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/nlcd_nature_deprived/etl.py

@@ -3,6 +3,8 @@
 import pandas as pd
 from data_pipeline.config import settings
 from data_pipeline.etl.base import ExtractTransformLoad
+from data_pipeline.etl.datasource import DataSource
+from data_pipeline.etl.datasource import ZIPDataSource
 from data_pipeline.etl.base import ValidGeoLevel
 from data_pipeline.utils import get_module_logger
 
@@ -13,10 +15,7 @@ class NatureDeprivedETL(ExtractTransformLoad):
     """ETL class for the Nature Deprived Communities dataset"""
 
     NAME = "nlcd_nature_deprived"
-    SOURCE_URL = (
-        settings.AWS_JUSTICE40_DATASOURCES_URL
-        + "/usa_conus_nat_dep__compiled_by_TPL.csv.zip"
-    )
+
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
     PUERTO_RICO_EXPECTED_IN_DATA = False
     LOAD_YAML_CONFIG: bool = True
@@ -29,14 +28,25 @@ class NatureDeprivedETL(ExtractTransformLoad):
     TRACT_PERCENT_CROPLAND_FIELD_NAME: str
 
     def __init__(self):
-        # define the full path for the input CSV file
-        self.INPUT_CSV = (
-            self.get_tmp_path() / "usa_conus_nat_dep__compiled_by_TPL.csv"
+
+        # fetch
+        self.nature_deprived_url = (
+            settings.AWS_JUSTICE40_DATASOURCES_URL
+            + "/usa_conus_nat_dep__compiled_by_TPL.csv.zip"
         )
 
+        # source
+        # define the full path for the input CSV file
+        self.nature_deprived_source = (
+            self.get_sources_path() / "usa_conus_nat_dep__compiled_by_TPL.csv"
+        )
+
+        # output
         # this is the main dataframe
         self.df: pd.DataFrame
 
+        self.df_ncld: pd.DataFrame
+
         # Start dataset-specific vars here
         self.PERCENT_NATURAL_FIELD_NAME = "PctNatural"
         self.PERCENT_IMPERVIOUS_FIELD_NAME = "PctImperv"
@@ -47,28 +57,43 @@ class NatureDeprivedETL(ExtractTransformLoad):
         # for area. This does indeed remove tracts from the 90th+ percentile later on
         self.TRACT_ACRES_LOWER_BOUND = 35
 
-    def transform(self) -> None:
+    def get_data_sources(self) -> [DataSource]:
+        return [
+            ZIPDataSource(
+                source=self.nature_deprived_url,
+                destination=self.get_sources_path(),
+            )
+        ]
+
+    def extract(self, use_cached_data_sources: bool = False) -> None:
         """Reads the unzipped data file into memory and applies the following
         transformations to prepare it for the load() method:
 
         - Renames columns as needed
         """
 
-        df_ncld: pd.DataFrame = pd.read_csv(
-            self.INPUT_CSV,
+        super().extract(
+            use_cached_data_sources
+        )  # download and extract data sources
+
+        self.df_ncld = pd.read_csv(
+            self.nature_deprived_source,
             dtype={self.INPUT_GEOID_TRACT_FIELD_NAME: str},
             low_memory=False,
         )
 
-        df_ncld[self.ELIGIBLE_FOR_NATURE_DEPRIVED_FIELD_NAME] = (
-            df_ncld[self.TRACT_ACRES_FIELD_NAME] >= self.TRACT_ACRES_LOWER_BOUND
+    def transform(self) -> None:
+
+        self.df_ncld[self.ELIGIBLE_FOR_NATURE_DEPRIVED_FIELD_NAME] = (
+            self.df_ncld[self.TRACT_ACRES_FIELD_NAME]
+            >= self.TRACT_ACRES_LOWER_BOUND
         )
-        df_ncld[self.TRACT_PERCENT_NON_NATURAL_FIELD_NAME] = (
-            100 - df_ncld[self.PERCENT_NATURAL_FIELD_NAME]
+        self.df_ncld[self.TRACT_PERCENT_NON_NATURAL_FIELD_NAME] = (
+            100 - self.df_ncld[self.PERCENT_NATURAL_FIELD_NAME]
         )
 
         # Assign the final df to the class' output_df for the load method with rename
-        self.output_df = df_ncld.rename(
+        self.output_df = self.df_ncld.rename(
             columns={
                 self.PERCENT_IMPERVIOUS_FIELD_NAME: self.TRACT_PERCENT_IMPERVIOUS_FIELD_NAME,
                 self.PERCENT_CROPLAND_FIELD_NAME: self.TRACT_PERCENT_CROPLAND_FIELD_NAME,