Download column order completed (#1077)

* Download column order completed

* Kameron changes

* Lucas and Beth column order changes

* cdc_places update

* passing score

* pandas error

* checkpoint

* score passing

* rounding complete - percentages still showing one decimal

* fixing tests

* fixing percentages

* updating comment

* int percentages! 🎉🎉

* forgot to pass back to df

* passing tests

Co-authored-by: lucasmbrown-usds <lucas.m.brown@omb.eop.gov>

data/data-pipeline/.vscode/launch.json

@@ -13,6 +13,15 @@
         "score-run"
       ]
     },
+    {
+      "name": "Generate Score Post",
+      "type": "python",
+      "request": "launch",
+      "module": "data_pipeline.application",
+      "args": [
+        "generate-score-post"
+      ]
+    },
     {
       "name": "Data Cleanup",
       "type": "python",

data/data-pipeline/data_pipeline/etl/score/constants.py

@@ -63,6 +63,17 @@ SCORE_DOWNLOADABLE_ZIP_FILE_PATH = (
 # Column subsets
 CENSUS_COUNTIES_COLUMNS = ["USPS", "GEOID", "NAME"]
 
+# Percent prefixes for rounding
+PERCENT_PREFIXES_SUFFIXES = [
+    "Percent",
+    "percent",
+    "Percentage",
+    "Energy burden",
+    "loss rate",
+    "greater than or equal to 18 years",
+    field_names.PERCENTILE_FIELD_SUFFIX,
+]
+
 TILES_ROUND_NUM_DECIMALS = 2
 # Tiles data: full field name, tile index name
 TILES_SCORE_COLUMNS = {
@@ -191,91 +202,88 @@ DOWNLOADABLE_SCORE_COLUMNS = [
     field_names.GEOID_TRACT_FIELD,
     field_names.COUNTY_FIELD,
     field_names.STATE_FIELD,
+    field_names.THRESHOLD_COUNT,
     field_names.SCORE_L_COMMUNITIES,
     field_names.TOTAL_POP_FIELD,
     field_names.FPL_200_SERIES,
-    field_names.POVERTY_LESS_THAN_200_FPL_FIELD,
+    field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD,
-    field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-    + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD,
     field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD,
+    field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD,
-    field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD,
+    field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD,
     field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD,
+    field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD,
-    field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD,
+    field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD,
     field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD,
+    field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD,
-    field_names.ENERGY_BURDEN_FIELD,
-    field_names.ENERGY_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
     field_names.ENERGY_BURDEN_LOW_INCOME_FIELD,
-    field_names.PM25_FIELD,
+    field_names.ENERGY_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.ENERGY_BURDEN_FIELD,
     field_names.PM25_EXPOSURE_LOW_INCOME_FIELD,
-    field_names.DIESEL_FIELD,
+    field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.PM25_FIELD,
     field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD,
-    field_names.TRAFFIC_FIELD,
+    field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.DIESEL_FIELD,
     field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD,
-    field_names.HOUSING_BURDEN_FIELD,
+    field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.HOUSING_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.TRAFFIC_FIELD,
     field_names.HOUSING_BURDEN_LOW_INCOME_FIELD,
-    field_names.LEAD_PAINT_FIELD,
+    field_names.HOUSING_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.LEAD_PAINT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.HOUSING_BURDEN_FIELD,
     field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD,
-    field_names.MEDIAN_HOUSE_VALUE_FIELD,
+    field_names.LEAD_PAINT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.LEAD_PAINT_FIELD,
     field_names.MEDIAN_HOUSE_VALUE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.TSDF_FIELD,
+    field_names.MEDIAN_HOUSE_VALUE_FIELD,
-    field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
     field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD,
-    field_names.NPL_FIELD,
+    field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.TSDF_FIELD,
     field_names.SUPERFUND_LOW_INCOME_FIELD,
-    field_names.RMP_FIELD,
+    field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.NPL_FIELD,
     field_names.RMP_LOW_INCOME_FIELD,
-    field_names.WASTEWATER_FIELD,
+    field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.WASTEWATER_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.RMP_FIELD,
     field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD,
-    field_names.ASTHMA_FIELD,
+    field_names.WASTEWATER_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.ASTHMA_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.WASTEWATER_FIELD,
     field_names.ASTHMA_LOW_INCOME_FIELD,
-    field_names.DIABETES_FIELD,
+    field_names.ASTHMA_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.DIABETES_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.ASTHMA_FIELD,
     field_names.DIABETES_LOW_INCOME_FIELD,
-    field_names.HEART_DISEASE_FIELD,
+    field_names.DIABETES_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.HEART_DISEASE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.DIABETES_FIELD,
     field_names.HEART_DISEASE_LOW_INCOME_FIELD,
-    field_names.LIFE_EXPECTANCY_FIELD,
+    field_names.HEART_DISEASE_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.LOW_LIFE_EXPECTANCY_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.HEART_DISEASE_FIELD,
     field_names.LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD,
-    field_names.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD,
+    field_names.LOW_LIFE_EXPECTANCY_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.LIFE_EXPECTANCY_FIELD,
+    field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
     field_names.LOW_MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
+    field_names.MEDIAN_INCOME_AS_PERCENT_OF_AMI_FIELD,
-    field_names.LINGUISTIC_ISO_FIELD,
     field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD,
-    field_names.UNEMPLOYMENT_FIELD,
-    field_names.UNEMPLOYMENT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
     field_names.LINGUISTIC_ISO_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.POVERTY_LESS_THAN_100_FPL_FIELD,
+    field_names.LINGUISTIC_ISO_FIELD,
+    field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
+    field_names.UNEMPLOYMENT_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.UNEMPLOYMENT_FIELD,
+    field_names.POVERTY_LOW_HS_EDUCATION_FIELD,
+    field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+    + field_names.PERCENTILE_FIELD_SUFFIX,
     field_names.POVERTY_LESS_THAN_100_FPL_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.POVERTY_LOW_HS_EDUCATION_FIELD,
+    field_names.POVERTY_LESS_THAN_200_FPL_FIELD,
-    field_names.HIGH_SCHOOL_ED_FIELD,
+    field_names.POVERTY_LESS_THAN_100_FPL_FIELD,
     field_names.HIGH_SCHOOL_ED_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
-    field_names.LOW_HS_EDUCATION_FIELD,
+    field_names.HIGH_SCHOOL_ED_FIELD,
-    field_names.THRESHOLD_COUNT,
-    field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
     field_names.COMBINED_UNEMPLOYMENT_2010,
-    field_names.CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009,
     field_names.COMBINED_POVERTY_LESS_THAN_100_FPL_FIELD_2010,
     field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
     field_names.ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD,
     field_names.ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
-    field_names.ISLAND_AREAS_LOW_HS_EDUCATION_FIELD,
 ]

data/data-pipeline/data_pipeline/etl/score/etl_score_post.py

@@ -1,5 +1,7 @@
 from pathlib import Path
 import json
+from numpy import float64
+import numpy as np
 import pandas as pd
 
 from data_pipeline.etl.base import ExtractTransformLoad
@@ -129,7 +131,7 @@ class PostScoreETL(ExtractTransformLoad):
         new_df = initial_states_df.rename(
             columns={
                 "fips": "State Code",
-                "state_name": "State Name",
+                "state_name": field_names.STATE_FIELD,
                 "state_abbreviation": "State Abbreviation",
             }
         )
@@ -206,7 +208,9 @@ class PostScoreETL(ExtractTransformLoad):
         tiles_score_column_titles = list(constants.TILES_SCORE_COLUMNS.keys())
 
         # filter the columns on full score
-        score_tiles = score_county_state_merged_df[tiles_score_column_titles]
+        score_tiles = score_county_state_merged_df[
+            tiles_score_column_titles
+        ].copy()
 
         score_tiles[constants.TILES_SCORE_FLOAT_COLUMNS] = score_tiles[
             constants.TILES_SCORE_FLOAT_COLUMNS
@@ -238,9 +242,31 @@ class PostScoreETL(ExtractTransformLoad):
     def _create_downloadable_data(
         self, score_county_state_merged_df: pd.DataFrame
     ) -> pd.DataFrame:
-        return score_county_state_merged_df[
+        df = score_county_state_merged_df[
             constants.DOWNLOADABLE_SCORE_COLUMNS
-        ]
+        ].copy(deep=True)
+
+        df_of_float_columns = df.select_dtypes(include=["float64"])
+
+        for column in df_of_float_columns.columns:
+            # TODO: create a schema for fields to make it more explicit and safe which
+            #  fields are percentages.
+            if any(x in column for x in constants.PERCENT_PREFIXES_SUFFIXES):
+                # Convert percentages from fractions between 0 and 1 to an integer
+                # from 0 to 100.
+                df_100 = df[column] * 100
+                df_int = np.floor(
+                    pd.to_numeric(df_100, errors="coerce")
+                ).astype("Int64")
+                df[column] = df_int
+            else:
+                # Round all other floats.
+                df[column] = floor_series(
+                    series=df[column].astype(float64),
+                    number_of_decimals=constants.TILES_ROUND_NUM_DECIMALS,
+                )
+
+        return df
 
     def transform(self) -> None:
         logger.info("Transforming data sources for Score + County CSVs")
@@ -297,7 +323,7 @@ class PostScoreETL(ExtractTransformLoad):
         # Rename score column
         downloadable_df_copy = downloadable_df.rename(
             columns={
-                field_names.SCORE_L_COMMUNITIES: "Community of focus (v0.1)"
+                field_names.SCORE_L_COMMUNITIES: "Identified as disadvantaged (v0.1)"
             },
             inplace=False,
         )

data/data-pipeline/data_pipeline/etl/score/tests/conftest.py

@@ -87,7 +87,7 @@ def states_transformed_expected():
     return pd.DataFrame.from_dict(
         data={
             "State Code": pd.Series(["01", "02", "04"], dtype="string"),
-            "State Name": pd.Series(
+            "State/Territory": pd.Series(
                 ["Alabama", "Alaska", "Arizona"], dtype="object"
             ),
             "State Abbreviation": pd.Series(["AL", "AK", "AZ"], dtype="string"),

data/data-pipeline/data_pipeline/etl/sources/cdc_places/etl.py

@@ -2,6 +2,7 @@ import pandas as pd
 
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.utils import get_module_logger, download_file_from_url
+from data_pipeline.score import field_names
 
 logger = get_module_logger(__name__)
 
@@ -49,6 +50,20 @@ class CDCPlacesETL(ExtractTransformLoad):
             values=self.CDC_VALUE_FIELD_NAME,
         )
 
+        # rename columns to be used in score
+        rename_fields = {
+            "Current asthma among adults aged >=18 years": field_names.ASTHMA_FIELD,
+            "Coronary heart disease among adults aged >=18 years": field_names.HEART_DISEASE_FIELD,
+            "Cancer (excluding skin cancer) among adults aged >=18 years": field_names.CANCER_FIELD,
+            "Diagnosed diabetes among adults aged >=18 years": field_names.DIABETES_FIELD,
+            "Physical health not good for >=14 days among adults aged >=18 years": field_names.PHYS_HEALTH_NOT_GOOD_FIELD,
+        }
+        self.df.rename(
+            columns=rename_fields,
+            inplace=True,
+            errors="raise",
+        )
+
         # Make the index (the census tract ID) a column, not the index.
         self.df.reset_index(inplace=True)
 

data/data-pipeline/data_pipeline/etl/sources/census_acs/etl.py

@@ -5,6 +5,7 @@ from data_pipeline.etl.sources.census_acs.etl_utils import (
     retrieve_census_acs_data,
 )
 from data_pipeline.utils import get_module_logger
+from data_pipeline.score import field_names
 
 logger = get_module_logger(__name__)
 
@@ -22,7 +23,7 @@ class CensusACSETL(ExtractTransformLoad):
             self.TOTAL_UNEMPLOYED_FIELD,
             self.TOTAL_IN_LABOR_FORCE,
         ]
-        self.UNEMPLOYED_FIELD_NAME = "Unemployed civilians (percent)"
+        self.UNEMPLOYED_FIELD_NAME = "Unemployment (percent)"
 
         self.LINGUISTIC_ISOLATION_FIELD_NAME = "Linguistic isolation (percent)"
         self.LINGUISTIC_ISOLATION_TOTAL_FIELD_NAME = (
@@ -353,18 +354,29 @@ class CensusACSETL(ExtractTransformLoad):
             + df[self.COLLEGE_ATTENDANCE_FEMALE_ENROLLED_PRIVATE]
         ) / df[self.COLLEGE_ATTENDANCE_TOTAL_POPULATION_ASKED]
 
+        # strip columns
+        df = df[self.COLUMNS_TO_KEEP]
+
         # Save results to self.
         self.df = df
 
+        # rename columns to be used in score
+        rename_fields = {
+            "Percent of individuals < 200% Federal Poverty Line": field_names.POVERTY_LESS_THAN_200_FPL_FIELD,
+        }
+        self.df.rename(
+            columns=rename_fields,
+            inplace=True,
+            errors="raise",
+        )
+
     def load(self) -> None:
         logger.info("Saving Census ACS Data")
 
         # mkdir census
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
 
-        self.df[self.COLUMNS_TO_KEEP].to_csv(
+        self.df.to_csv(path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False)
-            path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False
-        )
 
     def validate(self) -> None:
         logger.info("Validating Census ACS Data")

data/data-pipeline/data_pipeline/etl/sources/census_acs_2010/etl.py

@@ -5,6 +5,7 @@ from data_pipeline.etl.sources.census_acs.etl_utils import (
     retrieve_census_acs_data,
 )
 from data_pipeline.utils import get_module_logger
+from data_pipeline.score import field_names
 
 logger = get_module_logger(__name__)
 
@@ -73,7 +74,7 @@ class CensusACS2010ETL(ExtractTransformLoad):
             self.EMPLOYMENT_COLLEGE_IN_LABOR_FORCE,
         ]
 
-        self.UNEMPLOYED_FIELD_NAME = "Unemployed civilians (percent)"
+        self.UNEMPLOYED_FIELD_NAME = "Unemployment (percent)"
 
         self.POVERTY_FIELDS = [
             "C17002_001E",  # Estimate!!Total,
@@ -149,15 +150,6 @@ class CensusACS2010ETL(ExtractTransformLoad):
             + df["C17002_007E"]
         ) / df["C17002_001E"]
 
-        # Save results to self.
-        self.df = df
-
-    def load(self) -> None:
-        logger.info("Saving Census ACS Data")
-
-        # mkdir census
-        self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
-
         columns_to_include = [
             self.GEOID_TRACT_FIELD_NAME,
             self.UNEMPLOYED_FIELD_NAME,
@@ -166,7 +158,7 @@ class CensusACS2010ETL(ExtractTransformLoad):
             self.POVERTY_LESS_THAN_200_PERCENT_FPL_FIELD_NAME,
         ]
 
-        output_df = self.df[columns_to_include]
+        output_df = df[columns_to_include]
 
         # Add the year to the end of every column, so when it's all joined in the
         # score df, it's obvious which year this data is from.
@@ -178,7 +170,26 @@ class CensusACS2010ETL(ExtractTransformLoad):
                     }
                 )
 
-        output_df.to_csv(path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False)
+        # rename columns to be used in score
+        rename_fields = {
+            "Percent of individuals < 100% Federal Poverty Line in 2010": field_names.CENSUS_POVERTY_LESS_THAN_100_FPL_FIELD_2010,
+        }
+        output_df.rename(
+            columns=rename_fields,
+            inplace=True,
+            errors="raise",
+        )
+
+        # Save results to self.
+        self.df = output_df
+
+    def load(self) -> None:
+        logger.info("Saving Census ACS Data")
+
+        # mkdir census
+        self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
+
+        self.df.to_csv(path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False)
 
     def validate(self) -> None:
         logger.info("Validating Census ACS Data")

data/data-pipeline/data_pipeline/etl/sources/census_decennial/etl.py

@@ -6,6 +6,7 @@ import pandas as pd
 
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.utils import get_module_logger
+from data_pipeline.score import field_names
 
 pd.options.mode.chained_assignment = "raise"
 
@@ -141,7 +142,9 @@ class CensusDecennialETL(ExtractTransformLoad):
             "PBG036014"  # Total!!Female!!In labor force!!Civilian!!Unemployed
         )
 
-        self.UNEMPLOYMENT_FIELD_NAME = "Unemployed civilians (percent) in 2009"
+        self.UNEMPLOYMENT_FIELD_NAME = (
+            field_names.CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009
+        )
 
         var_list = [
             self.MEDIAN_INCOME_FIELD,

data/data-pipeline/data_pipeline/score/field_names.py

@@ -6,7 +6,7 @@ TOP_25_PERCENTILE_SUFFIX = " (top 25th percentile)"
 
 # Geographic field names
 GEOID_TRACT_FIELD = "GEOID10_TRACT"
-STATE_FIELD = "State Name"
+STATE_FIELD = "State/Territory"
 COUNTY_FIELD = "County Name"
 
 # Score file field names
@@ -45,7 +45,7 @@ MEDIAN_HOUSE_VALUE_PERCENTILE = 90
 # Poverty / Income
 POVERTY_FIELD = "Poverty (Less than 200% of federal poverty line)"
 POVERTY_LESS_THAN_200_FPL_FIELD = (
-    "Percent of individuals < 200% Federal Poverty Line"
+    "Percent of individuals below 200% Federal Poverty Line"
 )
 POVERTY_LESS_THAN_150_FPL_FIELD = (
     "Percent of individuals < 150% Federal Poverty Line"
@@ -83,15 +83,15 @@ EXPECTED_POPULATION_LOSS_RATE_FIELD = (
 )
 
 # Environment
-DIESEL_FIELD = "Diesel particulate matter"
+DIESEL_FIELD = "Diesel particulate matter exposure"
-PM25_FIELD = "Particulate matter (PM2.5)"
+PM25_FIELD = "PM2.5 in the air"
 OZONE_FIELD = "Ozone"
 TRAFFIC_FIELD = "Traffic proximity and volume"
 LEAD_PAINT_FIELD = "Percent pre-1960s housing (lead paint indicator)"
 WASTEWATER_FIELD = "Wastewater discharge"
 AGGREGATION_POLLUTION_FIELD = "Pollution Burden"
 RMP_FIELD = "Proximity to Risk Management Plan (RMP) facilities"
-TSDF_FIELD = "Proximity to TSDF sites"
+TSDF_FIELD = "Proximity to hazardous waste sites"
 NPL_FIELD = "Proximity to NPL sites"
 AIR_TOXICS_CANCER_RISK_FIELD = "Air toxics cancer risk"
 RESPIRATORY_HAZARD_FIELD = "Respiratory hazard index"
@@ -106,22 +106,26 @@ HT_INDEX_FIELD = (
 ENERGY_BURDEN_FIELD = "Energy burden"
 
 # Health
-DIABETES_FIELD = "Diagnosed diabetes among adults aged >=18 years"
+DIABETES_FIELD = (
-ASTHMA_FIELD = "Current asthma among adults aged >=18 years"
+    "Diagnosed diabetes among adults aged greater than or equal to 18 years"
-HEART_DISEASE_FIELD = "Coronary heart disease among adults aged >=18 years"
+)
-CANCER_FIELD = "Cancer (excluding skin cancer) among adults aged >=18 years"
+ASTHMA_FIELD = (
+    "Current asthma among adults aged greater than or equal to 18 years"
+)
+HEART_DISEASE_FIELD = (
+    "Coronary heart disease among adults aged greater than or equal to 18 years"
+)
+CANCER_FIELD = "Cancer (excluding skin cancer) among adults aged greater than or equal to 18 years"
 HEALTH_INSURANCE_FIELD = (
     "Current lack of health insurance among adults aged 18-64 years"
 )
-PHYS_HEALTH_NOT_GOOD_FIELD = (
+PHYS_HEALTH_NOT_GOOD_FIELD = "Physical health not good for greater than or equal to 14 days among adults aged greater than or equal to 18 years"
-    "Physical health not good for >=14 days among adults aged >=18 years"
-)
 LIFE_EXPECTANCY_FIELD = "Life expectancy (years)"
 LOW_LIFE_EXPECTANCY_FIELD = "Low life expectancy"
 
 # Other Demographics
 TOTAL_POP_FIELD = "Total population"
-UNEMPLOYMENT_FIELD = "Unemployed civilians (percent)"
+UNEMPLOYMENT_FIELD = "Unemployment (percent)"
 LINGUISTIC_ISO_FIELD = "Linguistic isolation (percent)"
 HOUSEHOLDS_LINGUISTIC_ISO_FIELD = (
     "Percent of households in linguistic isolation"
@@ -139,25 +143,25 @@ CENSUS_DECENNIAL_POVERTY_LESS_THAN_100_FPL_FIELD_2009 = (
     "Percentage households below 100% of federal poverty line in 2009"
 )
 CENSUS_DECENNIAL_HIGH_SCHOOL_ED_FIELD_2009 = "Percent individuals age 25 or over with less than high school degree in 2009"
-CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009 = (
+CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009 = "Unemployment (percent) in 2009"
-    "Unemployed civilians (percent) in 2009"
-)
 CENSUS_DECENNIAL_TOTAL_POPULATION_FIELD_2009 = "Total population in 2009"
 CENSUS_DECENNIAL_AREA_MEDIAN_INCOME_PERCENT_FIELD_2009 = (
     "Median household income as a percent of territory median income in 2009"
 )
 LOW_CENSUS_DECENNIAL_AREA_MEDIAN_INCOME_PERCENT_FIELD_2009 = "Low median household income as a percent of territory median income in 2009"
 # Fields from 2010 ACS (loaded for comparison with the territories)
-CENSUS_UNEMPLOYMENT_FIELD_2010 = "Unemployed civilians (percent) in 2010"
+CENSUS_UNEMPLOYMENT_FIELD_2010 = "Unemployment (percent) in 2010"
 CENSUS_POVERTY_LESS_THAN_100_FPL_FIELD_2010 = (
-    "Percent of individuals < 100% Federal Poverty Line in 2010"
+    "Percent of individuals less than 100% Federal Poverty Line in 2010"
 )
 
 # Combined fields that merge island areas and states data
 COMBINED_CENSUS_TOTAL_POPULATION_2010 = (
     "Total population in 2009 (island areas) and 2019 (states and PR)"
 )
-COMBINED_UNEMPLOYMENT_2010 = "Unemployed civilians (percent) in 2009 (island areas) and 2010 (states and PR)"
+COMBINED_UNEMPLOYMENT_2010 = (
+    "Unemployment (percent) in 2009 (island areas) and 2010 (states and PR)"
+)
 COMBINED_POVERTY_LESS_THAN_100_FPL_FIELD_2010 = (
     "Percentage households below 100% of federal poverty line in 2009 (island areas) "
     "and 2010 (states and PR)"
@@ -259,66 +263,77 @@ TRANSPORTATION_COSTS = "Transportation Costs"
 #####
 # Names for individual factors being exceeded
 # Climate Change
-EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected population loss rate and is low income"
+EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD = (
-EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected agriculture loss rate and is low income"
+    f"Greater than or equal to the {PERCENTILE}th percentile"
-EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected building loss rate and is low income"
+    f" for expected population loss rate and is low income?"
+)
+EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile"
+    f" for expected agriculture loss rate and is low income?"
+)
+EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile"
+    f" for expected building loss rate and is low income?"
+)
 
 # Clean energy and efficiency
-PM25_EXPOSURE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for PM2.5 exposure and is low income"
+PM25_EXPOSURE_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for PM2.5 exposure and is low income?"
-ENERGY_BURDEN_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for energy burden and is low income"
+ENERGY_BURDEN_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for energy burden and is low income?"
 
 # Clean transportation
-DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for diesel particulate matter and is low income"
+DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD = (
-TRAFFIC_PROXIMITY_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for traffic proximity and is low income"
+    f"Greater than or equal to the {PERCENTILE}th percentile for "
+    "diesel particulate matter and is low income?"
+)
+TRAFFIC_PROXIMITY_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for traffic proximity and is low income?"
 
 # Affordable and Sustainable Housing
 LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for lead paint and"
+    f"Greater than or equal to the {PERCENTILE}th percentile for lead paint and"
     f" the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th "
-    f"percentile and is low income"
+    f"percentile and is low income?"
 )
-HOUSING_BURDEN_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for housing burden and is low income"
+HOUSING_BURDEN_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for housing burden and is low income?"
 
 # Remediation and Reduction of Legacy Pollution
-RMP_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for proximity to RMP sites and is low income"
+RMP_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for proximity to RMP sites and is low income?"
-SUPERFUND_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for proximity to superfund sites and is low income"
+SUPERFUND_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for proximity to superfund sites and is low income?"
-HAZARDOUS_WASTE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for proximity to hazardous waste facilities and is low income"
+HAZARDOUS_WASTE_LOW_INCOME_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile"
+    f" for proximity to hazardous waste facilities and is low income?"
+)
 
 # Critical Clean Water and Waste Infrastructure
-WASTEWATER_DISCHARGE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for wastewater discharge and is low income"
+WASTEWATER_DISCHARGE_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for wastewater discharge and is low income?"
 
 # Health Burdens
-DIABETES_LOW_INCOME_FIELD = (
+DIABETES_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for diabetes and is low income?"
-    f"At or above the {PERCENTILE}th percentile for diabetes and is low income"
+ASTHMA_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for asthma and is low income?"
-)
+HEART_DISEASE_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for heart disease and is low income?"
-ASTHMA_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for asthma and is low income"
-)
-HEART_DISEASE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for heart disease and is low income"
 
 LOW_LIFE_EXPECTANCY_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile "
+    f"Greater than or equal to the {PERCENTILE}th percentile "
-    f"for low life expectancy and is low income"
+    f"for low life expectancy and is low income?"
 )
 
 # Workforce
 UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for unemployment"
+    f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
     " and has low HS education"
 )
 
 LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for households in linguistic isolation"
+    f"Greater than or equal to the {PERCENTILE}th percentile for households in linguistic isolation"
     " and has low HS education"
 )
 
 POVERTY_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
+    f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
     " and has low HS education"
 )
 
 LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for low median household income as a "
+    f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
     f"percent of area median income and has low HS education"
 )
 
@@ -327,17 +342,17 @@ LOW_HS_EDUCATION_FIELD = "Low high school education"
 # Workforce for island areas
 ISLAND_AREAS_SUFFIX = " in 2009 (island areas)"
 ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for unemployment"
+    f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
     f" and has low HS education{ISLAND_AREAS_SUFFIX}"
 )
 
 ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
+    f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
     f" and has low HS education{ISLAND_AREAS_SUFFIX}"
 )
 
 ISLAND_AREAS_LOW_MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for low median household income as a "
+    f"Greater than or equal to the {PERCENTILE}th percentile for low median household income as a "
     f"percent of area median income"
     f" and has low HS education{ISLAND_AREAS_SUFFIX}"
 )
@@ -348,27 +363,27 @@ ISLAND_AREAS_LOW_HS_EDUCATION_FIELD = (
 
 # Not currently used in a factor
 EXTREME_HEAT_MEDIAN_HOUSE_VALUE_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for summer days above 90F and "
+    f"Greater than or equal to the {PERCENTILE}th percentile for summer days above 90F and "
     f"the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th "
-    f"percentile and is low income"
+    f"percentile and is low income?"
 )
 IMPENETRABLE_SURFACES_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for impenetrable surfaces and is low "
+    f"Greater than or equal to the {PERCENTILE}th percentile for impenetrable surfaces and is low "
     f"income"
 )
-AIR_TOXICS_CANCER_RISK_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for air toxics cancer risk and is low income"
+AIR_TOXICS_CANCER_RISK_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for air toxics cancer risk and is low income?"
-RESPIRATORY_HAZARD_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for respiratory hazard index and is low income"
+RESPIRATORY_HAZARD_LOW_INCOME_FIELD = f"Greater than or equal to the {PERCENTILE}th percentile for respiratory hazard index and is low income?"
 HEALTHY_FOOD_LOW_INCOME_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for low "
+    f"Greater than or equal to the {PERCENTILE}th percentile for low "
-    f"access to healthy food and is low income"
+    f"access to healthy food and is low income?"
 )
 LOW_READING_LOW_HS_EDUCATION_FIELD = (
-    f"At or above the {PERCENTILE}th percentile for low 3rd grade reading proficiency"
+    f"Greater than or equal to the {PERCENTILE}th percentile for low 3rd grade reading proficiency"
     " and has low HS education"
 )
 
 THRESHOLD_COUNT = "Total threshold criteria exceeded"
 
-FPL_200_SERIES = "Is low income"
+FPL_200_SERIES = "Is low income?"
 # End of names for individual factors being exceeded
 ####