Skip to content

[Refactor] Add type hints to geomap.py and a small test refactor #1706

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 3, 2024
Merged

[Refactor] Add type hints to geomap.py and a small test refactor #1706

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
8afaa63
refactor(geomap): add type hints, refactor test_archive
dshemetov May 3, 2024
d4b056e
lint: format geomap.py with black
dshemetov May 3, 2024
677131e
repo: ignore format commit blame
dshemetov May 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .git-blame-ignore-revs
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Format geomap.py with black
d4b056e7a4c11982324e9224c9f9f6fd5d5ec65c
7 changes: 3 additions & 4 deletions _delphi_utils_python/data_proc/geomap/geo_data_proc.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,6 @@
from os import remove, listdir
from os.path import join, isfile
from zipfile import ZipFile
from pandas.core.frame import DataFrame

import requests
import pandas as pd
Expand Down Expand Up @@ -70,8 +69,8 @@ def create_fips_zip_crosswalk():
# Find the population fractions (the heaviest computation, takes about a minute)
# Note that the denominator in the fractions is the source population
pop_df.set_index(["fips", "zip"], inplace=True)
fips_zip: DataFrame = pop_df.groupby("fips", as_index=False).apply(lambda g: g["pop"] / g["pop"].sum())
zip_fips: DataFrame = pop_df.groupby("zip", as_index=False).apply(lambda g: g["pop"] / g["pop"].sum())
fips_zip: pd.DataFrame = pop_df.groupby("fips", as_index=False).apply(lambda g: g["pop"] / g["pop"].sum())
zip_fips: pd.DataFrame = pop_df.groupby("zip", as_index=False).apply(lambda g: g["pop"] / g["pop"].sum())

# Rename and write to file
fips_zip = fips_zip.reset_index(level=["fips", "zip"]).rename(columns={"pop": "weight"}).query("weight > 0.0")
Expand Down Expand Up @@ -228,7 +227,7 @@ def create_state_population_table():
derive_fips_state_crosswalk()

census_pop = pd.read_csv(join(OUTPUT_DIR, FIPS_POPULATION_OUT_FILENAME), dtype={"fips": str, "pop": int})
state: DataFrame = pd.read_csv(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME), dtype=str)
state: pd.DataFrame = pd.read_csv(join(OUTPUT_DIR, FIPS_STATE_OUT_FILENAME), dtype=str)
state_pop = state.merge(census_pop, on="fips").groupby(["state_code", "state_id", "state_name"], as_index=False).sum()
state_pop.sort_values("state_code").to_csv(join(OUTPUT_DIR, STATE_POPULATION_OUT_FILENAME), index=False)

Expand Down
Loading
Loading