From d4d72c883087a938d140c1b142fd0f66fdd2bcbc Mon Sep 17 00:00:00 2001 From: lucasmbrown-usds Date: Wed, 21 Sep 2022 15:01:26 -0400 Subject: [PATCH] placeholder etl files --- .../sources/geocorr_alternatives/README.md | 0 .../sources/geocorr_alternatives/__init__.py | 0 .../etl/sources/geocorr_alternatives/etl.py | 38 +++++++++++++++++++ 3 files changed, 38 insertions(+) create mode 100644 data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/README.md create mode 100644 data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/__init__.py create mode 100644 data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/etl.py diff --git a/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/README.md b/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/README.md new file mode 100644 index 00000000..e69de29b diff --git a/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/__init__.py b/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/etl.py b/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/etl.py new file mode 100644 index 00000000..4b188129 --- /dev/null +++ b/data/data-pipeline/data_pipeline/etl/sources/geocorr_alternatives/etl.py @@ -0,0 +1,38 @@ +import geopandas as gpd +import numpy as np +import pandas as pd +from data_pipeline.etl.base import ExtractTransformLoad, ValidGeoLevel +from data_pipeline.etl.sources.geo_utils import ( + add_tracts_for_geometries, + get_tribal_geojson, + get_tract_geojson, +) +from data_pipeline.score import field_names +from data_pipeline.utils import get_module_logger + +logger = get_module_logger(__name__) + + +class GeoCorrAlternativesETL(ExtractTransformLoad): + """Calculates overlap between Census tracts & various alternative geographies.""" + + # Metadata for the baseclass + NAME = "geocorr_alternatives" + GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT + + # Define these for easy code completion + def __init__(self): + self.COLUMNS_TO_KEEP = [ + self.GEOID_TRACT_FIELD_NAME, + ] + + self.output_df: pd.DataFrame + + def extract(self) -> None: + pass + + def transform(self) -> None: + logger.info("Starting GeoCorr alternatives transforms.") + + # self.output_df = +