publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 15:01:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Poetry updates for application (#483)

Browse source
This commit is contained in:
Jorge Escobar 2021-08-06 16:24:30 -04:00 • committed by GitHub
commit f51b0d69d9
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 31 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

5
data/data-pipeline/data_pipeline/etl/runner.py
View file

@ -17,11 +17,6 @@ def etl_runner(dataset_to_run: str = None) -> None:
# this list comes from YAMLs
dataset_list = [
{
"name": "census",
"module_dir": "census",
"class_name": "CensusETL",
},
{
"name": "tree_equity_score",
"module_dir": "tree_equity_score",

16
data/data-pipeline/data_pipeline/etl/sources/census/etl.py
View file

@ -72,14 +72,14 @@ class CensusETL(ExtractTransformLoad):
f"{fips_code} shp file does not exist. Downloading and extracting shape file"
)
# 2020 tiger data is here: https://www2.census.gov/geo/tiger/TIGER2020/BG/
# But using 2010 for now
cbg_state_url = f"https://www2.census.gov/geo/tiger/TIGER2010/BG/2010/tl_2010_{fips_code}_bg10.zip"
unzip_file_from_url(
cbg_state_url,
self.TMP_PATH,
self.DATA_PATH / "census" / "shp" / fips_code,
)
# 2020 tiger data is here: https://www2.census.gov/geo/tiger/TIGER2020/BG/
# But using 2010 for now
cbg_state_url = f"https://www2.census.gov/geo/tiger/TIGER2010/BG/2010/tl_2010_{fips_code}_bg10.zip"
unzip_file_from_url(
cbg_state_url,
self.TMP_PATH,
self.DATA_PATH / "census" / "shp" / fips_code,
)
def extract(self) -> None:
logger.info("Downloading Census Data")