Adding constants for front end to display booleans (#1348)

Added constants for the threshold categories and socioeconomic indicators for front end.

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

@@ -187,8 +187,6 @@ TILES_SCORE_COLUMNS = {
     field_names.POVERTY_LOW_HS_LOW_HIGHER_ED_FIELD: "PLHSE",
     field_names.LOW_MEDIAN_INCOME_LOW_HS_LOW_HIGHER_ED_FIELD: "LMILHSE",
     field_names.UNEMPLOYMENT_LOW_HS_LOW_HIGHER_ED_FIELD: "ULHSE",
-    field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD: "LHE",
-    field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES: "FPL200S",
     field_names.THRESHOLD_COUNT: "TC",
     field_names.ISLAND_AREAS_UNEMPLOYMENT_LOW_HS_EDUCATION_FIELD: "IAULHSE",
     field_names.ISLAND_AREAS_POVERTY_LOW_HS_EDUCATION_FIELD: "IAPLHSE",
@@ -203,10 +201,26 @@ TILES_SCORE_COLUMNS = {
     field_names.CENSUS_DECENNIAL_UNEMPLOYMENT_FIELD_2009
     + field_names.ISLAND_AREAS_PERCENTILE_ADJUSTMENT_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX: "IAULHSE_PFS",
+    field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD: "LHE",
     # Percentage of HS Degree completion for Islands
     field_names.CENSUS_DECENNIAL_HIGH_SCHOOL_ED_FIELD_2009: "IAHSEF",
     field_names.COLLEGE_ATTENDANCE_FIELD: "CA",
     field_names.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD: "CA_LT20",
+    field_names.LOW_INCOME_THRESHOLD: "FPL200S",
+    # Booleans for the front end about the types of thresholds exceeded
+    field_names.CLIMATE_THRESHOLD_EXCEEDED: "M_CLT_EOMI",
+    field_names.ENERGY_THRESHOLD_EXCEEDED: "M_ENY_EOMI",
+    field_names.TRAFFIC_THRESHOLD_EXCEEDED: "M_TRN_EOMI",
+    field_names.HOUSING_THREHSOLD_EXCEEDED: "M_HSG_EOMI",
+    field_names.POLLUTION_THRESHOLD_EXCEEDED: "M_PLN_EOMI",
+    field_names.WATER_THRESHOLD_EXCEEDED: "M_WTR_EOMI",
+    field_names.HEALTH_THRESHOLD_EXCEEDED: "M_HLTH_EOMI",
+    field_names.WORKFORCE_THRESHOLD_EXCEEDED: "M_WKFC_EOMI",
+    # These are the booleans for socioeconomic indicators
+    ## Low high school and low higher ed for t&wd
+    field_names.WORKFORCE_SOCIO_INDICATORS_EXCEEDED: "M_WKFC_EBSI",
+    ## FPL 200 and low higher ed for all others
+    field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES: "M_EBSI",
 }
 
 # columns to round floats to 2 decimals

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

@@ -59,6 +59,38 @@ M_NON_WORKFORCE = "Any Non-Workforce Factor (Definition M)"
 PERCENTILE = 90
 MEDIAN_HOUSE_VALUE_PERCENTILE = 90
 
+# Boolean fields
+CLIMATE_THRESHOLD_EXCEEDED = "At least one climate threshold exceeded"
+ENERGY_THRESHOLD_EXCEEDED = "At least one energy threshold exceeded"
+TRAFFIC_THRESHOLD_EXCEEDED = "At least one traffic threshold exceeded"
+HOUSING_THREHSOLD_EXCEEDED = "At least one housing threshold exceeded"
+POLLUTION_THRESHOLD_EXCEEDED = "At least one pollution threshold exceeded"
+WATER_THRESHOLD_EXCEEDED = "At least one water threshold exceeded"
+HEALTH_THRESHOLD_EXCEEDED = "At least one health threshold exceeded"
+WORKFORCE_THRESHOLD_EXCEEDED = "At least one workforce threshold exceeded"
+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)"
 POVERTY_LESS_THAN_200_FPL_FIELD = (
@@ -113,6 +145,8 @@ NPL_FIELD = "Proximity to NPL sites"
 AIR_TOXICS_CANCER_RISK_FIELD = "Air toxics cancer risk"
 RESPIRATORY_HAZARD_FIELD = "Respiratory hazard index"
 
+LOW_INCOME_THRESHOLD = "Exceeds FPL200 threshold"
+
 # Housing
 HOUSING_BURDEN_FIELD = "Housing burden (percent)"
 HT_INDEX_FIELD = (

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

@@ -94,15 +94,7 @@ class ScoreM(Score):
         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
-            )
-        ) & (
+        return (df[field_names.LOW_INCOME_THRESHOLD]) & (
             df[field_names.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD]
             | (
                 # If college attendance data is null for this tract, just rely on the
@@ -174,6 +166,12 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.CLIMATE_THRESHOLD_EXCEEDED] = (
+            expected_population_loss_threshold
+            | expected_agriculture_loss_threshold
+            | expected_building_loss_threshold
+        )
+
         self.df[
             field_names.EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD
         ] = (
@@ -230,6 +228,10 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.ENERGY_THRESHOLD_EXCEEDED] = (
+            energy_burden_threshold | pm25_threshold
+        )
+
         self.df[field_names.PM25_EXPOSURE_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
             pm25_threshold
             & self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
@@ -278,6 +280,10 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.TRAFFIC_THRESHOLD_EXCEEDED] = (
+            traffic_threshold | diesel_threshold
+        )
+
         self.df[
             field_names.DIESEL_PARTICULATE_MATTER_LOW_INCOME_LOW_HIGHER_ED_FIELD
         ] = (
@@ -341,6 +347,10 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.HOUSING_THREHSOLD_EXCEEDED] = (
+            lead_paint_median_home_value_threshold | housing_burden_threshold
+        )
+
         # series by series indicators
         self.df[
             field_names.LEAD_PAINT_MEDIAN_HOUSE_VALUE_LOW_INCOME_LOW_HIGHER_ED_FIELD
@@ -392,6 +402,10 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.POLLUTION_THRESHOLD_EXCEEDED] = (
+            rmp_sites_threshold | npl_sites_threshold
+        ) | tsdf_sites_threshold
+
         # individual series-by-series
         self.df[field_names.RMP_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
             rmp_sites_threshold
@@ -421,7 +435,7 @@ class ScoreM(Score):
         # poverty level and has a low percent of higher ed students
         # Source: Census's American Community Survey
 
-        wastewater_threshold = (
+        self.df[field_names.WATER_THRESHOLD_EXCEEDED] = (
             self.df[
                 field_names.WASTEWATER_FIELD
                 + field_names.PERCENTILE_FIELD_SUFFIX
@@ -432,7 +446,7 @@ class ScoreM(Score):
         self.df[
             field_names.WASTEWATER_DISCHARGE_LOW_INCOME_LOW_HIGHER_ED_FIELD
         ] = (
-            wastewater_threshold
+            self.df[field_names.WATER_THRESHOLD_EXCEEDED]
             & self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
         )
 
@@ -496,6 +510,10 @@ class ScoreM(Score):
             >= self.ENVIRONMENTAL_BURDEN_THRESHOLD
         )
 
+        self.df[field_names.HEALTH_THRESHOLD_EXCEEDED] = (
+            (diabetes_threshold | asthma_threshold) | heart_disease_threshold
+        ) | low_life_expectancy_threshold
+
         self.df[field_names.DIABETES_LOW_INCOME_LOW_HIGHER_ED_FIELD] = (
             diabetes_threshold
             & self.df[field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES]
@@ -726,6 +744,34 @@ class ScoreM(Score):
             f"in the column) have a value of TRUE."
         )
 
+        # Because these criteria are calculated differently for the islands, we also calculate the
+        # thresholds to pass to the FE slightly differently
+
+        self.df[field_names.WORKFORCE_THRESHOLD_EXCEEDED] = (
+            ## First we calculate for the non-island areas
+            (
+                (poverty_threshold | linguistic_isolation_threshold)
+                | low_median_income_threshold
+            )
+            | unemployment_threshold
+        ) | (
+            ## then we calculate just for the island areas
+            (
+                self.df[island_areas_unemployment_criteria_field_name]
+                | self.df[island_areas_poverty_criteria_field_name]
+            )
+            | self.df[
+                island_areas_low_median_income_as_a_percent_of_ami_criteria_field_name
+            ]
+        )
+
+        # Because of the island complications, we also have to separately calculate the threshold for
+        # socioeconomic thresholds
+        self.df[field_names.WORKFORCE_SOCIO_INDICATORS_EXCEEDED] = (
+            self.df[field_names.ISLAND_AREAS_LOW_HS_EDUCATION_FIELD]
+            | self.df[field_names.LOW_HS_EDUCATION_LOW_HIGHER_ED_FIELD]
+        )
+
         # A tract is included if it meets either the states tract criteria or the
         # island areas tract criteria.
         return (
@@ -743,6 +789,14 @@ class ScoreM(Score):
         # and change the return signature of that method.
         # Create a standalone field that captures the college attendance boolean
         # threshold.
+        self.df[field_names.LOW_INCOME_THRESHOLD] = (
+            self.df[
+                field_names.POVERTY_LESS_THAN_200_FPL_FIELD
+                + field_names.PERCENTILE_FIELD_SUFFIX
+            ]
+            >= self.LOW_INCOME_THRESHOLD
+        )
+
         self.df[field_names.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD] = (
             self.df[field_names.COLLEGE_ATTENDANCE_FIELD]
             <= self.MAX_COLLEGE_ATTENDANCE_THRESHOLD