mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-28 14:51:16 -07:00
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
This commit is contained in:
parent
4d9c1dd11e
commit
6f39033dde
52 changed files with 1787 additions and 686 deletions
|
@ -4,6 +4,7 @@ import geopandas as gpd
|
|||
import numpy as np
|
||||
import pandas as pd
|
||||
from data_pipeline.etl.base import ExtractTransformLoad
|
||||
from data_pipeline.etl.datasource import DataSource
|
||||
from data_pipeline.etl.base import ValidGeoLevel
|
||||
from data_pipeline.etl.sources.geo_utils import add_tracts_for_geometries
|
||||
from data_pipeline.etl.sources.geo_utils import get_tract_geojson
|
||||
|
@ -67,6 +68,9 @@ class TribalOverlapETL(ExtractTransformLoad):
|
|||
self.census_tract_gdf: gpd.GeoDataFrame
|
||||
self.tribal_gdf: gpd.GeoDataFrame
|
||||
|
||||
def get_data_sources(self) -> [DataSource]:
|
||||
return [] # this uses already retrieved / calculated data
|
||||
|
||||
@staticmethod
|
||||
def _create_string_from_list(series: pd.Series) -> str:
|
||||
"""Helper method that creates a sorted string list (for tribal names)."""
|
||||
|
@ -89,7 +93,12 @@ class TribalOverlapETL(ExtractTransformLoad):
|
|||
|
||||
return percentage_float
|
||||
|
||||
def extract(self) -> None:
|
||||
def extract(self, use_cached_data_sources: bool = False) -> None:
|
||||
|
||||
super().extract(
|
||||
use_cached_data_sources
|
||||
) # download and extract data sources
|
||||
|
||||
self.census_tract_gdf = get_tract_geojson()
|
||||
self.tribal_gdf = get_tribal_geojson()
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue