mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-28 14:21:16 -07:00
updating ejscreen data, try two (#1747)
This commit is contained in:
parent
7559cf46f6
commit
2ab24c60fa
4 changed files with 11 additions and 14 deletions
|
@ -8,16 +8,14 @@ logger = get_module_logger(__name__)
|
|||
|
||||
|
||||
class EJSCREENETL(ExtractTransformLoad):
|
||||
"""Load EJSCREEN data.
|
||||
|
||||
Data dictionary:
|
||||
https://gaftp.epa.gov/EJSCREEN/2019/2019_EJSCREEN_columns_explained.csv
|
||||
"""
|
||||
"""Load updated EJSCREEN data."""
|
||||
|
||||
def __init__(self):
|
||||
self.EJSCREEN_FTP_URL = "https://edap-arcgiscloud-data-commons.s3.amazonaws.com/EJSCREEN2020/EJSCREEN_Tract_2020_USPR.csv.zip"
|
||||
self.EJSCREEN_CSV = self.get_tmp_path() / "EJSCREEN_Tract_2020_USPR.csv"
|
||||
self.CSV_PATH = self.DATA_PATH / "dataset" / "ejscreen_2019"
|
||||
self.EJSCREEN_FTP_URL = "https://gaftp.epa.gov/EJSCREEN/2021/EJSCREEN_2021_USPR_Tracts.csv.zip"
|
||||
self.EJSCREEN_CSV = (
|
||||
self.get_tmp_path() / "EJSCREEN_2021_USPR_Tracts.csv"
|
||||
)
|
||||
self.CSV_PATH = self.DATA_PATH / "dataset" / "ejscreen"
|
||||
self.df: pd.DataFrame
|
||||
|
||||
self.COLUMNS_TO_KEEP = [
|
||||
|
@ -39,6 +37,7 @@ class EJSCREENETL(ExtractTransformLoad):
|
|||
field_names.OVER_64_FIELD,
|
||||
field_names.UNDER_5_FIELD,
|
||||
field_names.LEAD_PAINT_FIELD,
|
||||
field_names.UST_FIELD,
|
||||
]
|
||||
|
||||
def extract(self) -> None:
|
||||
|
@ -53,7 +52,7 @@ class EJSCREENETL(ExtractTransformLoad):
|
|||
logger.info("Transforming EJScreen Data")
|
||||
self.df = pd.read_csv(
|
||||
self.EJSCREEN_CSV,
|
||||
dtype={"ID": "string"},
|
||||
dtype={"ID": str},
|
||||
# EJSCREEN writes the word "None" for NA data.
|
||||
na_values=["None"],
|
||||
low_memory=False,
|
||||
|
@ -63,8 +62,6 @@ 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.RESPIRATORY_HAZARD_FIELD,
|
||||
|
@ -81,6 +78,7 @@ class EJSCREENETL(ExtractTransformLoad):
|
|||
"OVER64PCT": field_names.OVER_64_FIELD,
|
||||
"UNDER5PCT": field_names.UNDER_5_FIELD,
|
||||
"PRE1960PCT": field_names.LEAD_PAINT_FIELD,
|
||||
"UST": field_names.UST_FIELD, # added for 2021 update
|
||||
},
|
||||
inplace=True,
|
||||
)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue