def write_local_files_debug(self): """Downloads and writes the tables to the local file system as csv and json files. This is only for debugging/convenience, and should not be used in production.""" metadata = fetch_acs_metadata(self.base_acs_url) var_map = parse_acs_metadata(metadata, list(GROUPS.keys())) by_hisp_and_race_json = fetch_acs_group(self.base_acs_url, HISPANIC_BY_RACE_CONCEPT, var_map, 2, self.county_level) sex_by_age_frames = {} for concept in SEX_BY_AGE_CONCEPTS_TO_RACE: json_string = fetch_acs_group(self.base_acs_url, concept, var_map, 2, self.county_level) frame = gcs_to_bq_util.values_json_to_dataframe(json_string) sex_by_age_frames[concept] = update_col_types(frame) race_and_hispanic_frame = gcs_to_bq_util.values_json_to_dataframe( by_hisp_and_race_json) race_and_hispanic_frame = update_col_types(race_and_hispanic_frame) race_and_hispanic_frame = standardize_frame( race_and_hispanic_frame, get_vars_for_group(HISPANIC_BY_RACE_CONCEPT, var_map, 2), [HISPANIC_COL, RACE_COL], self.county_level, POPULATION_COL) frames = { self.get_table_name_by_race(): self.get_all_races_frame(race_and_hispanic_frame), self.get_table_name_by_sex_age_race(): self.get_sex_by_age_and_race(var_map, sex_by_age_frames) } for key, df in frames.items(): df.to_csv("table_" + key + ".csv", index=False) df.to_json("table_" + key + ".json", orient="records")
def upload_to_gcs(self, gcs_bucket): """Uploads population data from census to GCS bucket.""" metadata = fetch_acs_metadata(self.base_acs_url) var_map = parse_acs_metadata(metadata, list(GROUPS.keys())) concepts = list(SEX_BY_AGE_CONCEPTS_TO_RACE.keys()) concepts.append(HISPANIC_BY_RACE_CONCEPT) file_diff = False for concept in concepts: group_vars = get_vars_for_group(concept, var_map, 2) cols = list(group_vars.keys()) url_params = get_census_params(cols, self.county_level) concept_file_diff = url_file_to_gcs.url_file_to_gcs( self.base_acs_url, url_params, gcs_bucket, self.get_filename(concept)) file_diff = file_diff or concept_file_diff url_params = get_census_params([TOTAL_POP_VARIABLE_ID], self.county_level) next_file_diff = url_file_to_gcs.url_file_to_gcs( self.base_acs_url, url_params, gcs_bucket, self.add_filename_suffix(TOTAL_POP_VARIABLE_ID)) file_diff = file_diff or next_file_diff return file_diff
def testAcsMetadata(self): """Tests parsing ACS metadata and retrieving group variables from it""" metadata = census.parse_acs_metadata( self._fake_metadata, ["B02001", "B01001"]) self.assertEqual( "Estimate!!Total:!!Male:!!25 to 29 years", metadata["B01001_011E"]["label"]) self.assertEqual( "Estimate!!Total:!!Two or more races:", metadata["B02001_008E"]["label"]) # Wasn't specified in the groups to include. self.assertIsNone(metadata.get("B01001B_029E")) group_vars = census.get_vars_for_group("SEX BY AGE", metadata, 2) self.assertDictEqual({ "B01001_011E": ["Male", "25 to 29 years"], "B01001_012E": ["Male", "30 to 34 years"], "B01001_041E": ["Female", "55 to 59 years"], "B01001_042E": ["Female", "60 and 61 years"] }, group_vars) group_vars = census.get_vars_for_group("RACE", metadata, 1) self.assertDictEqual({ "B02001_005E": ["Asian alone"], "B02001_007E": ["Some other race alone"], "B02001_008E": ["Two or more races"] }, group_vars)
def testStandarizeFrameTwoDims(self): """Tests standardizing an ACS DataFrame""" metadata = census.parse_acs_metadata( self._fake_metadata, ["B02001", "B01001"]) group_vars = census.get_vars_for_group("SEX BY AGE", metadata, 2) df = gcs_to_bq_util.values_json_to_dataframe( json.dumps(self._fake_sex_by_age_data)) df = census.standardize_frame( df, group_vars, ["sex", "age"], False, "population") expected_df = gcs_to_bq_util.values_json_to_dataframe( json.dumps(self._expected_sex_by_age_data)).reset_index(drop=True) assert_frame_equal(expected_df, df)
def write_to_bq(self, dataset, gcs_bucket): """Writes population data to BigQuery from the provided GCS bucket dataset: The BigQuery dataset to write to gcs_bucket: The name of the gcs bucket to read the data from""" # TODO change this to have it read metadata from GCS bucket metadata = fetch_acs_metadata(self.base_acs_url) var_map = parse_acs_metadata(metadata, list(GROUPS.keys())) race_and_hispanic_frame = gcs_to_bq_util.load_values_as_dataframe( gcs_bucket, self.get_filename(HISPANIC_BY_RACE_CONCEPT)) race_and_hispanic_frame = update_col_types(race_and_hispanic_frame) race_and_hispanic_frame = standardize_frame( race_and_hispanic_frame, get_vars_for_group(HISPANIC_BY_RACE_CONCEPT, var_map, 2), [HISPANIC_COL, RACE_COL], self.county_level, POPULATION_COL) total_frame = gcs_to_bq_util.load_values_as_dataframe( gcs_bucket, self.add_filename_suffix(TOTAL_POP_VARIABLE_ID)) total_frame = update_col_types(total_frame) total_frame = standardize_frame( total_frame, {TOTAL_POP_VARIABLE_ID: ['Total']}, [RACE_OR_HISPANIC_COL], self.county_level, POPULATION_COL) sex_by_age_frames = {} for concept in SEX_BY_AGE_CONCEPTS_TO_RACE: sex_by_age_frame = gcs_to_bq_util.load_values_as_dataframe( gcs_bucket, self.get_filename(concept)) sex_by_age_frame = update_col_types(sex_by_age_frame) sex_by_age_frames[concept] = sex_by_age_frame frames = { self.get_table_name_by_race(): self.get_all_races_frame( race_and_hispanic_frame, total_frame), self.get_table_name_by_sex_age_race(): self.get_sex_by_age_and_race( var_map, sex_by_age_frames) } for table_name, df in frames.items(): # All breakdown columns are strings column_types = {c: 'STRING' for c in df.columns} column_types[POPULATION_COL] = 'INT64' gcs_to_bq_util.add_dataframe_to_bq( df, dataset, table_name, column_types=column_types)