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

Jump to bottom

FIX-#4154: add value_counts method for SeriesGroupBy and DataFrameGroupBy #5453

Merged
merged 1 commit into from
Dec 16, 2022
Merged

FIX-#4154: add value_counts method for SeriesGroupBy and DataFrameGroupBy #5453

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
36 changes: 36 additions & 0 deletions modin/pandas/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,6 +160,24 @@ def ffill(self, limit=None):
def sem(self, ddof=1):
return self._default_to_pandas(lambda df: df.sem(ddof=ddof))

def value_counts(
self,
subset=None,
normalize: bool = False,
sort: bool = True,
ascending: bool = False,
dropna: bool = True,
):
return self._default_to_pandas(
lambda df: df.value_counts(
subset=subset,
normalize=normalize,
sort=sort,
ascending=ascending,
dropna=dropna,
)
)

def mean(self, numeric_only=None):
return self._check_index(
self._wrap_aggregation(
Expand Down Expand Up @@ -1262,6 +1280,24 @@ def _iter(self):
for k in (sorted(group_ids) if self._sort else group_ids)
)

def value_counts(
self,
normalize: bool = False,
sort: bool = True,
ascending: bool = False,
bins=None,
dropna: bool = True,
):
return self._default_to_pandas(
lambda ser: ser.value_counts(
normalize=normalize,
sort=sort,
ascending=ascending,
bins=bins,
dropna=dropna,
)
)


if IsExperimental.get():
from modin.experimental.cloud.meta_magic import make_wrapped_class
Expand Down
10 changes: 10 additions & 0 deletions modin/pandas/test/test_groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,6 +198,7 @@ def test_mixed_dtypes_groupby(as_index):
eval_sum(modin_groupby, pandas_groupby)
eval_ngroup(modin_groupby, pandas_groupby)
eval_nunique(modin_groupby, pandas_groupby)
eval_value_counts(modin_groupby, pandas_groupby)
eval_median(modin_groupby, pandas_groupby)
eval_general(modin_groupby, pandas_groupby, lambda df: df.head(n))
eval_cumprod(modin_groupby, pandas_groupby)
Expand Down Expand Up @@ -591,6 +592,7 @@ def test_single_group_row_groupby():
eval_sum(modin_groupby, pandas_groupby)
eval_ngroup(modin_groupby, pandas_groupby)
eval_nunique(modin_groupby, pandas_groupby)
eval_value_counts(modin_groupby, pandas_groupby)
eval_median(modin_groupby, pandas_groupby)
eval_general(modin_groupby, pandas_groupby, lambda df: df.head(n))
eval_cumprod(modin_groupby, pandas_groupby)
Expand Down Expand Up @@ -709,6 +711,7 @@ def test_large_row_groupby(is_by_category):
eval_sum(modin_groupby, pandas_groupby)
eval_ngroup(modin_groupby, pandas_groupby)
eval_nunique(modin_groupby, pandas_groupby)
eval_value_counts(modin_groupby, pandas_groupby)
eval_median(modin_groupby, pandas_groupby)
eval_general(modin_groupby, pandas_groupby, lambda df: df.head(n))
# eval_cumprod(modin_groupby, pandas_groupby) causes overflows
Expand Down Expand Up @@ -816,6 +819,8 @@ def test_simple_col_groupby():
# Pandas fails on this case with ValueError
# eval_ngroup(modin_groupby, pandas_groupby)
# eval_nunique(modin_groupby, pandas_groupby)
# NotImplementedError: DataFrameGroupBy.value_counts only handles axis=0
# eval_value_counts(modin_groupby, pandas_groupby)
eval_median(modin_groupby, pandas_groupby)
eval_general(
modin_groupby,
Expand Down Expand Up @@ -942,6 +947,7 @@ def test_series_groupby(by, as_index_series_or_dataframe):
eval_size(modin_groupby, pandas_groupby)
eval_ngroup(modin_groupby, pandas_groupby)
eval_nunique(modin_groupby, pandas_groupby)
eval_value_counts(modin_groupby, pandas_groupby)
eval_median(modin_groupby, pandas_groupby)
eval_general(modin_groupby, pandas_groupby, lambda df: df.head(n))
eval_cumprod(modin_groupby, pandas_groupby)
Expand Down Expand Up @@ -1076,6 +1082,10 @@ def eval_nunique(modin_groupby, pandas_groupby):
df_equals(modin_groupby.nunique(), pandas_groupby.nunique())


def eval_value_counts(modin_groupby, pandas_groupby):
df_equals(modin_groupby.value_counts(), pandas_groupby.value_counts())


def eval_median(modin_groupby, pandas_groupby):
modin_df_almost_equals_pandas(modin_groupby.median(), pandas_groupby.median())

Expand Down