passing score

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

@@ -5,6 +5,7 @@ from data_pipeline.etl.sources.census_acs.etl_utils import (
     retrieve_census_acs_data,
 )
 from data_pipeline.utils import get_module_logger
+from data_pipeline.score import field_names
 
 logger = get_module_logger(__name__)
 
@@ -353,18 +354,29 @@ class CensusACSETL(ExtractTransformLoad):
             + df[self.COLLEGE_ATTENDANCE_FEMALE_ENROLLED_PRIVATE]
         ) / df[self.COLLEGE_ATTENDANCE_TOTAL_POPULATION_ASKED]
 
+        # strip columns
+        df = df[self.COLUMNS_TO_KEEP]
+
         # Save results to self.
         self.df = df
 
+        # rename columns to be used in score
+        rename_fields = {
+            "Percent of individuals < 200% Federal Poverty Line": field_names.POVERTY_LESS_THAN_200_FPL_FIELD,
+        }
+        self.df.rename(
+            columns=rename_fields,
+            inplace=True,
+            errors="raise",
+        )
+
     def load(self) -> None:
         logger.info("Saving Census ACS Data")
 
         # mkdir census
         self.OUTPUT_PATH.mkdir(parents=True, exist_ok=True)
 
-        self.df[self.COLUMNS_TO_KEEP].to_csv(
-            path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False
-        )
+        self.df.to_csv(path_or_buf=self.OUTPUT_PATH / "usa.csv", index=False)
 
     def validate(self) -> None:
         logger.info("Validating Census ACS Data")