Skip to content

Fix FutureWarning in team_results.py #500

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

Open
yasumorishima wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix FutureWarning in team_results.py #500

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3dd8c81
Fix FutureWarning in team_results.py (#459)
yasumorishima Feb 4, 2026
e7d8501
test: add regression test for Unknown attendance to NaN conversion (#…
yasumorishima Jun 15, 2026
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: 1 addition & 1 deletion pybaseball/team_results.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ def get_table(soup: BeautifulSoup, team: str) -> pd.DataFrame:
df = df.rename(columns=df.iloc[0])
df = df.reindex(df.index.drop(0))
df = df.drop('', axis=1) #not a useful column
df['Attendance'].replace(r'^Unknown$', np.nan, regex=True, inplace = True) # make this a NaN so the column can benumeric
df['Attendance'] = df['Attendance'].replace(r'^Unknown$', np.nan, regex=True) # make this a NaN so the column can be numeric
return df

def process_win_streak(data: pd.DataFrame) -> pd.DataFrame:
Expand Down
12 changes: 12 additions & 0 deletions tests/pybaseball/data/team_results.html
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
<html><body>
<table>
<thead>
<tr><th>Gm#</th><th>Date</th><th>Tm</th><th>Opp</th><th>HA</th><th>WL</th><th>R</th><th>RA</th><th>Inn</th><th>Rank</th><th>GB</th><th>Win</th><th>Loss</th><th>Save</th><th>Time</th><th>DN</th><th>Streak</th><th>Attendance</th><th></th></tr>
</thead>
<tbody>
<tr><td>2019-04-01</td><td>NYY</td><td>BAL</td><td>Home</td><td>W</td><td>5</td><td>3</td><td>9</td><td>1</td><td>--</td><td>SmithA</td><td>JonesB</td><td>None</td><td>3:01</td><td>D</td><td>+1</td><td>Unknown</td><td>x</td></tr>
<tr><td>2019-04-02</td><td>NYY</td><td>BAL</td><td>Home</td><td>L</td><td>2</td><td>4</td><td>9</td><td>2</td><td>1.0</td><td>DoeC</td><td>RoeD</td><td>None</td><td>2:55</td><td>N</td><td>-1</td><td>40,000</td><td>x</td></tr>
<tr><td>Description row to be skipped</td></tr>
</tbody>
</table>
</body></html>
19 changes: 19 additions & 0 deletions tests/pybaseball/test_team_results.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
from typing import Callable

from bs4 import BeautifulSoup

from pybaseball.team_results import get_table


def test_get_table_unknown_attendance_becomes_nan(get_data_file_contents: Callable[[str], str]) -> None:
# Regression test for #459: 'Unknown' attendance values must be converted to
# NaN so the column can be made numeric. The previous chained-assignment
# `inplace=True` form silently failed under pandas copy-on-write (and emitted
# a FutureWarning), leaving the value as the string 'Unknown'.
soup = BeautifulSoup(get_data_file_contents('team_results.html'), 'lxml')

result = get_table(soup, 'NYY')

assert 'Attendance' in result.columns
assert result['Attendance'].isna().any()
assert 'Unknown' not in result['Attendance'].tolist()