Adding first street foundation data (#1823)

Adding FSF flood and wildfire risk datasets to the score.

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,
         ]