['allocation_from_scale'] to_scale = method['target_geoscale'] fbs_geo_agg = agg_by_geoscale(fbs, from_scale, to_scale, groupingcols) # aggregate data to every sector level log.info("Aggregating flowbysector to all sector levels") fbs_sec_agg = sector_aggregation(fbs_geo_agg, groupingcols) # add missing naics5/6 when only one naics5/6 associated with a naics4 fbs_agg = sector_disaggregation(fbs_sec_agg, groupingdict) # check if any sector information is lost before reaching the target sector length, if so, # allocate values equally to disaggregated sectors log.info('Checking for data at ' + method['target_sector_level']) fbs_agg_2 = check_if_losing_sector_data( fbs_agg, method['target_sector_level']) # compare flowbysector with flowbyactivity # todo: modify fxn to work if activities are sector like in df being allocated if load_source_catalog()[k]['sector-like_activities'] is False: check_for_differences_between_fba_load_and_fbs_output( flow_subset_mapped, fbs_agg_2, aset, k, method_name) # return sector level specified in method yaml # load the crosswalk linking sector lengths sector_list = get_sector_list(method['target_sector_level']) # subset df, necessary because not all of the sectors are NAICS and can get duplicate rows fbs_1 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isin(sector_list)) & (fbs_agg_2[fbs_activity_fields[1]].isin(sector_list) )].reset_index(drop=True) fbs_2 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isin(sector_list)) & (fbs_agg_2[fbs_activity_fields[1]].isnull())].reset_index( drop=True) fbs_3 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isnull()) & (fbs_agg_2[fbs_activity_fields[1]].isin(sector_list) )].reset_index(drop=True) fbs_sector_subset = pd.concat([fbs_1, fbs_2, fbs_3]) # drop activity columns fbs_sector_subset = fbs_sector_subset.drop( ['ActivityProducedBy', 'ActivityConsumedBy'], axis=1, errors='ignore') # save comparison of FBA total to FBS total for an activity set compare_fba_load_and_fbs_output_totals(flows_subset_geo, fbs_sector_subset, aset, k, method_name, attr, method, mapping_files) log.info( "Completed flowbysector for activity subset with flows " + ', '.join(map(str, names))) fbs_list.append(fbs_sector_subset) else: # if the loaded flow dt is already in FBS format, append directly to list of FBS log.info("Append " + k + " to FBS list") # ensure correct field datatypes and add any missing fields flows = clean_df(flows, flow_by_sector_fields, fbs_fill_na_dict) fbs_list.append(flows) # create single df of all activities log.info("Concat data for all activities") fbss = pd.concat(fbs_list, ignore_index=True, sort=False) log.info("Clean final dataframe") # aggregate df as activities might have data for the same specified sector length fbss = clean_df(fbss, flow_by_sector_fields, fbs_fill_na_dict) fbss = aggregator(fbss, fbs_default_grouping_fields) # sort df log.info("Sort and store dataframe") # add missing fields, ensure correct data type, reorder columns fbss = fbss.sort_values( ['SectorProducedBy', 'SectorConsumedBy', 'Flowable', 'Context']).reset_index(drop=True) # save parquet file store_flowbysector(fbss, method_name)
def main(**kwargs): """ Creates a flowbysector dataset :param kwargs: dictionary of arguments, only argument is "method_name", the name of method corresponding to flowbysector method yaml name :return: parquet, FBS save to local folder """ if len(kwargs) == 0: kwargs = parse_args() method_name = kwargs['method'] download_FBA_if_missing = kwargs.get('download_FBAs_if_missing') # assign arguments vLog.info("Initiating flowbysector creation for %s", method_name) # call on method method = load_yaml_dict(method_name, flowbytype='FBS') # create dictionary of data and allocation datasets fb = method['source_names'] # Create empty list for storing fbs files fbs_list = [] for k, v in fb.items(): # pull fba data for allocation flows = load_source_dataframe(k, v, download_FBA_if_missing) if v['data_format'] == 'FBA': # ensure correct datatypes and that all fields exist flows = clean_df(flows, flow_by_activity_fields, fba_fill_na_dict, drop_description=False) # clean up fba before mapping, if specified in yaml if "clean_fba_before_mapping_df_fxn" in v: vLog.info("Cleaning up %s FlowByActivity", k) flows = dynamically_import_fxn( k, v["clean_fba_before_mapping_df_fxn"])(flows) # map flows to federal flow list or material flow list flows_mapped, mapping_files = \ map_fbs_flows(flows, k, v, keep_fba_columns=True) # clean up fba, if specified in yaml if "clean_fba_df_fxn" in v: vLog.info("Cleaning up %s FlowByActivity", k) flows_mapped = dynamically_import_fxn( k, v["clean_fba_df_fxn"])(flows_mapped) # if activity_sets are specified in a file, call them here if 'activity_set_file' in v: aset_names = pd.read_csv(flowbysectoractivitysetspath + v['activity_set_file'], dtype=str) else: aset_names = None # master list of activity names read in from data source ml_act = [] # create dictionary of allocation datasets for different activities activities = v['activity_sets'] # subset activity data and allocate to sector for aset, attr in activities.items(): # subset by named activities if 'activity_set_file' in v: names = \ aset_names[aset_names['activity_set'] == aset]['name'] else: names = attr['names'] # to avoid double counting data from the same source, in # the event there are values in both the APB and ACB # columns, if an activity has already been read in and # allocated, remove that activity from the mapped flows # regardless of what activity set the data was read in flows_mapped = flows_mapped[~( (flows_mapped[fba_activity_fields[0]].isin(ml_act)) | (flows_mapped[fba_activity_fields[1]].isin(ml_act)) )].reset_index(drop=True) ml_act.extend(names) vLog.info("Preparing to handle %s in %s", aset, k) # subset fba data by activity flows_subset = flows_mapped[ (flows_mapped[fba_activity_fields[0]].isin(names)) | (flows_mapped[fba_activity_fields[1]].isin(names) )].reset_index(drop=True) # subset by flowname if exists if 'source_flows' in attr: flows_subset = flows_subset[flows_subset['FlowName'].isin( attr['source_flows'])] if len(flows_subset) == 0: log.warning(f"no data found for flows in {aset}") continue if len(flows_subset[flows_subset['FlowAmount'] != 0]) == 0: log.warning(f"all flow data for {aset} is 0") continue # if activities are sector-like, check sectors are valid if check_activities_sector_like(k): flows_subset2 = replace_naics_w_naics_from_another_year( flows_subset, method['target_sector_source']) # check impact on df FlowAmounts vLog.info( 'Calculate FlowAmount difference caused by ' 'replacing NAICS Codes with %s, saving ' 'difference in Validation log', method['target_sector_source'], ) calculate_flowamount_diff_between_dfs( flows_subset, flows_subset2) else: flows_subset2 = flows_subset.copy() # extract relevant geoscale data or aggregate existing data flows_subset_geo = subset_df_by_geoscale( flows_subset2, v['geoscale_to_use'], attr['allocation_from_scale']) # if loading data subnational geoscale, check for data loss if attr['allocation_from_scale'] != 'national': compare_geographic_totals(flows_subset_geo, flows_mapped, k, attr, aset, names) # Add sectors to df activity, depending on level # of specified sector aggregation log.info("Adding sectors to %s", k) flows_subset_wsec = add_sectors_to_flowbyactivity( flows_subset_geo, sectorsourcename=method['target_sector_source'], allocationmethod=attr['allocation_method']) # clean up fba with sectors, if specified in yaml if "clean_fba_w_sec_df_fxn" in v: vLog.info("Cleaning up %s FlowByActivity with sectors", k) flows_subset_wsec = dynamically_import_fxn( k, v["clean_fba_w_sec_df_fxn"])(flows_subset_wsec, attr=attr, method=method) # rename SourceName to MetaSources and drop columns flows_mapped_wsec = flows_subset_wsec.\ rename(columns={'SourceName': 'MetaSources'}).\ drop(columns=['FlowName', 'Compartment']) # if allocation method is "direct", then no need # to create alloc ratios, else need to use allocation # dataframe to create sector allocation ratios if attr['allocation_method'] == 'direct': fbs = direct_allocation_method(flows_mapped_wsec, k, names, method) # if allocation method for an activity set requires a specific # function due to the complicated nature # of the allocation, call on function here elif attr['allocation_method'] == 'allocation_function': fbs = function_allocation_method(flows_mapped_wsec, k, names, attr, fbs_list) else: fbs = dataset_allocation_method(flows_mapped_wsec, attr, names, method, k, v, aset, aset_names, download_FBA_if_missing) # drop rows where flowamount = 0 # (although this includes dropping suppressed data) fbs = fbs[fbs['FlowAmount'] != 0].reset_index(drop=True) # define grouping columns dependent on sectors # being activity-like or not if check_activities_sector_like(k) is False: groupingcols = fbs_grouping_fields_w_activities groupingdict = flow_by_sector_fields_w_activity else: groupingcols = fbs_default_grouping_fields groupingdict = flow_by_sector_fields # clean df fbs = clean_df(fbs, groupingdict, fbs_fill_na_dict) # aggregate df geographically, if necessary log.info("Aggregating flowbysector to %s level", method['target_geoscale']) # determine from scale if fips_number_key[v['geoscale_to_use']] <\ fips_number_key[attr['allocation_from_scale']]: from_scale = v['geoscale_to_use'] else: from_scale = attr['allocation_from_scale'] fbs_geo_agg = agg_by_geoscale(fbs, from_scale, method['target_geoscale'], groupingcols) # aggregate data to every sector level log.info("Aggregating flowbysector to all sector levels") fbs_sec_agg = sector_aggregation(fbs_geo_agg, groupingcols) # add missing naics5/6 when only one naics5/6 # associated with a naics4 fbs_agg = sector_disaggregation(fbs_sec_agg) # check if any sector information is lost before reaching # the target sector length, if so, # allocate values equally to disaggregated sectors vLog.info( 'Searching for and allocating FlowAmounts for any parent ' 'NAICS that were dropped in the subset to ' '%s child NAICS', method['target_sector_level']) fbs_agg_2 = equally_allocate_parent_to_child_naics( fbs_agg, method['target_sector_level']) # compare flowbysector with flowbyactivity compare_activity_to_sector_flowamounts(flows_mapped_wsec, fbs_agg_2, aset, k, method) # return sector level specified in method yaml # load the crosswalk linking sector lengths sector_list = get_sector_list(method['target_sector_level']) # subset df, necessary because not all of the sectors are # NAICS and can get duplicate rows fbs_1 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isin(sector_list)) & (fbs_agg_2[fbs_activity_fields[1]].isin(sector_list))].\ reset_index(drop=True) fbs_2 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isin(sector_list)) & (fbs_agg_2[fbs_activity_fields[1]].isnull())].\ reset_index(drop=True) fbs_3 = fbs_agg_2.loc[ (fbs_agg_2[fbs_activity_fields[0]].isnull()) & (fbs_agg_2[fbs_activity_fields[1]].isin(sector_list))].\ reset_index(drop=True) fbs_sector_subset = pd.concat([fbs_1, fbs_2, fbs_3]) # drop activity columns fbs_sector_subset = fbs_sector_subset.drop( ['ActivityProducedBy', 'ActivityConsumedBy'], axis=1, errors='ignore') # save comparison of FBA total to FBS total for an activity set compare_fba_geo_subset_and_fbs_output_totals( flows_subset_geo, fbs_sector_subset, aset, k, v, attr, method) log.info("Completed flowbysector for %s", aset) fbs_list.append(fbs_sector_subset) else: if 'clean_fbs_df_fxn' in v: flows = dynamically_import_fxn(v["clean_fbs_df_fxn_source"], v["clean_fbs_df_fxn"])(flows) flows = update_geoscale(flows, method['target_geoscale']) # if the loaded flow dt is already in FBS format, # append directly to list of FBS log.info("Append %s to FBS list", k) # ensure correct field datatypes and add any missing fields flows = clean_df(flows, flow_by_sector_fields, fbs_fill_na_dict) fbs_list.append(flows) # create single df of all activities log.info("Concat data for all activities") fbss = pd.concat(fbs_list, ignore_index=True, sort=False) log.info("Clean final dataframe") # add missing fields, ensure correct data type, # add missing columns, reorder columns fbss = clean_df(fbss, flow_by_sector_fields, fbs_fill_na_dict) # prior to aggregating, replace MetaSources string with all sources # that share context/flowable/sector values fbss = harmonize_FBS_columns(fbss) # aggregate df as activities might have data for # the same specified sector length fbss = aggregator(fbss, fbs_default_grouping_fields) # sort df log.info("Sort and store dataframe") # ensure correct data types/order of columns fbss = clean_df(fbss, flow_by_sector_fields, fbs_fill_na_dict) fbss = fbss.sort_values( ['SectorProducedBy', 'SectorConsumedBy', 'Flowable', 'Context']).reset_index(drop=True) # check for negative flow amounts check_for_negative_flowamounts(fbss) # tmp reset data quality scores fbss = reset_fbs_dq_scores(fbss) # save parquet file meta = set_fb_meta(method_name, "FlowBySector") write_df_to_file(fbss, paths, meta) write_metadata(method_name, method, meta, "FlowBySector") # rename the log file saved to local directory rename_log_file(method_name, meta) log.info( 'See the Validation log for detailed assessment of ' 'model results in %s', logoutputpath)
def compare_fba_load_and_fbs_output_totals(fba_load, fbs_load, activity_set, source_name, method_name, attr, method, mapping_files): """ Function to compare the loaded flowbyactivity total with the final flowbysector output total :param df: :return: """ from flowsa.flowbyfunctions import subset_df_by_geoscale, sector_aggregation from flowsa.common import load_source_catalog from flowsa.mapping import map_elementary_flows log.info( 'Comparing loaded FlowByActivity FlowAmount total to subset FlowBySector FlowAmount total' ) # load source catalog cat = load_source_catalog() src_info = cat[source_name] # extract relevant geoscale data or aggregate existing data fba = subset_df_by_geoscale(fba_load, attr['allocation_from_scale'], method['target_geoscale']) # map loaded fba fba = map_elementary_flows(fba, mapping_files, keep_unmapped_rows=True) if src_info['sector-like_activities']: # if activities are sector-like, run sector aggregation and then subset df to only keep NAICS2 fba = fba[[ 'Class', 'FlowAmount', 'Unit', 'Context', 'ActivityProducedBy', 'ActivityConsumedBy', 'Location', 'LocationSystem' ]] # rename the activity cols to sector cols for purposes of aggregation fba = fba.rename( columns={ 'ActivityProducedBy': 'SectorProducedBy', 'ActivityConsumedBy': 'SectorConsumedBy' }) group_cols_agg = [ 'Class', 'Context', 'Unit', 'Location', 'LocationSystem', 'SectorProducedBy', 'SectorConsumedBy' ] fba = sector_aggregation(fba, group_cols_agg) # subset fba to only include NAICS2 fba = replace_NoneType_with_empty_cells(fba) fba = fba[fba['SectorConsumedBy'].apply(lambda x: len(x) == 2) | fba['SectorProducedBy'].apply(lambda x: len(x) == 2)] # subset/agg dfs col_subset = [ 'Class', 'FlowAmount', 'Unit', 'Context', 'Location', 'LocationSystem' ] group_cols = ['Class', 'Unit', 'Context', 'Location', 'LocationSystem'] # fba fba = fba[col_subset] fba_agg = aggregator(fba, group_cols).reset_index(drop=True) fba_agg.rename(columns={ 'FlowAmount': 'FBA_amount', 'Unit': 'FBA_unit' }, inplace=True) # fbs fbs = fbs_load[col_subset] fbs_agg = aggregator(fbs, group_cols) fbs_agg.rename(columns={ 'FlowAmount': 'FBS_amount', 'Unit': 'FBS_unit' }, inplace=True) try: # merge FBA and FBS totals df_merge = fba_agg.merge(fbs_agg, how='left') df_merge['FlowAmount_difference'] = df_merge['FBA_amount'] - df_merge[ 'FBS_amount'] df_merge['Percent_difference'] = (df_merge['FlowAmount_difference'] / df_merge['FBA_amount']) * 100 # reorder df_merge = df_merge[[ 'Class', 'Context', 'Location', 'LocationSystem', 'FBA_amount', 'FBA_unit', 'FBS_amount', 'FBS_unit', 'FlowAmount_difference', 'Percent_difference' ]] df_merge = replace_NoneType_with_empty_cells(df_merge) # list of contexts context_list = df_merge['Context'].to_list() # loop through the contexts and print results of comparison for i in context_list: df_merge_subset = df_merge[df_merge['Context'] == i].reset_index( drop=True) diff_per = df_merge_subset['Percent_difference'][0] # make reporting more manageable if abs(diff_per) > 0.001: diff_per = round(diff_per, 2) else: diff_per = round(diff_per, 6) diff_units = df_merge_subset['FBS_unit'][0] if diff_per > 0: log.info('The total FlowBySector FlowAmount for ' + source_name + ' ' + activity_set + ' ' + i + ' is ' + str(abs(diff_per)) + '% less than the total FlowByActivity FlowAmount') else: log.info('The total FlowBySector FlowAmount for ' + source_name + ' ' + activity_set + ' ' + i + ' is ' + str(abs(diff_per)) + '% more than the total FlowByActivity FlowAmount') # save csv to output folder log.info( 'Save the comparison of FlowByActivity load to FlowBySector total FlowAmounts for ' + activity_set + ' in output folder') # output data at all sector lengths df_merge.to_csv(outputpath + "FlowBySectorMethodAnalysis/" + method_name + '_' + source_name + "_FBA_total_to_FBS_total_FlowAmount_comparison_" + activity_set + ".csv", index=False) except: log.info( 'Error occured when comparing total FlowAmounts for FlowByActivity and FlowBySector' ) return None