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

User Story 2152 – Clean up logging (#2155)

Browse source 
Update logging messages and message consistency

This update includes changes to the level of many log messages. Rather than everything being logged at the info level, it differentiates between debug, info, warning, and error messages. It also changes the default log level to info to avoid much of the noise previously in the logs.

It also removes many extra log messages, and adds additional decorators at the beginning of each pipeline run.
This commit is contained in:
Travis Newby 2023-02-08 13:08:55 -06:00 • committed by GitHub
commit 03a6d3c660
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
63 changed files with 307 additions and 339 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -36,7 +36,6 @@ class HudRecapETL(ExtractTransformLoad):
self.df: pd.DataFrame
def extract(self) -> None:
logger.info("Downloading HUD Recap Data")
download = requests.get(
self.HUD_RECAP_CSV_URL,
verify=None,
@ -48,8 +47,6 @@ class HudRecapETL(ExtractTransformLoad):
csv_file.close()
def transform(self) -> None:
logger.info("Transforming HUD Recap Data")
# Load comparison index (CalEnviroScreen 4)
self.df = pd.read_csv(self.HUD_RECAP_CSV, dtype={"GEOID": "string"})
@ -75,7 +72,6 @@ class HudRecapETL(ExtractTransformLoad):
self.df.sort_values(by=self.GEOID_TRACT_FIELD_NAME, inplace=True)
def load(self) -> None:
logger.info("Saving HUD Recap CSV")
# write nationwide csv
self.CSV_PATH.mkdir(parents=True, exist_ok=True)
self.df.to_csv(self.CSV_PATH / "usa.csv", index=False)