Skip to content
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

[BEAM-14474] Suppress 'Mean of empty slice' Runtime Warning in dataframe unit test #17682

Merged
merged 2 commits into from
May 18, 2022
Merged

[BEAM-14474] Suppress 'Mean of empty slice' Runtime Warning in dataframe unit test #17682

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9920440
[BEAM-14474] Suppress 'Mean of empty slice' Runtime Warning in datafr…
Abacn May 16, 2022
0a93326
use catch_warnings context manager
Abacn May 16, 2022
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
26 changes: 12 additions & 14 deletions sdks/python/apache_beam/dataframe/frames_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@

import re
import unittest
import warnings

import numpy as np
import pandas as pd
Expand Down Expand Up @@ -1601,6 +1602,11 @@ def test_pivot_no_index_provided_on_multiindex(self):

class GroupByTest(_AbstractFrameTest):
"""Tests for DataFrame/Series GroupBy operations."""
@staticmethod
def median_sum_fn(x):
warnings.filterwarnings("ignore", message="Mean of empty slice")
return (x.foo + x.bar).median()
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we use a context here to make sure the filters get reset?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the suggestion. Applied.


@parameterized.expand(ALL_GROUPING_AGGREGATIONS)
def test_groupby_agg(self, agg_type):
if agg_type == 'describe' and PD_VERSION < (1, 2):
Expand Down Expand Up @@ -1723,28 +1729,24 @@ def test_groupby_callable(self):

def test_groupby_apply(self):
df = GROUPBY_DF

def median_sum_fn(x):
return (x.foo + x.bar).median()

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: I would actually keep these where they are and just duplicate the filterwarnings calls, so that the tests are more self-contained and easy to inspect (but I'm also fine with the move if you prefer it that way)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah I agree with the idea. Given the amount of code added I considered pick up them into a separate helper function. Nevertheless it is still in the GroupByTest test class.

# Note this is the same as DataFrameGroupBy.describe. Using it here is
# just a convenient way to test apply() with a user fn that returns a Series
describe = lambda df: df.describe()

self._run_test(lambda df: df.groupby('group').foo.apply(describe), df)
self._run_test(
lambda df: df.groupby('group')[['foo', 'bar']].apply(describe), df)
self._run_test(lambda df: df.groupby('group').apply(median_sum_fn), df)
self._run_test(lambda df: df.groupby('group').apply(self.median_sum_fn), df)
self._run_test(
lambda df: df.set_index('group').foo.groupby(level=0).apply(describe),
df)
self._run_test(lambda df: df.groupby(level=0).apply(median_sum_fn), df)
self._run_test(lambda df: df.groupby(level=0).apply(self.median_sum_fn), df)
self._run_test(lambda df: df.groupby(lambda x: x % 3).apply(describe), df)
self._run_test(
lambda df: df.bar.groupby(lambda x: x % 3).apply(describe), df)
self._run_test(
lambda df: df.set_index(['str', 'group', 'bool']).groupby(
level='group').apply(median_sum_fn),
level='group').apply(self.median_sum_fn),
df)

def test_groupby_apply_preserves_column_order(self):
Expand Down Expand Up @@ -1830,9 +1832,7 @@ def test_groupby_level_agg(self, level):
self._run_test(
lambda df: df.groupby(level=level).sum(numeric_only=True), df)
self._run_test(
lambda df: df.groupby(level=level).apply(
lambda x: (x.foo + x.bar).median()),
df)
lambda df: df.groupby(level=level).apply(self.median_sum_fn), df)

@unittest.skipIf(PD_VERSION < (1, 1), "drop_na added in pandas 1.1.0")
def test_groupby_count_na(self):
Expand Down Expand Up @@ -1892,17 +1892,15 @@ def test_series_groupby_series(self, agg_type):
def test_groupby_series_apply(self):
df = GROUPBY_DF

def median_sum_fn(x):
return (x.foo + x.bar).median()

# Note this is the same as DataFrameGroupBy.describe. Using it here is
# just a convenient way to test apply() with a user fn that returns a Series
describe = lambda df: df.describe()

self._run_test(lambda df: df.groupby(df.group).foo.apply(describe), df)
self._run_test(
lambda df: df.groupby(df.group)[['foo', 'bar']].apply(describe), df)
self._run_test(lambda df: df.groupby(df.group).apply(median_sum_fn), df)
self._run_test(
lambda df: df.groupby(df.group).apply(self.median_sum_fn), df)

def test_groupby_multiindex_keep_nans(self):
# Due to https://github.com/pandas-dev/pandas/issues/36470
Expand Down
2 changes: 2 additions & 0 deletions sdks/python/apache_beam/dataframe/transforms_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@

import typing
import unittest
import warnings

import pandas as pd

Expand Down Expand Up @@ -132,6 +133,7 @@ def test_groupby_apply(self):
})

def median_sum_fn(x):
warnings.filterwarnings("ignore", message="Mean of empty slice")
return (x.foo + x.bar).median()

describe = lambda df: df.describe()
Expand Down