Add ability to cache ETL data sources (#2169)

* Add a rough prototype allowing a developer to pre-download data sources for all ETLs

* Update code to be more production-ish

* Move fetch to Extract part of ETL
* Create a downloader to house all downloading operations
* Remove unnecessary "name" in data source

* Format source files with black

* Fix issues from pylint and get the tests working with the new folder structure

* Clean up files with black

* Fix unzip test

* Add caching notes to README

* Fix tests (linting and case sensitivity bug)

* Address PR comments and add API keys for census where missing

* Merging comparator changes from main into this branch for the sake of the PR

* Add note on using cache (-u) during pipeline

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

@@ -3,12 +3,16 @@ from data_pipeline.config import settings
 from data_pipeline.etl.base import ExtractTransformLoad
 from data_pipeline.etl.base import ValidGeoLevel
 from data_pipeline.utils import get_module_logger
+from data_pipeline.etl.datasource import DataSource
+from data_pipeline.etl.datasource import ZIPDataSource
 
 logger = get_module_logger(__name__)
 
 
 class HistoricRedliningETL(ExtractTransformLoad):
+
     NAME = "historic_redlining"
+
     GEO_LEVEL: ValidGeoLevel = ValidGeoLevel.CENSUS_TRACT
     EXPECTED_MISSING_STATES = [
         "10",
@@ -25,14 +29,14 @@ class HistoricRedliningETL(ExtractTransformLoad):
     ]
     PUERTO_RICO_EXPECTED_IN_DATA = False
     ALASKA_AND_HAWAII_EXPECTED_IN_DATA: bool = False
-    SOURCE_URL = settings.AWS_JUSTICE40_DATASOURCES_URL + "/HRS_2010.zip"
 
     def __init__(self):
-        self.CSV_PATH = self.DATA_PATH / "dataset" / "historic_redlining"
 
-        self.HISTORIC_REDLINING_FILE_PATH = (
-            self.get_tmp_path() / "HRS_2010.xlsx"
-        )
+        # fetch
+        self.hrs_url = settings.AWS_JUSTICE40_DATASOURCES_URL + "/HRS_2010.zip"
+
+        # input
+        self.hrs_source = self.get_sources_path() / "HRS_2010.xlsx"
 
         self.REDLINING_SCALAR = "Tract-level redlining score"
 
@@ -40,30 +44,47 @@ class HistoricRedliningETL(ExtractTransformLoad):
             self.GEOID_TRACT_FIELD_NAME,
             self.REDLINING_SCALAR,
         ]
+
         self.df: pd.DataFrame
+        self.historic_redlining_data: pd.DataFrame
+
+    def get_data_sources(self) -> [DataSource]:
+        return [
+            ZIPDataSource(
+                source=self.hrs_url, destination=self.get_sources_path()
+            )
+        ]
+
+    def extract(self, use_cached_data_sources: bool = False) -> None:
+
+        super().extract(
+            use_cached_data_sources
+        )  # download and extract data sources
+
+        self.historic_redlining_data = pd.read_excel(self.hrs_source)
 
     def transform(self) -> None:
         # this is obviously temporary
-        historic_redlining_data = pd.read_excel(
-            self.HISTORIC_REDLINING_FILE_PATH
+
+        self.historic_redlining_data[self.GEOID_TRACT_FIELD_NAME] = (
+            self.historic_redlining_data["GEOID10"].astype(str).str.zfill(11)
         )
-        historic_redlining_data[self.GEOID_TRACT_FIELD_NAME] = (
-            historic_redlining_data["GEOID10"].astype(str).str.zfill(11)
-        )
-        historic_redlining_data = historic_redlining_data.rename(
+        self.historic_redlining_data = self.historic_redlining_data.rename(
             columns={"HRS2010": self.REDLINING_SCALAR}
         )
 
-        logger.debug(f"{historic_redlining_data.columns}")
+        logger.debug(f"{self.historic_redlining_data.columns}")
 
         # Calculate lots of different score thresholds for convenience
         for threshold in [3.25, 3.5, 3.75]:
-            historic_redlining_data[
+            self.historic_redlining_data[
                 f"{self.REDLINING_SCALAR} meets or exceeds {round(threshold, 2)}"
-            ] = (historic_redlining_data[self.REDLINING_SCALAR] >= threshold)
+            ] = (
+                self.historic_redlining_data[self.REDLINING_SCALAR] >= threshold
+            )
             ## NOTE We add to columns to keep here
             self.COLUMNS_TO_KEEP.append(
                 f"{self.REDLINING_SCALAR} meets or exceeds {round(threshold, 2)}"
             )
 
-        self.output_df = historic_redlining_data
+        self.output_df = self.historic_redlining_data