publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-25 20:40:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update HUD Housing Burden (#1005)

Browse source 
* update paths

* size information added in extract function

Co-authored-by: Saran Ahluwalia <sarahluw@cisco.com>
This commit is contained in:
Saran Ahluwalia 2021-12-08 11:57:52 -05:00 • committed by GitHub
commit df675b231a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

12
data/data-pipeline/data_pipeline/etl/sources/hud_housing/etl.py
View file

@ -9,7 +9,7 @@ class HudHousingETL(ExtractTransformLoad):
def __init__(self):
self.OUTPUT_PATH = self.DATA_PATH / "dataset" / "hud_housing"
self.GEOID_TRACT_FIELD_NAME = "GEOID10_TRACT"
self.HOUSING_FTP_URL = "https://www.huduser.gov/portal/datasets/cp/2012thru2016-140-csv.zip"
self.HOUSING_FTP_URL = "https://www.huduser.gov/portal/datasets/cp/2014thru2018-140-csv.zip"
self.HOUSING_ZIP_FILE_DIR = self.TMP_PATH / "hud_housing"
# We measure households earning less than 80% of HUD Area Median Family Income by county
@ -32,7 +32,7 @@ class HudHousingETL(ExtractTransformLoad):
self.df: pd.DataFrame
def extract(self) -> None:
logger.info("Extracting HUD Housing Data")
logger.info("Extracting 1.09 GB HUD Housing Data")
super().extract(
self.HOUSING_FTP_URL,
self.HOUSING_ZIP_FILE_DIR,
@ -42,13 +42,7 @@ class HudHousingETL(ExtractTransformLoad):
logger.info("Transforming HUD Housing Data")
# New file name:
tmp_csv_file_path = (
self.HOUSING_ZIP_FILE_DIR
/ "2012thru2016-140-csv"
/ "2012thru2016-140-csv"
/ "140"
/ "Table8.csv"
)
tmp_csv_file_path = self.HOUSING_ZIP_FILE_DIR / "140" / "Table8.csv"
self.df = pd.read_csv(
filepath_or_buffer=tmp_csv_file_path,
encoding="latin-1",