Adding first street foundation data (#1823)

Adding FSF flood and wildfire risk datasets to the score.

data/data-pipeline/data_pipeline/content/config/csv.yml

@@ -272,3 +272,21 @@ fields:
   - score_name: Leaky underground storage tanks
     label: Leaky underground storage tanks
     format: float
+  - score_name: Share of properties at risk of flood in 30 years
+    label: Share of properties at risk of flood in 30 years
+    format: float
+  - score_name: Share of properties at risk of fire in 30 years
+    label: Share of properties at risk of fire in 30 years
+    format: float
+  - score_name: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years and is low income?
+    label: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years and is low income?
+    format: bool
+  - score_name: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years and is low income?
+    label: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years and is low income?
+    format: bool
+  - score_name: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years
+    label: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years
+    format: bool
+  - score_name: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years
+    label: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years
+    format: bool

data/data-pipeline/data_pipeline/content/config/excel.yml

@@ -276,3 +276,21 @@ sheets:
       - score_name: Greater than or equal to the 90th percentile for low median household income as a percent of area median income and has low HS education in 2009 (island areas)?
         label: Greater than or equal to the 90th percentile for low median household income as a percent of area median income and has low HS education in 2009 (island areas)?
         format: bool
+      - score_name: Share of properties at risk of flood in 30 years
+        label: Share of properties at risk of flood in 30 years
+        format: float
+      - score_name: Share of properties at risk of fire in 30 years
+        label: Share of properties at risk of fire in 30 years
+        format: float
+      - score_name: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years and is low income?
+        label: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years and is low income?
+        format: bool
+      - score_name: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years and is low income?
+        label: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years and is low income?
+        format: bool
+      - score_name: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years
+        label: Greater than or equal to the 90th percentile for share of properties at risk of flood in 30 years
+        format: bool
+      - score_name: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years
+        label: Greater than or equal to the 90th percentile for share of properties at risk of fire in 30 years
+        format: bool

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

@@ -34,6 +34,16 @@ DATASET_LIST = [
         "module_dir": "mapping_for_ej",
         "class_name": "MappingForEJETL",
     },
+    {
+        "name": "fsf_flood_risk",
+        "module_dir": "fsf_flood_risk",
+        "class_name": "FloodRiskETL",
+    },
+    {
+        "name": "fsf_wildfire_risk",
+        "module_dir": "fsf_wildfire_risk",
+        "class_name": "WildfireRiskETL",
+    },
     {
         "name": "ejscreen",
         "module_dir": "ejscreen",

data/data-pipeline/data_pipeline/etl/score/config/datasets.yml

@@ -157,6 +157,88 @@ datasets:
         include_in_tiles: true
         include_in_downloadable_files: true
 
+  - long_name: "First Street Foundation Flood Risk"
+    short_name: "FSF Flood Risk"
+    module_name: fsf_flood_risk
+    input_geoid_tract_field_name: "GEOID"
+    load_fields:
+      - short_name: "flood_eligible_properties"
+        df_field_name: "COUNT_PROPERTIES"
+        long_name: "Count of properties eligible for flood risk calculation within tract (floor of 250)" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "flood_risk_properties_today"
+        df_field_name: "PROPERTIES_AT_RISK_FROM_FLOODING_TODAY"
+        long_name: "Count of properties at risk of flood today" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "flood_risk_properties_30yrs"
+        df_field_name: "PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS"
+        long_name: "Count of properties at risk of flood in 30 years" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "flood_risk_share_today"
+        df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_TODAY"
+        long_name: "Share of properties at risk of flood today" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: true
+      - short_name: "flood_risk_share_30yrs"
+        df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS"
+        long_name: "Share of properties at risk of flood in 30 years" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: true
+
+  - long_name: "First Street Foundation Wildfire Risk"
+    short_name: "FSF Wildfire Risk"
+    module_name: fsf_wildfire_risk
+    input_geoid_tract_field_name: "GEOID"
+    load_fields:
+      - short_name: "fire_eligible_properties"
+        df_field_name: "COUNT_PROPERTIES"
+        long_name: "Count of properties eligible for wildfire risk calculation within tract (floor of 250)" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "fire_risk_properties_today"
+        df_field_name: "PROPERTIES_AT_RISK_FROM_FIRE_TODAY"
+        long_name: "Count of properties at risk of wildfire today" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "fire_risk_properties_30yrs"
+        df_field_name: "PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS"
+        long_name: "Count of properties at risk of wildfire in 30 years" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: false
+      - short_name: "fire_risk_share_today"
+        df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_TODAY"
+        long_name: "Share of properties at risk of fire today" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: true
+      - short_name: "fire_risk_share_30yrs"
+        df_field_name: "SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS"
+        long_name: "Share of properties at risk of fire in 30 years" 
+        field_type: float
+        include_in_tiles: false
+        include_in_downloadable_files: true
+        create_percentile: true
+
   - long_name: "DOT Travel Disadvantage Index"
     short_name: "DOT"
     module_name: "travel_composite"

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

@@ -293,12 +293,18 @@ TILES_SCORE_COLUMNS = {
     field_names.WORKFORCE_THRESHOLD_EXCEEDED: "M_WKFC_EOMI",
     # These are the booleans for socioeconomic indicators
     ## this measures low income boolean
-    field_names.FPL_200_SERIES: "FPL200S",
+    field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED: "FPL200S",
     ## Low high school for t&wd
     field_names.WORKFORCE_SOCIO_INDICATORS_EXCEEDED: "M_WKFC_EBSI",
     field_names.DOT_BURDEN_PCTILE_THRESHOLD: "TD_ET",
     field_names.DOT_TRAVEL_BURDEN_FIELD
-    + field_names.PERCENTILE_FIELD_SUFFIX: "TD_PFS"
+    + field_names.PERCENTILE_FIELD_SUFFIX: "TD_PFS",
+    field_names.FUTURE_FLOOD_RISK_FIELD
+    + field_names.PERCENTILE_FIELD_SUFFIX: "FLD_PFS",
+    field_names.FUTURE_WILDFIRE_RISK_FIELD
+    + field_names.PERCENTILE_FIELD_SUFFIX: "WF_PFS",
+    field_names.HIGH_FUTURE_FLOOD_RISK_FIELD: "FLD_ET",
+    field_names.HIGH_FUTURE_WILDFIRE_RISK_FIELD: "WF_ET",
     ## FPL 200 and low higher ed for all others should no longer be M_EBSI, but rather
     ## FPL_200 (there is no higher ed in narwhal)
 }
@@ -352,4 +358,7 @@ TILES_SCORE_FLOAT_COLUMNS = [
     field_names.COLLEGE_NON_ATTENDANCE_FIELD,
     field_names.COLLEGE_ATTENDANCE_FIELD,
     field_names.DOT_TRAVEL_BURDEN_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.FUTURE_FLOOD_RISK_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.FUTURE_WILDFIRE_RISK_FIELD
+    + field_names.PERCENTILE_FIELD_SUFFIX,
 ]

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

@@ -11,6 +11,10 @@ from data_pipeline.etl.sources.national_risk_index.etl import (
 from data_pipeline.etl.sources.dot_travel_composite.etl import (
     TravelCompositeETL,
 )
+from data_pipeline.etl.sources.fsf_flood_risk.etl import (
+    FloodRiskETL,
+)
+from data_pipeline.etl.sources.fsf_wildfire_risk.etl import WildfireRiskETL
 from data_pipeline.score.score_runner import ScoreRunner
 from data_pipeline.score import field_names
 from data_pipeline.etl.score import constants
@@ -41,6 +45,8 @@ class ScoreETL(ExtractTransformLoad):
         self.child_opportunity_index_df: pd.DataFrame
         self.hrs_df: pd.DataFrame
         self.dot_travel_disadvantage_df: pd.DataFrame
+        self.fsf_flood_df: pd.DataFrame
+        self.fsf_fire_df: pd.DataFrame
 
     def extract(self) -> None:
         logger.info("Loading data sets from disk.")
@@ -122,6 +128,12 @@ class ScoreETL(ExtractTransformLoad):
         # Load DOT Travel Disadvantage
         self.dot_travel_disadvantage_df = TravelCompositeETL.get_data_frame()
 
+        # Load fire risk data
+        self.fsf_fire_df = WildfireRiskETL.get_data_frame()
+
+        # Load flood risk data
+        self.fsf_flood_df = FloodRiskETL.get_data_frame()
+
         # Load GeoCorr Urban Rural Map
         geocorr_urban_rural_csv = (
             constants.DATA_PATH / "dataset" / "geocorr" / "usa.csv"
@@ -342,6 +354,8 @@ class ScoreETL(ExtractTransformLoad):
             self.child_opportunity_index_df,
             self.hrs_df,
             self.dot_travel_disadvantage_df,
+            self.fsf_flood_df,
+            self.fsf_fire_df,
         ]
 
         # Sanity check each data frame before merging.
@@ -426,6 +440,8 @@ class ScoreETL(ExtractTransformLoad):
             field_names.UST_FIELD,
             field_names.DOT_TRAVEL_BURDEN_FIELD,
             field_names.AGRICULTURAL_VALUE_BOOL_FIELD,
+            field_names.FUTURE_FLOOD_RISK_FIELD,
+            field_names.FUTURE_WILDFIRE_RISK_FIELD,
             field_names.POVERTY_LESS_THAN_200_FPL_IMPUTED_FIELD,
         ]
 

data/data-pipeline/data_pipeline/etl/sources/fsf_flood_risk/README.md

@@ -0,0 +1,3 @@
+# FSF flood risk data
+
+Flood risk computed as 1 in 100 year flood zone

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

@@ -0,0 +1,93 @@
+# pylint: disable=unsubscriptable-object
+# pylint: disable=unsupported-assignment-operation
+
+import pandas as pd
+from data_pipeline.config import settings
+
+from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel
+from data_pipeline.utils import get_module_logger
+
+logger = get_module_logger(__name__)
+
+
+class FloodRiskETL(ExtractTransformLoad):
+    """ETL class for the First Street Foundation flood risk dataset"""
+
+    NAME = "fsf_flood_risk"
+    SOURCE_URL = settings.AWS_JUSTICE40_DATASOURCES_URL + "/fsf_flood.zip"
+    GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
+
+    # Output score variables (values set on datasets.yml) for linting purposes
+    COUNT_PROPERTIES: str
+    PROPERTIES_AT_RISK_FROM_FLOODING_TODAY: str
+    PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS: str
+    SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_TODAY: str
+    SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS: str
+
+    def __init__(self):
+        # define the full path for the input CSV file
+        self.INPUT_CSV = (
+            self.get_tmp_path() / "fsf_flood" / "flood_tract_2010.csv"
+        )
+
+        # this is the main dataframe
+        self.df: pd.DataFrame
+
+        # Start dataset-specific vars here
+        self.COUNT_PROPERTIES_NATIVE_FIELD_NAME = "count_properties"
+        self.COUNT_PROPERTIES_AT_RISK_TODAY = "mid_depth_100_year00"
+        self.COUNT_PROPERTIES_AT_RISK_30_YEARS = "mid_depth_100_year30"
+        self.CLIP_PROPERTIES_COUNT = 250
+
+    def transform(self) -> None:
+        """Reads the unzipped data file into memory and applies the following
+        transformations to prepare it for the load() method:
+
+        - Renames the Census Tract column to match the other datasets
+        - Calculates share of properties at risk, left-clipping number of properties at 250
+        """
+        logger.info("Transforming National Risk Index Data")
+
+        logger.info(self.COLUMNS_TO_KEEP)
+        # read in the unzipped csv data source then rename the
+        # Census Tract column for merging
+        df_fsf_flood_disagg: pd.DataFrame = pd.read_csv(
+            self.INPUT_CSV,
+            dtype={self.INPUT_GEOID_TRACT_FIELD_NAME: str},
+            low_memory=False,
+        )
+
+        df_fsf_flood_disagg[self.GEOID_TRACT_FIELD_NAME] = df_fsf_flood_disagg[
+            self.INPUT_GEOID_TRACT_FIELD_NAME
+        ].str.zfill(11)
+
+        # Because we have some tracts that are listed twice, we aggregate based on
+        # GEOID10_TRACT. Note that I haven't confirmed this with the FSF boys -- to do!
+        df_fsf_flood = (
+            df_fsf_flood_disagg.groupby(self.GEOID_TRACT_FIELD_NAME)
+            .sum()
+            .reset_index()
+        )
+
+        df_fsf_flood[self.COUNT_PROPERTIES] = df_fsf_flood[
+            self.COUNT_PROPERTIES_NATIVE_FIELD_NAME
+        ].clip(lower=self.CLIP_PROPERTIES_COUNT)
+
+        df_fsf_flood[self.SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_TODAY] = (
+            df_fsf_flood[self.COUNT_PROPERTIES_AT_RISK_TODAY]
+            / df_fsf_flood[self.COUNT_PROPERTIES]
+        )
+        df_fsf_flood[
+            self.SHARE_OF_PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS
+        ] = (
+            df_fsf_flood[self.COUNT_PROPERTIES_AT_RISK_30_YEARS]
+            / df_fsf_flood[self.COUNT_PROPERTIES]
+        )
+
+        # Assign the final df to the class' output_df for the load method with rename
+        self.output_df = df_fsf_flood.rename(
+            columns={
+                self.COUNT_PROPERTIES_AT_RISK_TODAY: self.PROPERTIES_AT_RISK_FROM_FLOODING_TODAY,
+                self.COUNT_PROPERTIES_AT_RISK_30_YEARS: self.PROPERTIES_AT_RISK_FROM_FLOODING_IN_30_YEARS,
+            }
+        )

data/data-pipeline/data_pipeline/etl/sources/fsf_wildfire_risk/README.md

@@ -0,0 +1,3 @@
+# FSF wildfire risk data
+
+Fire risk computed as >= 0.003 burn risk probability

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

@@ -0,0 +1,91 @@
+# pylint: disable=unsubscriptable-object
+# pylint: disable=unsupported-assignment-operation
+
+import pandas as pd
+from data_pipeline.config import settings
+
+from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel
+from data_pipeline.utils import get_module_logger
+
+logger = get_module_logger(__name__)
+
+
+class WildfireRiskETL(ExtractTransformLoad):
+    """ETL class for the First Street Foundation wildfire risk dataset"""
+
+    NAME = "fsf_wildfire_risk"
+    SOURCE_URL = settings.AWS_JUSTICE40_DATASOURCES_URL + "/fsf_fire.zip"
+    GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
+
+    # Output score variables (values set on datasets.yml) for linting purposes
+    COUNT_PROPERTIES: str
+    PROPERTIES_AT_RISK_FROM_FIRE_TODAY: str
+    PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS: str
+    SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_TODAY: str
+    SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS: str
+
+    def __init__(self):
+        # define the full path for the input CSV file
+        self.INPUT_CSV = (
+            self.get_tmp_path() / "fsf_fire" / "fire_tract_2010.csv"
+        )
+
+        # this is the main dataframe
+        self.df: pd.DataFrame
+
+        # Start dataset-specific vars here
+        self.COUNT_PROPERTIES_NATIVE_FIELD_NAME = "count_properties"
+        self.COUNT_PROPERTIES_AT_RISK_TODAY = "burnprob_year00_flag"
+        self.COUNT_PROPERTIES_AT_RISK_30_YEARS = "burnprob_year30_flag"
+        self.CLIP_PROPERTIES_COUNT = 250
+
+    def transform(self) -> None:
+        """Reads the unzipped data file into memory and applies the following
+        transformations to prepare it for the load() method:
+
+        - Renames the Census Tract column to match the other datasets
+        - Calculates share of properties at risk, left-clipping number of properties at 250
+        """
+        logger.info("Transforming National Risk Index Data")
+
+        logger.info(self.COLUMNS_TO_KEEP)
+        # read in the unzipped csv data source then rename the
+        # Census Tract column for merging
+        df_fsf_fire_disagg: pd.DataFrame = pd.read_csv(
+            self.INPUT_CSV,
+            dtype={self.INPUT_GEOID_TRACT_FIELD_NAME: str},
+            low_memory=False,
+        )
+
+        df_fsf_fire_disagg[self.GEOID_TRACT_FIELD_NAME] = df_fsf_fire_disagg[
+            self.INPUT_GEOID_TRACT_FIELD_NAME
+        ].str.zfill(11)
+
+        # Because we have some tracts that are listed twice, we aggregate based on
+        # GEOID10_TRACT. Note that I haven't confirmed this with the FSF boys -- to do!
+        df_fsf_fire = (
+            df_fsf_fire_disagg.groupby(self.GEOID_TRACT_FIELD_NAME)
+            .sum()
+            .reset_index()
+        )
+
+        df_fsf_fire[self.COUNT_PROPERTIES] = df_fsf_fire[
+            self.COUNT_PROPERTIES_NATIVE_FIELD_NAME
+        ].clip(lower=self.CLIP_PROPERTIES_COUNT)
+
+        df_fsf_fire[self.SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_TODAY] = (
+            df_fsf_fire[self.COUNT_PROPERTIES_AT_RISK_TODAY]
+            / df_fsf_fire[self.COUNT_PROPERTIES]
+        )
+        df_fsf_fire[self.SHARE_OF_PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS] = (
+            df_fsf_fire[self.COUNT_PROPERTIES_AT_RISK_30_YEARS]
+            / df_fsf_fire[self.COUNT_PROPERTIES]
+        )
+
+        # Assign the final df to the class' output_df for the load method with rename
+        self.output_df = df_fsf_fire.rename(
+            columns={
+                self.COUNT_PROPERTIES_AT_RISK_TODAY: self.PROPERTIES_AT_RISK_FROM_FIRE_TODAY,
+                self.COUNT_PROPERTIES_AT_RISK_30_YEARS: self.PROPERTIES_AT_RISK_FROM_FIRE_IN_30_YEARS,
+            }
+        )

data/data-pipeline/data_pipeline/score/adding_variables_to_score.md

@@ -0,0 +1,28 @@
+# How to add variables to a score
+
+So, there's a variable you want to add to the score! Once you have the data source created in `etl/sources`, what should you do? There are 6 steps across a minimum of 7 files. 
+
+__Updating `field_names.py`__
+Per indicator, you need to make (usually) three variables to get used in other files. 
+- raw variable: this is the name of the variable's raw data, not scaled into a percentile
+- variable with threshold exceeded: this is a boolean for whether the tract meets the threshold for the indicator alone
+- variable with threshold exceeded and socioeconomic criterion exceeded: this is whether the tract will be a DAC based on the socioeconomic criterion and the indicator
+
+__Updating `etl_score.py`__
+- add the dataframe from the source to the ScoreETL constructor and add a line to read the dataframe into memory
+- then, add the dataframe into the list of `census_tract_dfs`
+- finally, add columns you want to include as percentiles to the  `numeric_columns` list
+
+__Updating `score_narwhal.py`__ (or whatever the score file is)
+- per factor, add the columns that show the threshold and socioeconomic criterion is exceeded to the `eligibility_columns` list
+- construct all columns specified in `field_names`, using the factor method as a guide
+
+__Updating `constants.py`__
+- add the columns' shortnames to the tiles dictionary (using Vim's UI sheet to guide short names)
+- add the floats to the list of floats
+
+__Updating `csv.yml` and `excel.yml`__
+- make sure each column you want to be in the downloadable files is listed here
+
+__Update the fixtures__
+Follow the instructions on the repo to modify tiles so that `test_etl_post.py` doesn't fail. Then, confirm results. 

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

@@ -1,8 +1,5 @@
 # Suffixes
 PERCENTILE_FIELD_SUFFIX = " (percentile)"
-PERCENTILE_URBAN_RURAL_FIELD_SUFFIX = " (percentile urban/rural)"
-MIN_MAX_FIELD_SUFFIX = " (min-max normalized)"
-TOP_25_PERCENTILE_SUFFIX = " (top 25th percentile)"
 ISLAND_AREAS_PERCENTILE_ADJUSTMENT_FIELD = " for island areas"
 
 # Geographic field names
@@ -11,38 +8,6 @@ STATE_FIELD = "State/Territory"
 COUNTY_FIELD = "County Name"
 
 # Score file field names
-SCORE_A = "Score A"
-SCORE_B = "Score B"
-SCORE_C = "Score C"
-C_SOCIOECONOMIC = "Socioeconomic Factors"
-C_SENSITIVE = "Sensitive populations"
-C_ENVIRONMENTAL = "Environmental effects"
-C_EXPOSURES = "Exposures"
-SCORE_D = "Score D"
-SCORE_E = "Score E"
-SCORE_F_COMMUNITIES = "Score F (communities)"
-SCORE_G = "Score G"
-SCORE_G_COMMUNITIES = "Score G (communities)"
-SCORE_H = "Score H"
-SCORE_H_COMMUNITIES = "Score H (communities)"
-SCORE_I = "Score I"
-SCORE_I_COMMUNITIES = "Score I (communities)"
-SCORE_K = "NMTC (communities)"
-SCORE_K_COMMUNITIES = "Score K (communities)"
-
-# Definition L fields
-SCORE_L = "Definition L"
-SCORE_L_COMMUNITIES = "Definition L (communities)"
-L_CLIMATE = "Climate Factor (Definition L)"
-L_ENERGY = "Energy Factor (Definition L)"
-L_TRANSPORTATION = "Transportation Factor (Definition L)"
-L_HOUSING = "Housing Factor (Definition L)"
-L_POLLUTION = "Pollution Factor (Definition L)"
-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)"
-
 # Definition M fields
 SCORE_M = "Definition M"
 SCORE_M_COMMUNITIES = "Definition M (communities)"
@@ -85,25 +50,6 @@ WORKFORCE_SOCIO_INDICATORS_EXCEEDED = (
     "Both workforce socioeconomic indicators exceeded"
 )
 
-# For now, these are not used. Will delete after following up with Vim.
-POLLUTION_SOCIO_INDICATORS_EXCEEDED = (
-    "Both pollution socioeconomic indicators exceeded"
-)
-CLIMATE_SOCIO_INDICATORS_EXCEEDED = (
-    "Both climate socioeconomic indicators exceeded"
-)
-ENERGY_SOCIO_INDICATORS_EXCEEDED = (
-    "Both energy socioeconomic indicators exceeded"
-)
-HOUSING_SOCIO_INDICATORS_EXCEEDED = (
-    "Both housing socioeconomic indicators exceeded"
-)
-WATER_SOCIO_INDICATORS_EXCEEDED = "Both water socioeconomic indicators exceeded"
-
-HEALTH_SOCIO_INDICATORS_EXCEEDED = (
-    "Both health socioeconomic indicators exceeded"
-)
-
 # Poverty / Income
 POVERTY_FIELD = "Poverty (Less than 200% of federal poverty line)"
 
@@ -156,6 +102,8 @@ EXPECTED_AGRICULTURE_LOSS_RATE_FIELD = (
 EXPECTED_POPULATION_LOSS_RATE_FIELD = (
     "Expected population loss rate (Natural Hazards Risk Index)"
 )
+FUTURE_FLOOD_RISK_FIELD = "Share of properties at risk of flood in 30 years"
+FUTURE_WILDFIRE_RISK_FIELD = "Share of properties at risk of fire in 30 years"
 
 # Environment
 DIESEL_FIELD = "Diesel particulate matter exposure"
@@ -408,6 +356,15 @@ EXPECTED_BUILDING_LOSS_RATE_LOW_INCOME_FIELD = (
 )
 AGRICULTURAL_VALUE_BOOL_FIELD = "Contains agricultural value"
 
+HIGH_FUTURE_FLOOD_RISK_LOW_INCOME_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile for share of "
+    "properties at risk of flood in 30 years and is low income?"
+)
+HIGH_FUTURE_WILDFIRE_RISK_LOW_INCOME_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile for "
+    "share of properties at risk of fire in 30 years and is low income?"
+)
+
 # Clean energy and efficiency
 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"Greater than or equal to the {PERCENTILE}th percentile for energy burden and is low income?"
@@ -670,6 +627,16 @@ LOW_LIFE_EXPECTANCY_PCTILE_THRESHOLD = (
 UNEMPLOYMENT_PCTILE_THRESHOLD = (
     f"Greater than or equal to the {PERCENTILE}th percentile for unemployment"
 )
+HIGH_FUTURE_FLOOD_RISK_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile for share of properties "
+    "at risk of flood in 30 years"
+)
+HIGH_FUTURE_WILDFIRE_RISK_FIELD = (
+    f"Greater than or equal to the {PERCENTILE}th percentile for share of properties "
+    "at risk of fire in 30 years"
+)
+
+
 LINGUISTIC_ISOLATION_PCTILE_THRESHOLD = f"Greater than or equal to the {PERCENTILE}th percentile for households in linguistic isolation"
 POVERTY_PCTILE_THRESHOLD = f"Greater than or equal to the {PERCENTILE}th percentile for households at or below 100% federal poverty level"
 LOW_MEDIAN_INCOME_PCTILE_THRESHOLD = (

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

@@ -122,8 +122,13 @@ class ScoreNarwhal(Score):
             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,
+            field_names.HIGH_FUTURE_FLOOD_RISK_LOW_INCOME_FIELD,
+            field_names.HIGH_FUTURE_WILDFIRE_RISK_LOW_INCOME_FIELD,
         ]
 
+        # TODO: When we refactor this... it's the same code over and over and over again
+        # We should make a function, _get_all_columns(), that returns all three of these columns
+
         self.df[
             field_names.EXPECTED_POPULATION_LOSS_EXCEEDS_PCTILE_THRESHOLD
         ] = (
@@ -152,6 +157,22 @@ class ScoreNarwhal(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.HIGH_FUTURE_FLOOD_RISK_FIELD] = (
+            self.df[
+                field_names.FUTURE_FLOOD_RISK_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
+        self.df[field_names.HIGH_FUTURE_WILDFIRE_RISK_FIELD] = (
+            self.df[
+                field_names.FUTURE_WILDFIRE_RISK_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
+        )
+
         self.df[field_names.CLIMATE_THRESHOLD_EXCEEDED] = (
             self.df[
                 field_names.EXPECTED_POPULATION_LOSS_EXCEEDS_PCTILE_THRESHOLD
@@ -162,6 +183,8 @@ class ScoreNarwhal(Score):
             | self.df[
                 field_names.EXPECTED_BUILDING_LOSS_EXCEEDS_PCTILE_THRESHOLD
             ]
+            | self.df[field_names.HIGH_FUTURE_WILDFIRE_RISK_FIELD]
+            | self.df[field_names.HIGH_FUTURE_FLOOD_RISK_FIELD]
         )
 
         self.df[field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_FIELD] = (
@@ -183,6 +206,16 @@ class ScoreNarwhal(Score):
             & self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
         )
 
+        self.df[field_names.HIGH_FUTURE_FLOOD_RISK_LOW_INCOME_FIELD] = (
+            self.df[field_names.HIGH_FUTURE_FLOOD_RISK_FIELD]
+            & self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
+        )
+
+        self.df[field_names.HIGH_FUTURE_WILDFIRE_RISK_LOW_INCOME_FIELD] = (
+            self.df[field_names.HIGH_FUTURE_WILDFIRE_RISK_FIELD]
+            & self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED]
+        )
+
         self._increment_total_eligibility_exceeded(
             climate_eligibility_columns,
             skip_fips=constants.DROP_FIPS_FROM_NON_WTD_THRESHOLDS,
@@ -865,11 +898,6 @@ class ScoreNarwhal(Score):
 
         self.df[field_names.THRESHOLD_COUNT] = 0
 
-        # TODO: move this inside of
-        #  `_create_low_income_and_low_college_attendance_threshold`
-        # and change the return signature of that method.
-        # Create a standalone field that captures the college attendance boolean
-        # threshold.
         self.df[field_names.FPL_200_SERIES_IMPUTED_AND_ADJUSTED] = (
             self.df[
                 # UPDATE: Pull the imputed poverty statistic

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

@@ -1,13 +1,4 @@
 import pandas as pd
-from data_pipeline.score.score_a import ScoreA
-from data_pipeline.score.score_b import ScoreB
-from data_pipeline.score.score_c import ScoreC
-from data_pipeline.score.score_f import ScoreF
-from data_pipeline.score.score_g import ScoreG
-from data_pipeline.score.score_h import ScoreH
-from data_pipeline.score.score_i import ScoreI
-from data_pipeline.score.score_k import ScoreK
-from data_pipeline.score.score_l import ScoreL
 from data_pipeline.score.score_m import ScoreM
 from data_pipeline.score.score_narwhal import ScoreNarwhal
 
@@ -23,15 +14,6 @@ class ScoreRunner:
 
     def calculate_scores(self) -> pd.DataFrame:
         # Index scores
-        self.df = ScoreA(df=self.df).add_columns()
-        self.df = ScoreB(df=self.df).add_columns()
-        self.df = ScoreC(df=self.df).add_columns()
-        self.df = ScoreF(df=self.df).add_columns()
-        self.df = ScoreG(df=self.df).add_columns()
-        self.df = ScoreH(df=self.df).add_columns()
-        self.df = ScoreI(df=self.df).add_columns()
-        self.df = ScoreK(df=self.df).add_columns()
-        self.df = ScoreL(df=self.df).add_columns()
         self.df = ScoreM(df=self.df).add_columns()
         self.df = ScoreNarwhal(df=self.df).add_columns()