Issue 919: Fix too many tracts issue (#922)

* Some cleanup, adding error warning to merge function

* Error handling around tract merge
This commit is contained in:
Lucas Merrill Brown 2021-11-24 16:47:57 -05:00 committed by lucasmbrown-usds
commit a4108d24c0
7 changed files with 105 additions and 70 deletions

View file

@ -1,6 +1,7 @@
import pandas as pd
from data_pipeline.etl.base import ExtractTransformLoad
from data_pipeline.score import field_names
from data_pipeline.utils import get_module_logger
logger = get_module_logger(__name__)
@ -35,6 +36,25 @@ class EJSCREENETL(ExtractTransformLoad):
self.df.rename(
columns={
"ID": self.GEOID_TRACT_FIELD_NAME,
# Note: it is currently unorthodox to use `field_names` in an ETL class,
# but I think that's the direction we'd like to move all ETL classes. - LMB
"ACSTOTPOP": field_names.TOTAL_POP_FIELD,
"CANCER": field_names.AIR_TOXICS_CANCER_RISK_FIELD,
"RESP": field_names.RESPITORY_HAZARD_FIELD,
"DSLPM": field_names.DIESEL_FIELD,
"PM25": field_names.PM25_FIELD,
"OZONE": field_names.OZONE_FIELD,
"PTRAF": field_names.TRAFFIC_FIELD,
"PRMP": field_names.RMP_FIELD,
"PTSDF": field_names.TSDF_FIELD,
"PNPL": field_names.NPL_FIELD,
"PWDIS": field_names.WASTEWATER_FIELD,
"LINGISOPCT": field_names.HOUSEHOLDS_LINGUISTIC_ISO_FIELD,
"LOWINCPCT": field_names.POVERTY_FIELD,
"LESSHSPCT": field_names.HIGH_SCHOOL_ED_FIELD,
"OVER64PCT": field_names.OVER_64_FIELD,
"UNDER5PCT": field_names.UNDER_5_FIELD,
"PRE1960PCT": field_names.LEAD_PAINT_FIELD,
},
inplace=True,
)