1295-college-attendance-field (#1297)

Lucas' work. Adding college attendance to tiles.

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

@@ -203,6 +203,8 @@ TILES_SCORE_COLUMNS = {
     + field_names.PERCENTILE_FIELD_SUFFIX: "IAULHSE_PFS",
     # 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",
 }
 
 # columns to round floats to 2 decimals
@@ -252,6 +254,7 @@ TILES_SCORE_FLOAT_COLUMNS = [
     field_names.ISLAND_AREAS_LOW_HS_EDUCATION_FIELD,
     field_names.WASTEWATER_FIELD + field_names.PERCENTILE_FIELD_SUFFIX,
     field_names.SCORE_M + field_names.PERCENTILE_FIELD_SUFFIX,
+    field_names.COLLEGE_ATTENDANCE_FIELD,
 ]
 
 # Finally we augment with the GEOID10, county, and state
@@ -263,6 +266,8 @@ DOWNLOADABLE_SCORE_COLUMNS = [
     field_names.SCORE_M_COMMUNITIES,
     field_names.TOTAL_POP_FIELD,
     field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES,
+    field_names.COLLEGE_ATTENDANCE_FIELD,
+    field_names.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD,
     field_names.EXPECTED_AGRICULTURE_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD,
     field_names.EXPECTED_AGRICULTURE_LOSS_RATE_FIELD
     + field_names.PERCENTILE_FIELD_SUFFIX,

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

@@ -375,6 +375,10 @@ SCORE_M_LOW_INCOME_SUFFIX = (
     ", is low income, and has a low percent of higher ed students"
 )
 
+COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD = (
+    "Percent higher ed enrollment rate is less than 20%"
+)
+
 # Climate Change
 EXPECTED_POPULATION_LOSS_RATE_LOW_INCOME_LOW_HIGHER_ED_FIELD = (
     f"Greater than or equal to the {PERCENTILE}th percentile"

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

@@ -92,6 +92,7 @@ class ScoreM(Score):
         of booleans based on the condition of the FPL at 200%
         is at or more than some established threshold
         """
+
         return (
             (
                 df[
@@ -101,10 +102,7 @@ class ScoreM(Score):
                 >= self.LOW_INCOME_THRESHOLD
             )
         ) & (
-            (
-                df[field_names.COLLEGE_ATTENDANCE_FIELD]
-                <= self.MAX_COLLEGE_ATTENDANCE_THRESHOLD
-            )
+            df[field_names.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD]
             | (
                 # If college attendance data is null for this tract, just rely on the
                 # poverty data
@@ -732,6 +730,17 @@ class ScoreM(Score):
         logger.info("Adding Score M")
 
         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.COLLEGE_ATTENDANCE_LESS_THAN_20_FIELD] = (
+            self.df[field_names.COLLEGE_ATTENDANCE_FIELD]
+            <= self.MAX_COLLEGE_ATTENDANCE_THRESHOLD
+        )
+
         self.df[
             field_names.FPL_200_AND_COLLEGE_ATTENDANCE_SERIES
         ] = self._create_low_income_and_low_college_attendance_threshold(