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/dot_travel_composite/etl.py

@@ -3,6 +3,8 @@
 import geopandas as gpd
 import pandas as pd
 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
 from data_pipeline.config import settings
@@ -15,14 +17,6 @@ class TravelCompositeETL(ExtractTransformLoad):
 
     NAME = "travel_composite"
 
-    if settings.DATASOURCE_RETRIEVAL_FROM_AWS:
-        SOURCE_URL = (
-            f"{settings.AWS_JUSTICE40_DATASOURCES_URL}/raw-data-sources/"
-            "dot_travel_composite/Shapefile_and_Metadata.zip"
-        )
-    else:
-        SOURCE_URL = "https://www.transportation.gov/sites/dot.gov/files/Shapefile_and_Metadata.zip"
-
     GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
     PUERTO_RICO_EXPECTED_IN_DATA = False
     LOAD_YAML_CONFIG: bool = True
@@ -31,14 +25,29 @@ class TravelCompositeETL(ExtractTransformLoad):
     TRAVEL_BURDEN_FIELD_NAME: str
 
     def __init__(self):
+
+        # fetch
+        if settings.DATASOURCE_RETRIEVAL_FROM_AWS:
+            self.travel_composite_url = (
+                f"{settings.AWS_JUSTICE40_DATASOURCES_URL}/raw-data-sources/"
+                "dot_travel_composite/Shapefile_and_Metadata.zip"
+            )
+        else:
+            self.travel_composite_url = "https://www.transportation.gov/sites/dot.gov/files/Shapefile_and_Metadata.zip"
+
+        # input
         # define the full path for the input CSV file
-        self.INPUT_SHP = (
-            self.get_tmp_path() / "DOT_Disadvantage_Layer_Final_April2022.shp"
+        self.disadvantage_layer_shape_source = (
+            self.get_sources_path()
+            / "DOT_Disadvantage_Layer_Final_April2022.shp"
         )
 
+        # output
         # this is the main dataframe
         self.df: pd.DataFrame
 
+        self.df_dot: pd.DataFrame
+
         # Start dataset-specific vars here
         ## Average of Transportation Indicator Percentiles (calculated)
         ## Calculated: Average of (EPL_TCB+EPL_NWKI+EPL_NOVEH+EPL_COMMUTE) excluding NULLS
@@ -46,6 +55,22 @@ class TravelCompositeETL(ExtractTransformLoad):
         self.INPUT_TRAVEL_DISADVANTAGE_FIELD_NAME = "Transp_TH"
         self.INPUT_GEOID_TRACT_FIELD_NAME = "FIPS"
 
+    def get_data_sources(self) -> [DataSource]:
+        return [
+            ZIPDataSource(
+                source=self.travel_composite_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.df_dot = gpd.read_file(self.disadvantage_layer_shape_source)
+
     def transform(self) -> None:
         """Reads the unzipped data file into memory and applies the following
         transformations to prepare it for the load() method:
@@ -54,15 +79,15 @@ class TravelCompositeETL(ExtractTransformLoad):
         - Converts to CSV
         """
 
-        # read in the unzipped shapefile from data source
         # reformat it to be standard df, remove unassigned rows, and
         # then rename the Census Tract column for merging
-        df_dot: pd.DataFrame = gpd.read_file(self.INPUT_SHP)
-        df_dot = df_dot.rename(
+
+        self.df_dot = self.df_dot.rename(
             columns={
                 self.INPUT_GEOID_TRACT_FIELD_NAME: self.GEOID_TRACT_FIELD_NAME,
                 self.INPUT_TRAVEL_DISADVANTAGE_FIELD_NAME: self.TRAVEL_BURDEN_FIELD_NAME,
             }
         ).dropna(subset=[self.GEOID_TRACT_FIELD_NAME])
+
         # Assign the final df to the class' output_df for the load method
-        self.output_df = df_dot
+        self.output_df = self.df_dot