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/doe_energy_burden/etl.py

@@ -5,22 +5,35 @@ 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 DOEEnergyBurden(ExtractTransformLoad):
+
     NAME = "doe_energy_burden"
-    SOURCE_URL: str = (
-        settings.AWS_JUSTICE40_DATASOURCES_URL
-        + "/DOE_LEAD_AMI_TRACT_2018_ALL.csv.zip"
-    )
+
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
     LOAD_YAML_CONFIG: bool = True
 
     REVISED_ENERGY_BURDEN_FIELD_NAME: str
 
     def __init__(self):
+
+        # fetch
+        self.doe_energy_burden_url = (
+            settings.AWS_JUSTICE40_DATASOURCES_URL
+            + "/DOE_LEAD_AMI_TRACT_2018_ALL.csv.zip"
+        )
+
+        # input
+        self.doe_energy_burden_source = (
+            self.get_sources_path() / "DOE_LEAD_AMI_TRACT_2018_ALL.csv"
+        )
+
+        # output
         self.OUTPUT_PATH: Path = (
             self.DATA_PATH / "dataset" / "doe_energy_burden"
         )
@@ -29,10 +42,22 @@ class DOEEnergyBurden(ExtractTransformLoad):
         self.raw_df: pd.DataFrame
         self.output_df: pd.DataFrame
 
-    def transform(self) -> None:
-        raw_df: pd.DataFrame = pd.read_csv(
-            filepath_or_buffer=self.get_tmp_path()
-            / "DOE_LEAD_AMI_TRACT_2018_ALL.csv",
+    def get_data_sources(self) -> [DataSource]:
+        return [
+            ZIPDataSource(
+                source=self.doe_energy_burden_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.raw_df = pd.read_csv(
+            filepath_or_buffer=self.doe_energy_burden_source,
             # The following need to remain as strings for all of their digits, not get converted to numbers.
             dtype={
                 self.INPUT_GEOID_TRACT_FIELD_NAME: "string",
@@ -40,8 +65,10 @@ class DOEEnergyBurden(ExtractTransformLoad):
             low_memory=False,
         )
 
+    def transform(self) -> None:
+
         logger.debug("Renaming columns and ensuring output format is correct")
-        output_df = raw_df.rename(
+        output_df = self.raw_df.rename(
             columns={
                 self.INPUT_ENERGY_BURDEN_FIELD_NAME: self.REVISED_ENERGY_BURDEN_FIELD_NAME,
                 self.INPUT_GEOID_TRACT_FIELD_NAME: self.GEOID_TRACT_FIELD_NAME,