publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-02-22 17:44:20 -08:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactoring tribal (#1960)

Browse source
This commit is contained in:
Lucas Merrill Brown 2022-09-30 12:04:12 -04:00 • committed by GitHub
parent 247db4acdc
commit f4adf172e3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 52 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
data/data-pipeline/data_pipeline/etl/sources/census_decennial/etl.py
View file

@ -160,9 +160,7 @@ class CensusDecennialETL(ExtractTransformLoad):
# our other demographic data
self.NON_HISPANIC_WHITE_FIELD = "PCT086005" # Total!!White
self.HISPANIC_FIELD = "PCT086006" # Total!!Hispanic or Latino
self.OTHER_RACE_FIELD = (
"PCT086007" # Total!!Other Ethnic Origin or Ra
)
self.OTHER_RACE_FIELD = "PCT086007" # Total!!Other Ethnic Origin or Ra
self.TOTAL_RACE_POPULATION_VI_FIELD = "P003001" # Total
self.BLACK_VI_FIELD = (

76
data/data-pipeline/data_pipeline/etl/sources/tribal/etl.py
View file

@ -2,6 +2,7 @@ from pathlib import Path
import geopandas as gpd
import pandas as pd
from data_pipeline.config import settings
from data_pipeline.etl.base import ExtractTransformLoad
from data_pipeline.score import field_names
from data_pipeline.utils import get_module_logger, unzip_file_from_url
@ -11,9 +12,13 @@ logger = get_module_logger(__name__)
class TribalETL(ExtractTransformLoad):
def __init__(self):
self.GEOJSON_BASE_PATH = self.DATA_PATH / "tribal" / "geojson"
self.GEOGRAPHIC_BASE_PATH = (
self.DATA_PATH / "tribal" / "geographic_data"
)
self.CSV_BASE_PATH = self.DATA_PATH / "tribal" / "csv"
self.NATIONAL_TRIBAL_GEOJSON_PATH = self.GEOJSON_BASE_PATH / "usa.json"
self.NATIONAL_TRIBAL_GEOJSON_PATH = (
self.GEOGRAPHIC_BASE_PATH / "usa.json"
)
self.USA_TRIBAL_DF_LIST = []
def extract(self) -> None:
@ -24,37 +29,57 @@ class TribalETL(ExtractTransformLoad):
"""
logger.info("Downloading Tribal Data")
bia_geojson_url = "https://justice40-data.s3.amazonaws.com/data-sources/BIA_National_LAR_json.zip"
alaska_geojson_url = "https://justice40-data.s3.amazonaws.com/data-sources/Alaska_Native_Villages_json.zip"
bia_shapefile_zip_url = (
settings.AWS_JUSTICE40_DATASOURCES_URL
+ "/BIA_National_LAR_updated_20220929.zip"
)
tsa_and_aian_geojson_zip_url = (
settings.AWS_JUSTICE40_DATASOURCES_URL
+ "/BIA_TSA_and_AIAN_json.zip"
)
alaska_geojson_url = (
settings.AWS_JUSTICE40_DATASOURCES_URL
+ "/Alaska_Native_Villages_json.zip"
)
unzip_file_from_url(
bia_geojson_url,
bia_shapefile_zip_url,
self.TMP_PATH,
self.DATA_PATH / "tribal" / "geojson" / "bia_national_lar",
self.GEOGRAPHIC_BASE_PATH / "bia_national_lar",
)
unzip_file_from_url(
tsa_and_aian_geojson_zip_url,
self.TMP_PATH,
self.GEOGRAPHIC_BASE_PATH / "tsa_and_aian",
)
unzip_file_from_url(
alaska_geojson_url,
self.TMP_PATH,
self.DATA_PATH / "tribal" / "geojson" / "alaska_native_villages",
self.GEOGRAPHIC_BASE_PATH / "alaska_native_villages",
)
pass
def _transform_bia_national_lar(self, tribal_geojson_path: Path) -> None:
def _transform_bia_national_lar(self, path: Path) -> None:
"""Transform the Tribal BIA National Lar Geodataframe and appends it to the
national Tribal Dataframe List
Args:
tribal_geojson_path (Path): the Path to the Tribal Geojson
path (Path): the Path to the BIA National Lar
Returns:
None
"""
bia_national_lar_df = gpd.read_file(tribal_geojson_path)
bia_national_lar_df = gpd.read_file(path)
# DELETE
logger.info(f"Columns: {bia_national_lar_df.columns}\n")
bia_national_lar_df.drop(
["OBJECTID", "GISAcres", "Shape_Length", "Shape_Area"],
["GISAcres"],
axis=1,
inplace=True,
)
@ -162,29 +187,30 @@ class TribalETL(ExtractTransformLoad):
"""
logger.info("Transforming Tribal Data")
# load the geojsons
bia_national_lar_geojson = (
self.GEOJSON_BASE_PATH
/ "bia_national_lar"
/ "BIA_National_LAR.json"
# Set the filepaths:
bia_national_lar_shapefile = (
self.GEOGRAPHIC_BASE_PATH / "bia_national_lar"
)
bia_aian_supplemental_geojson = (
self.GEOJSON_BASE_PATH
/ "bia_national_lar"
self.GEOGRAPHIC_BASE_PATH
/ "tsa_and_aian"
/ "BIA_AIAN_Supplemental.json"
)
bia_tsa_geojson_geojson = (
self.GEOJSON_BASE_PATH / "bia_national_lar" / "BIA_TSA.json"
bia_tsa_geojson = (
self.GEOGRAPHIC_BASE_PATH / "tsa_and_aian" / "BIA_TSA.json"
)
alaska_native_villages_geojson = (
self.GEOJSON_BASE_PATH
self.GEOGRAPHIC_BASE_PATH
/ "alaska_native_villages"
/ "AlaskaNativeVillages.gdb.geojson"
)
self._transform_bia_national_lar(bia_national_lar_geojson)
self._transform_bia_national_lar(bia_national_lar_shapefile)
self._transform_bia_aian_supplemental(bia_aian_supplemental_geojson)
self._transform_bia_tsa(bia_tsa_geojson_geojson)
self._transform_bia_tsa(bia_tsa_geojson)
self._transform_alaska_native_villages(alaska_native_villages_geojson)
def load(self) -> None:
@ -194,13 +220,13 @@ class TribalETL(ExtractTransformLoad):
None
"""
logger.info("Saving Tribal GeoJson and CSV")
usa_tribal_df = gpd.GeoDataFrame(
pd.concat(self.USA_TRIBAL_DF_LIST, ignore_index=True)
)
usa_tribal_df = usa_tribal_df.to_crs(
"+proj=longlat +ellps=WGS84 +datum=WGS84 +no_defs"
)
logger.info("Writing national geojson file")
usa_tribal_df.to_file(
self.NATIONAL_TRIBAL_GEOJSON_PATH, driver="GeoJSON"