mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-02-24 18:44:20 -08:00
876655d2b2
* Refactor CDC life-expectancy (1554) * Update to new tract list (#1554) * Adjust for tests (#1848) * Add tests for cdc_places (#1848) * Add EJScreen tests (#1848) * Add tests for HUD housing (#1848) * Add tests for GeoCorr (#1848) * Add persistent poverty tests (#1848) * Update for sources without zips, for new validation (#1848) * Update tests for new multi-CSV but (#1848) Lucas updated the CDC life expectancy data to handle a bug where two states are missing from the US Overall download. Since virtually none of our other ETL classes download multiple CSVs directly like this, it required a pretty invasive new mocking strategy. * Add basic tests for nature deprived (#1848) * Add wildfire tests (#1848) * Add flood risk tests (#1848) * Add DOT travel tests (#1848) * Add historic redlining tests (#1848) * Add tests for ME and WI (#1848) * Update now that validation exists (#1848) * Adjust for validation (#1848) * Add health insurance back to cdc places (#1848) Ooops * Update tests with new field (#1848) * Test for blank tract removal (#1848) * Add tracts for clipping behavior * Test clipping and zfill behavior (#1848) * Fix bad test assumption (#1848) * Simplify class, add test for tract padding (#1848) * Fix percentage inversion, update tests (#1848) Looking through the transformations, I noticed that we were subtracting a percentage that is usually between 0-100 from 1 instead of 100, and so were endind up with some surprising results. Confirmed with lucasmbrown-usds * Add note about first street data (#1848)
80 lines
2.2 KiB
Python
80 lines
2.2 KiB
Python
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, ValidGeoLevel
|
|
from data_pipeline.etl.sources.geo_utils import add_tracts_for_geometries
|
|
from data_pipeline.utils import get_module_logger
|
|
|
|
logger = get_module_logger(__name__)
|
|
|
|
|
|
class AbandonedMineETL(ExtractTransformLoad):
|
|
"""Data from Office Of Surface Mining Reclamation and Enforcement's
|
|
eAMLIS. These are the locations of abandoned mines.
|
|
"""
|
|
|
|
# Metadata for the baseclass
|
|
NAME = "eamlis"
|
|
GEO_LEVEL = ValidGeoLevel.CENSUS_TRACT
|
|
AML_BOOLEAN: str
|
|
LOAD_YAML_CONFIG: bool = True
|
|
|
|
PUERTO_RICO_EXPECTED_IN_DATA = False
|
|
EXPECTED_MISSING_STATES = [
|
|
"10",
|
|
"11",
|
|
"12",
|
|
"15",
|
|
"23",
|
|
"27",
|
|
"31",
|
|
"33",
|
|
"34",
|
|
"36",
|
|
"45",
|
|
"50",
|
|
"55",
|
|
]
|
|
|
|
# Define these for easy code completion
|
|
def __init__(self):
|
|
self.SOURCE_URL = (
|
|
settings.AWS_JUSTICE40_DATASOURCES_URL
|
|
+ "/eAMLIS export of all data.tsv.zip"
|
|
)
|
|
|
|
self.TRACT_INPUT_COLUMN_NAME = self.INPUT_GEOID_TRACT_FIELD_NAME
|
|
|
|
self.OUTPUT_PATH: Path = (
|
|
self.DATA_PATH / "dataset" / "abandoned_mine_land_inventory_system"
|
|
)
|
|
|
|
self.COLUMNS_TO_KEEP = [
|
|
self.GEOID_TRACT_FIELD_NAME,
|
|
self.AML_BOOLEAN,
|
|
]
|
|
|
|
self.output_df: pd.DataFrame
|
|
|
|
def transform(self) -> None:
|
|
logger.info("Starting eAMLIS transforms.")
|
|
df = pd.read_csv(
|
|
self.get_tmp_path() / "eAMLIS export of all data.tsv",
|
|
sep="\t",
|
|
low_memory=False,
|
|
)
|
|
gdf = gpd.GeoDataFrame(
|
|
df,
|
|
geometry=gpd.points_from_xy(
|
|
x=df["Longitude"],
|
|
y=df["Latitude"],
|
|
),
|
|
crs="epsg:4326",
|
|
)
|
|
gdf = gdf.drop_duplicates(subset=["geometry"], keep="last")
|
|
gdf_tracts = add_tracts_for_geometries(gdf)
|
|
gdf_tracts = gdf_tracts.drop_duplicates(self.GEOID_TRACT_FIELD_NAME)
|
|
gdf_tracts[self.AML_BOOLEAN] = True
|
|
self.output_df = gdf_tracts[self.COLUMNS_TO_KEEP]
|