Skip to content

Add string to int cleaning for USAFacts #488

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 4 commits into from
Nov 10, 2020
Merged

Add string to int cleaning for USAFacts #488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
f20cab9
add cleaning line
chinandrew Nov 10, 2020
934724a
fix whitespace
chinandrew Nov 10, 2020
4b34006
Update tests
chinandrew Nov 10, 2020
78b367b
add test data to other file
chinandrew Nov 10, 2020
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
3 changes: 3 additions & 0 deletions usafacts/delphi_usafacts/pull.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,9 @@ def pull_usafacts_data(base_url: str, metric: str, geo_mapper: GeoMapper) -> pd.
"""
# Read data
df = pd.read_csv(base_url.format(metric=metric)).rename({"countyFIPS":"FIPS"}, axis=1)
# Clean commas in count fields in case the input file included them
df[df.columns[4:]] = df[df.columns[4:]].applymap(
lambda x: int(x.replace(",", "")) if isinstance(x, str) else x)
# Check missing FIPS
null_mask = pd.isnull(df["FIPS"])
assert null_mask.sum() == 0
Expand Down
5 changes: 5 additions & 0 deletions usafacts/tests/test_data/small_deaths_pull.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
countyFIPS,County Name,State,stateFIPS,2/29/20,3/1/20,3/2/20
1,New York City Unallocated/Probable,NY,36,0,0,1
6000,Somewhere,NY,36,11,12,13
2270,Place,NY,36,101,101,"1,0,2"
36009,City,NY,36,2,4,6
19 changes: 13 additions & 6 deletions usafacts/tests/test_pull.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,11 @@
from os.path import join

import pandas as pd
import numpy as np
from delphi_utils import GeoMapper
from delphi_usafacts.pull import pull_usafacts_data

base_url_good = "test_data/small_{metric}.csv"
base_url_good = "test_data/small_{metric}_pull.csv"

base_url_bad = {
"missing_days": "test_data/bad_{metric}_missing_days.csv",
Expand All @@ -21,11 +22,17 @@ class TestPullUSAFacts:
def test_good_file(self):
metric = "deaths"
df = pull_usafacts_data(base_url_good, metric, geo_mapper)

assert (
df.columns.values
== ["fips", "timestamp", "population", "new_counts", "cumulative_counts"]
).all()
expected_df = pd.DataFrame({
"fips": ["00001", "00001", "00001", "36009", "36009", "36009"],
"timestamp": [pd.Timestamp("2020-02-29"), pd.Timestamp("2020-03-01"),
pd.Timestamp("2020-03-02"), pd.Timestamp("2020-02-29"),
pd.Timestamp("2020-03-01"), pd.Timestamp("2020-03-02")],
"population": [np.nan, np.nan, np.nan, 76117., 76117., 76117.],
"new_counts": [0., 0., 1., 2., 2., 2.],
"cumulative_counts": [0, 0, 1, 2, 4, 6]},
index=[1, 2, 3, 5, 6, 7])
# sort since rows order doesn't matter
pd.testing.assert_frame_equal(df.sort_index(), expected_df.sort_index())

def test_missing_days(self):

Expand Down