publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-07-28 08:21:16 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cleaning up quick code (#1349)

Browse source 
Did some quick, mostly cosmetic changes and updates to the quick launch changes. This mostly entailed changing strings to constants and cleaning up some code to make it neater.

Changes -- PR AMI, updating ag loss, and dropping pr from some threshold counts.
This commit is contained in:
Emma Nechamkin 2022-03-02 16:50:04 -05:00 • committed by GitHub
commit aea49cbb5a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
6 changed files with 341 additions and 348 deletions
Download patch file Download diff file Expand all files Collapse all files

4
data/data-pipeline/data_pipeline/etl/score/constants.py
View file

@ -22,7 +22,6 @@ DATA_CENSUS_CSV_DIR = DATA_CENSUS_DIR / "csv"
DATA_CENSUS_CSV_FILE_PATH = DATA_CENSUS_CSV_DIR / "us.csv"
DATA_CENSUS_CSV_STATE_FILE_PATH = DATA_CENSUS_CSV_DIR / "fips_states_2010.csv"
# Score paths
DATA_SCORE_DIR = DATA_PATH / "score"
@ -66,6 +65,9 @@ CENSUS_COUNTIES_COLUMNS = ["USPS", "GEOID", "NAME"]
# Drop FIPS codes from map
DROP_FIPS_CODES = ["66", "78"]
# Drop FIPS codes from incrementing
DROP_FIPS_FROM_NON_WTD_THRESHOLDS = "72"
# Percent prefixes for rounding
PERCENT_PREFIXES_SUFFIXES = [
"Percent",

35
data/data-pipeline/data_pipeline/etl/score/etl_score.py
View file

@ -298,33 +298,20 @@ class ScoreETL(ExtractTransformLoad):
] = df[input_column_name].rank(pct=True, ascending=ascending)
else:
# For agricultural loss, we are using whether there is value at all to determine percentile
# This is not the most thoughtfully written code, but it works.
# Take only rows with agrivalue
tmp_df = df[df[field_names.AGRICULTURAL_VALUE_BOOL_FIELD] == 1][
[input_column_name, field_names.GEOID_TRACT_FIELD]
].copy()
# Construct a percentile only among those tracts
tmp_df["temporary_ranking"] = tmp_df[input_column_name].transform(
lambda x: x.rank(pct=True, ascending=True)
)
# # Create a map for just those tracts and map it onto the df
temporary_ranking = tmp_df.set_index(field_names.GEOID_TRACT_FIELD)[
"temporary_ranking"
].to_dict()
# For agricultural loss, we are using whether there is value at all to determine percentile and then
# filling places where the value is False with 0
df[
f"{output_column_name_root}"
f"{field_names.PERCENTILE_FIELD_SUFFIX}"
] = np.where(
df[field_names.AGRICULTURAL_VALUE_BOOL_FIELD].isna(),
np.nan,
df[field_names.GEOID_TRACT_FIELD]
.map(temporary_ranking)
.fillna(0),
] = (
df.where(
df[field_names.AGRICULTURAL_VALUE_BOOL_FIELD].astype(float)
== 1.0
)[input_column_name]
.rank(ascending=ascending, pct=True)
.fillna(
df[field_names.AGRICULTURAL_VALUE_BOOL_FIELD].astype(float)
)
)
# Create the urban/rural percentiles.