publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-29 13:41:17 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update to use new FSF files (#1838)

Browse source 
backend is partially done!
This commit is contained in:
Emma Nechamkin 2022-08-18 15:54:44 -04:00 • committed by GitHub
commit 3ba1c620f5
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
8 changed files with 24 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

14
data/data-pipeline/data_pipeline/etl/sources/fsf_flood_risk/etl.py
View file

@ -27,7 +27,7 @@ class FloodRiskETL(ExtractTransformLoad):
def __init__(self):
# define the full path for the input CSV file
self.INPUT_CSV = (
self.get_tmp_path() / "fsf_flood" / "flood_tract_2010.csv"
self.get_tmp_path() / "fsf_flood" / "flood-tract2010.csv"
)
# this is the main dataframe
@ -50,24 +50,16 @@ class FloodRiskETL(ExtractTransformLoad):
# read in the unzipped csv data source then rename the
# Census Tract column for merging
df_fsf_flood_disagg: pd.DataFrame = pd.read_csv(
df_fsf_flood: pd.DataFrame = pd.read_csv(
self.INPUT_CSV,
dtype={self.INPUT_GEOID_TRACT_FIELD_NAME: str},
low_memory=False,
)
df_fsf_flood_disagg[self.GEOID_TRACT_FIELD_NAME] = df_fsf_flood_disagg[
df_fsf_flood[self.GEOID_TRACT_FIELD_NAME] = df_fsf_flood[
self.INPUT_GEOID_TRACT_FIELD_NAME
].str.zfill(11)
# Because we have some tracts that are listed twice, we aggregate based on
# GEOID10_TRACT. Note that I haven't confirmed this with the FSF boys -- to do!
df_fsf_flood = (
df_fsf_flood_disagg.groupby(self.GEOID_TRACT_FIELD_NAME)
.sum()
.reset_index()
)
df_fsf_flood[self.COUNT_PROPERTIES] = df_fsf_flood[
self.COUNT_PROPERTIES_NATIVE_FIELD_NAME
].clip(lower=self.CLIP_PROPERTIES_COUNT)