Merge branch 'usds:main' into main

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

@@ -2,6 +2,7 @@ from pathlib import Path
 import pandas as pd
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.utils import get_module_logger, zip_files
+from data_pipeline.score import field_names
 
 
 from data_pipeline.etl.sources.census.etl_utils import (
@@ -179,7 +180,9 @@ class PostScoreETL(ExtractTransformLoad):
         )
 
         # list the null score tracts
-        null_tract_df = merged_df[merged_df["Score E (percentile)"].isnull()]
+        null_tract_df = merged_df[
+            merged_df[field_names.SCORE_L_COMMUNITIES].isnull()
+        ]
 
         # subtract data sets
         # this follows the XOR pattern outlined here:
@@ -267,7 +270,9 @@ class PostScoreETL(ExtractTransformLoad):
 
         # Rename score column
         downloadable_df_copy = downloadable_df.rename(
-            columns={"Score G (communities)": "Community of focus (v0.1)"},
+            columns={
+                field_names.SCORE_L_COMMUNITIES: "Community of focus (v0.1)"
+            },
             inplace=False,
         )
 

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

@@ -114,6 +114,46 @@ class CensusACSETL(ExtractTransformLoad):
         )
         self.HIGH_SCHOOL_ED_FIELD = "Percent individuals age 25 or over with less than high school degree"
 
+        self.RE_FIELDS = [
+            "B02001_001E",
+            "B02001_002E",
+            "B02001_003E",
+            "B02001_004E",
+            "B02001_005E",
+            "B02001_006E",
+            "B02001_007E",
+            "B02001_008E",
+            "B02001_009E",
+            "B02001_010E",
+            "B03002_001E",
+            "B03002_003E",
+            "B03003_001E",
+            "B03003_003E",
+        ]
+
+        # Name output demographics fields.
+        self.BLACK_FIELD_NAME = "Black or African American alone"
+        self.AMERICAN_INDIAN_FIELD_NAME = (
+            "American Indian and Alaska Native alone"
+        )
+        self.ASIAN_FIELD_NAME = "Asian alone"
+        self.HAWAIIAN_FIELD_NAME = "Native Hawaiian and Other Pacific alone"
+        self.TWO_OR_MORE_RACES_FIELD_NAME = "Two or more races"
+        self.NON_HISPANIC_WHITE_FIELD_NAME = "Non-Hispanic White"
+        self.HISPANIC_FIELD_NAME = "Hispanic or Latino"
+
+        self.RE_OUTPUT_FIELDS = [
+            self.BLACK_FIELD_NAME,
+            self.AMERICAN_INDIAN_FIELD_NAME,
+            self.ASIAN_FIELD_NAME,
+            self.HAWAIIAN_FIELD_NAME,
+            self.TWO_OR_MORE_RACES_FIELD_NAME,
+            self.NON_HISPANIC_WHITE_FIELD_NAME,
+            self.HISPANIC_FIELD_NAME,
+        ]
+
+        self.PERCENT_PREFIX = "Percent "
+
         self.STATE_GEOID_FIELD_NAME = "GEOID2"
 
         self.df: pd.DataFrame
@@ -131,6 +171,7 @@ class CensusACSETL(ExtractTransformLoad):
             + self.LINGUISTIC_ISOLATION_FIELDS
             + self.POVERTY_FIELDS
             + self.EDUCATIONAL_FIELDS
+            + self.RE_FIELDS
         )
 
         self.df = retrieve_census_acs_data(
@@ -235,6 +276,38 @@ class CensusACSETL(ExtractTransformLoad):
             / df[self.EDUCATION_POPULATION_OVER_25]
         )
 
+        # Calculate some demographic information.
+        df[self.BLACK_FIELD_NAME] = df["B02001_003E"]
+        df[self.AMERICAN_INDIAN_FIELD_NAME] = df["B02001_004E"]
+        df[self.ASIAN_FIELD_NAME] = df["B02001_005E"]
+        df[self.HAWAIIAN_FIELD_NAME] = df["B02001_006E"]
+        df[self.TWO_OR_MORE_RACES_FIELD_NAME] = df["B02001_008E"]
+        df[self.NON_HISPANIC_WHITE_FIELD_NAME] = df["B03002_003E"]
+        df[self.HISPANIC_FIELD_NAME] = df["B03003_003E"]
+
+        # Calculate demographics as percent
+        df[self.PERCENT_PREFIX + self.BLACK_FIELD_NAME] = (
+            df["B02001_003E"] / df["B02001_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.AMERICAN_INDIAN_FIELD_NAME] = (
+            df["B02001_004E"] / df["B02001_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.ASIAN_FIELD_NAME] = (
+            df["B02001_005E"] / df["B02001_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.HAWAIIAN_FIELD_NAME] = (
+            df["B02001_006E"] / df["B02001_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.TWO_OR_MORE_RACES_FIELD_NAME] = (
+            df["B02001_008E"] / df["B02001_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.NON_HISPANIC_WHITE_FIELD_NAME] = (
+            df["B03002_003E"] / df["B03002_001E"]
+        )
+        df[self.PERCENT_PREFIX + self.HISPANIC_FIELD_NAME] = (
+            df["B03003_003E"] / df["B03003_001E"]
+        )
+
         # Save results to self.
         self.df = df
 
@@ -244,17 +317,21 @@ class CensusACSETL(ExtractTransformLoad):
         # mkdir census
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
 
-        columns_to_include = [
-            self.GEOID_TRACT_FIELD_NAME,
-            self.UNEMPLOYED_FIELD_NAME,
-            self.LINGUISTIC_ISOLATION_FIELD_NAME,
-            self.MEDIAN_INCOME_FIELD_NAME,
-            self.POVERTY_LESS_THAN_100_PERCENT_FPL_FIELD_NAME,
-            self.POVERTY_LESS_THAN_150_PERCENT_FPL_FIELD_NAME,
-            self.POVERTY_LESS_THAN_200_PERCENT_FPL_FIELD_NAME,
-            self.MEDIAN_HOUSE_VALUE_FIELD_NAME,
-            self.HIGH_SCHOOL_ED_FIELD,
-        ]
+        columns_to_include = (
+            [
+                self.GEOID_TRACT_FIELD_NAME,
+                self.UNEMPLOYED_FIELD_NAME,
+                self.LINGUISTIC_ISOLATION_FIELD_NAME,
+                self.MEDIAN_INCOME_FIELD_NAME,
+                self.POVERTY_LESS_THAN_100_PERCENT_FPL_FIELD_NAME,
+                self.POVERTY_LESS_THAN_150_PERCENT_FPL_FIELD_NAME,
+                self.POVERTY_LESS_THAN_200_PERCENT_FPL_FIELD_NAME,
+                self.MEDIAN_HOUSE_VALUE_FIELD_NAME,
+                self.HIGH_SCHOOL_ED_FIELD,
+            ]
+            + self.RE_OUTPUT_FIELDS
+            + [self.PERCENT_PREFIX + field for field in self.RE_OUTPUT_FIELDS]
+        )
 
         self.df[columns_to_include].to_csv(
             path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False

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

@@ -26,7 +26,7 @@ class DOEEnergyBurden(ExtractTransformLoad):
         # Constants for output
         self.COLUMNS_TO_KEEP = [
             self.GEOID_TRACT_FIELD_NAME,
-            self.REVISED_ENERGY_BURDEN_FIELD_NAME 
+            self.REVISED_ENERGY_BURDEN_FIELD_NAME,
         ]
 
         self.raw_df: pd.DataFrame
@@ -57,7 +57,7 @@ class DOEEnergyBurden(ExtractTransformLoad):
 
         output_df = self.raw_df.rename(
             columns={
-                self.INPUT_ENERGY_BURDEN_FIELD_NAME : self.REVISED_ENERGY_BURDEN_FIELD_NAME,
+                self.INPUT_ENERGY_BURDEN_FIELD_NAME: self.REVISED_ENERGY_BURDEN_FIELD_NAME,
                 self.TRACT_INPUT_COLUMN_NAME: self.GEOID_TRACT_FIELD_NAME,
             }
         )
@@ -79,7 +79,7 @@ class DOEEnergyBurden(ExtractTransformLoad):
 
     def load(self) -> None:
         logger.info("Saving DOE Energy Burden CSV")
-        
+
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
         self.output_df[self.COLUMNS_TO_KEEP].to_csv(
             path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False

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

@@ -31,6 +31,8 @@ L_WATER = "Water Factor (Definition L)"
 L_HEALTH = "Health Factor (Definition L)"
 L_WORKFORCE = "Workforce Factor (Definition L)"
 L_NON_WORKFORCE = "Any Non-Workforce Factor (Definition L)"
+PERCENTILE = 90
+MEDIAN_HOUSE_VALUE_PERCENTILE = 90
 
 # Poverty / Income
 POVERTY_FIELD = "Poverty (Less than 200% of federal poverty line)"
@@ -196,3 +198,63 @@ HOLC_GRADE_D_TRACT_PERCENT_FIELD: str = "Percent of tract that is HOLC Grade D"
 HOLC_GRADE_D_TRACT_20_PERCENT_FIELD: str = "Tract is >20% HOLC Grade D"
 HOLC_GRADE_D_TRACT_50_PERCENT_FIELD: str = "Tract is >50% HOLC Grade D"
 HOLC_GRADE_D_TRACT_75_PERCENT_FIELD: str = "Tract is >75% HOLC Grade D"
+
+
+# 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_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for expected agriculture loss rate and is low income"
+EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile 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"
+ENERGY_BURDEN_LOW_INCOME_FIELD = f"At or above 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"
+TRAFFIC_PROXIMITY_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for traffic proximity and is low income"
+# Affordable and Sustainable Housing
+LEAD_PAINT_MEDIAN_HOME_VALUE_LOW_INCOME_FIELD = (
+    f"At or above the {PERCENTILE}th percentile for lead paint and"
+    " the median house value is less than {MEDIAN_HOUSE_VALUE_PERCENTILE}th 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"
+# 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"
+SUPERFUND_LOW_INCOME_FIELD = f"At or above 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"
+# 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"
+# Health Burden
+DIABETES_LOW_INCOME_FIELD = (
+    f"At or above the {PERCENTILE}th percentile for diabetes 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"
+
+LIFE_EXPECTANCY_LOW_INCOME_FIELD = f"At or above the {PERCENTILE}th percentile for life expectancy and is low income"
+
+# Workforce
+UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD = (
+    f"At or above the {PERCENTILE}th percentile for unemployment"
+    " and low HS education"
+)
+
+LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD = (
+    f"At or above the {PERCENTILE}th percentile for households in linguistic isolation"
+    " and 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"
+    " and low HS education"
+)
+
+MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD = (
+    f"At or below the {PERCENTILE}th percentile for median income"
+    "  and low HS education"
+)
+
+THRESHOLD_COUNT = "Total threshold criteria exceeded"
+
+FPL_200_SERIES = "Is low income"

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

@@ -93,9 +93,38 @@ class ScoreL(Score):
 
         return df, threshold_column_name
 
+    def _create_low_income_threshold(self, df: pd.DataFrame) -> pd.Series:
+        """
+        Returns a pandas series (really a numpy array)
+        of booleans based on the condition of the FPL at 200%
+        is at or more than some established threshold
+        """
+        return (
+            df[
+                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.LOW_INCOME_THRESHOLD
+        )
+
+    def _increment_total_eligibility_exceeded(
+        self, columns_for_subset: list
+    ) -> None:
+        """
+        Increments the total eligible factors for a given tract
+        """
+
+        self.df[field_names.THRESHOLD_COUNT] += self.df[columns_for_subset].sum(
+            axis=1
+        )
+
     def add_columns(self) -> pd.DataFrame:
         logger.info("Adding Score L")
 
+        self.df[field_names.THRESHOLD_COUNT] = 0
+        self.df[field_names.FPL_200_SERIES] = self._create_low_income_threshold(
+            self.df
+        )
         self.df[field_names.L_CLIMATE] = self._climate_factor()
         self.df[field_names.L_ENERGY] = self._energy_factor()
         self.df[field_names.L_TRANSPORTATION] = self._transportation_factor()
@@ -143,37 +172,55 @@ class ScoreL(Score):
         # Low income: In 60th percentile or above for percent of block group population
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
-        climate_criteria = (
-            (
-                self.df[
-                    field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-        )
 
-        return (
+        climate_eligibility_columns = [
+            field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD,
+            field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD,
+            field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD,
+        ]
+
+        expected_population_loss_threshold = (
             self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+                field_names.EXPECTED_POPULATION_LOSS_RATE_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
             ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & climate_criteria
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        expected_agriculture_loss_threshold = (
+            self.df[
+                field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        expected_building_loss_threshold = (
+            self.df[
+                field_names.EXPECTED_BUILDING_LOSS_RATE_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        self.df[field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD] = (
+            expected_population_loss_threshold
+            & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self.df[field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_FIELD] = (
+            expected_agriculture_loss_threshold
+            & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self.df[field_names.EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD] = (
+            expected_building_loss_threshold
+            & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(climate_eligibility_columns)
+
+        return self.df[climate_eligibility_columns].any(axis="columns")
 
     def _energy_factor(self) -> bool:
         # In Xth percentile or above for DOE’s energy cost burden score (Source: LEAD Score)
@@ -181,26 +228,38 @@ class ScoreL(Score):
         # Low income: In 60th percentile or above for percent of block group population
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
-        energy_criteria = (
+
+        energy_eligibility_columns = [
+            field_names.PM25_EXPOSURE_LOW_INCOME_FIELD,
+            field_names.ENERGY_BURDEN_LOW_INCOME_FIELD,
+        ]
+
+        energy_burden_threshold = (
             self.df[
                 field_names.ENERGY_BURDEN_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
             ]
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-        ) | (
+        )
+
+        pm25_threshold = (
             self.df[
                 field_names.PM25_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
             ]
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
-        return (
-            self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-                + field_names.PERCENTILE_FIELD_SUFFIX
-            ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & energy_criteria
+        self.df[field_names.PM25_EXPOSURE_LOW_INCOME_FIELD] = (
+            pm25_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self.df[field_names.ENERGY_BURDEN_LOW_INCOME_FIELD] = (
+            energy_burden_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(energy_eligibility_columns)
+
+        return self.df[energy_eligibility_columns].any(axis="columns")
 
     def _transportation_factor(self) -> bool:
         # In Xth percentile or above for diesel particulate matter (Source: EPA National Air Toxics Assessment (NATA)
@@ -212,25 +271,39 @@ class ScoreL(Score):
         # Low income: In 60th percentile or above for percent of block group population
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
-        transportation_criteria = (
+
+        transportion_eligibility_columns = [
+            field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD,
+            field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD,
+        ]
+
+        diesel_threshold = (
             self.df[
                 field_names.DIESEL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
             ]
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-        ) | (
+        )
+
+        traffic_threshold = (
             self.df[
                 field_names.TRAFFIC_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
             ]
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
-        return (
-            self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-                + field_names.PERCENTILE_FIELD_SUFFIX
-            ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & transportation_criteria
+        self.df[field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_FIELD] = (
+            diesel_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self.df[field_names.TRAFFIC_PROXIMITY_LOW_INCOME_FIELD] = (
+            traffic_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(
+            transportion_eligibility_columns
+        )
+
+        return self.df[transportion_eligibility_columns].any(axis="columns")
 
     def _housing_factor(self) -> bool:
         # (
@@ -245,35 +318,47 @@ class ScoreL(Score):
         # Low income: In 60th percentile or above for percent of block group population
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
-        housing_criteria = (
-            (
-                self.df[
-                    field_names.LEAD_PAINT_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            & (
-                self.df[
-                    field_names.MEDIAN_HOUSE_VALUE_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                <= self.MEDIAN_HOUSE_VALUE_THRESHOLD
-            )
-        ) | (
+
+        housing_eligibility_columns = [
+            field_names.LEAD_PAINT_MEDIAN_HOME_VALUE_LOW_INCOME_FIELD,
+            field_names.HOUSING_BURDEN_LOW_INCOME_FIELD,
+        ]
+
+        lead_paint_median_house_hold_threshold = (
+            self.df[
+                field_names.LEAD_PAINT_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        ) & (
+            self.df[
+                field_names.MEDIAN_HOUSE_VALUE_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            <= self.MEDIAN_HOUSE_VALUE_THRESHOLD
+        )
+
+        housing_burden_threshold = (
             self.df[
                 field_names.HOUSING_BURDEN_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
             ]
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
-        return (
-            self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-                + field_names.PERCENTILE_FIELD_SUFFIX
-            ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & housing_criteria
+
+        # series by series indicators
+        self.df[field_names.LEAD_PAINT_MEDIAN_HOME_VALUE_LOW_INCOME_FIELD] = (
+            lead_paint_median_house_hold_threshold
+            & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self.df[field_names.HOUSING_BURDEN_LOW_INCOME_FIELD] = (
+            housing_burden_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(housing_eligibility_columns)
+
+        return self.df[housing_eligibility_columns].any(axis="columns")
 
     def _pollution_factor(self) -> bool:
         # Proximity to Risk Management Plan sites is > X
@@ -282,48 +367,54 @@ class ScoreL(Score):
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
 
-        pollution_criteria = (
-            (
-                self.df[
-                    field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
+        pollution_eligibility_columns = [
+            field_names.RMP_LOW_INCOME_FIELD,
+            field_names.SUPERFUND_LOW_INCOME_FIELD,
+            field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD,
+        ]
+
+        rmp_sites_threshold = (
+            self.df[field_names.RMP_FIELD + field_names.PERCENTILE_FIELD_SUFFIX]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
-        return pollution_criteria & (
-            self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-                + field_names.PERCENTILE_FIELD_SUFFIX
-            ]
-            >= self.LOW_INCOME_THRESHOLD
+        npl_sites_threshold = (
+            self.df[field_names.NPL_FIELD + field_names.PERCENTILE_FIELD_SUFFIX]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        tsdf_sites_threshold = (
+            self.df[
+                field_names.TSDF_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        # individual series-by-series
+        self.df[field_names.RMP_LOW_INCOME_FIELD] = (
+            rmp_sites_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+        self.df[field_names.SUPERFUND_LOW_INCOME_FIELD] = (
+            npl_sites_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+        self.df[field_names.HAZARDOUS_WASTE_LOW_INCOME_FIELD] = (
+            tsdf_sites_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(
+            pollution_eligibility_columns
+        )
+
+        return self.df[pollution_eligibility_columns].any(axis="columns")
+
     def _water_factor(self) -> bool:
         # In Xth percentile or above for wastewater discharge (Source: EPA Risk-Screening Environmental Indicators (RSEI) Model)
         # AND
         # Low income: In 60th percentile or above for percent of block group population
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
-        return (
-            self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
-                + field_names.PERCENTILE_FIELD_SUFFIX
-            ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & (
+
+        wastewater_threshold = (
             self.df[
                 field_names.WASTEWATER_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
@@ -331,6 +422,16 @@ class ScoreL(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD] = (
+            wastewater_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(
+            [field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD]
+        )
+
+        return self.df[field_names.WASTEWATER_DISCHARGE_LOW_INCOME_FIELD]
+
     def _health_factor(self) -> bool:
         # In Xth percentile or above for diabetes (Source: CDC Places)
         # or
@@ -344,45 +445,61 @@ class ScoreL(Score):
         # of households where household income is less than or equal to twice the federal
         # poverty level. Source: Census's American Community Survey]
 
-        health_criteria = (
-            (
-                self.df[
-                    field_names.DIABETES_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.ASTHMA_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.HEART_DISEASE_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.LIFE_EXPECTANCY_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                # Note: a high life expectancy is good, so take 1 minus the threshold to invert it,
-                # and then look for life expenctancies lower than that (not greater than).
-                <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-        )
-        return (
+        health_eligibility_columns = [
+            field_names.DIABETES_LOW_INCOME_FIELD,
+            field_names.ASTHMA_LOW_INCOME_FIELD,
+            field_names.HEART_DISEASE_LOW_INCOME_FIELD,
+            field_names.LIFE_EXPECTANCY_LOW_INCOME_FIELD,
+        ]
+
+        diabetes_threshold = (
             self.df[
-                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+                field_names.DIABETES_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        asthma_threshold = (
+            self.df[
+                field_names.ASTHMA_FIELD + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        heart_disease_threshold = (
+            self.df[
+                field_names.HEART_DISEASE_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
             ]
-            >= self.LOW_INCOME_THRESHOLD
-        ) & health_criteria
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        life_expectancy_threshold = (
+            self.df[
+                field_names.LIFE_EXPECTANCY_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            # Note: a high life expectancy is good, so take 1 minus the threshold to invert it,
+            # and then look for life expenctancies lower than that (not greater than).
+            <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        self.df[field_names.DIABETES_LOW_INCOME_FIELD] = (
+            diabetes_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+        self.df[field_names.ASTHMA_LOW_INCOME_FIELD] = (
+            asthma_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+        self.df[field_names.HEART_DISEASE_LOW_INCOME_FIELD] = (
+            heart_disease_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+        self.df[field_names.LIFE_EXPECTANCY_LOW_INCOME_FIELD] = (
+            life_expectancy_threshold & self.df[field_names.FPL_200_SERIES]
+        )
+
+        self._increment_total_eligibility_exceeded(health_eligibility_columns)
+
+        return self.df[health_eligibility_columns].any(axis="columns")
 
     def _workforce_factor(self) -> bool:
         # Where unemployment is above X%
@@ -395,42 +512,80 @@ class ScoreL(Score):
         # AND
         # Where the high school degree achievement rates for adults 25 years and older is less than 95%
         # (necessary to screen out university block groups)
-        workforce_criteria_for_states = (
-            (
-                self.df[
-                    field_names.UNEMPLOYMENT_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.MEDIAN_INCOME_PERCENT_AMI_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                # Note: a high median income as a % of AMI is good, so take 1 minus the threshold to invert it.
-                # and then look for median income lower than that (not greater than).
-                <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.POVERTY_LESS_THAN_100_FPL_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-            | (
-                self.df[
-                    field_names.LINGUISTIC_ISO_FIELD
-                    + field_names.PERCENTILE_FIELD_SUFFIX
-                ]
-                >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
-            )
-        )
-        workforce_combined_criteria_for_states = (
+
+        high_scool_achievement_rate_threshold = (
             self.df[field_names.HIGH_SCHOOL_ED_FIELD]
             >= self.LACK_OF_HIGH_SCHOOL_MINIMUM_THRESHOLD
-        ) & workforce_criteria_for_states
+        )
+
+        unemployment_threshold = (
+            self.df[
+                field_names.UNEMPLOYMENT_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        median_income_threshold = (
+            self.df[
+                field_names.MEDIAN_INCOME_PERCENT_AMI_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            # Note: a high median income as a % of AMI is good, so take 1 minus the threshold to invert it.
+            # and then look for median income lower than that (not greater than).
+            <= 1 - self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        linguistic_isolation_threshold = (
+            self.df[
+                field_names.LINGUISTIC_ISO_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        poverty_threshold = (
+            self.df[
+                field_names.POVERTY_LESS_THAN_100_FPL_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        self.df[field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD] = (
+            linguistic_isolation_threshold
+            & high_scool_achievement_rate_threshold
+        )
+
+        self.df[field_names.POVERTY_LOW_HS_EDUCATION_FIELD] = (
+            poverty_threshold & high_scool_achievement_rate_threshold
+        )
+
+        self.df[field_names.MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD] = (
+            median_income_threshold & high_scool_achievement_rate_threshold
+        )
+
+        self.df[field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD] = (
+            unemployment_threshold & high_scool_achievement_rate_threshold
+        )
+
+        # Workforce criteria for states fields that create indicator columns
+        # for each tract in order to indicate whether they met any of the four
+        # criteria. We will used this create individual indicator columns.
+        workforce_eligibility_columns = [
+            field_names.UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD,
+            field_names.POVERTY_LOW_HS_EDUCATION_FIELD,
+            field_names.LINGUISTIC_ISOLATION_LOW_HS_EDUCATION_FIELD,
+            field_names.MEDIAN_INCOME_LOW_HS_EDUCATION_FIELD,
+        ]
+
+        workforce_combined_criteria_for_states = self.df[
+            workforce_eligibility_columns
+        ].any(axis="columns")
+
+        self._increment_total_eligibility_exceeded(
+            workforce_eligibility_columns
+        )
 
         # Now, calculate workforce criteria for island territories.