Skip to content

DOC: Fixing EX01 - Added examples #53554

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
Jun 7, 2023
Merged

DOC: Fixing EX01 - Added examples #53554

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
9d2c7ff
Example for count
DeaMariaLeon Jun 7, 2023
eb5b6f2
Added examples
DeaMariaLeon Jun 7, 2023
4d7b7fa
Merge remote-tracking branch 'upstream/main' into exa-Jun7
DeaMariaLeon Jun 7, 2023
33a25bd
Merged and fixed conflict
DeaMariaLeon Jun 7, 2023
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
10 changes: 0 additions & 10 deletions ci/code_checks.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,11 +263,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
pandas.core.window.ewm.ExponentialMovingWindow.cov \
pandas.api.indexers.BaseIndexer \
pandas.api.indexers.VariableOffsetWindowIndexer \
pandas.core.groupby.DataFrameGroupBy.count \
pandas.core.groupby.DataFrameGroupBy.cummax \
pandas.core.groupby.DataFrameGroupBy.cummin \
pandas.core.groupby.DataFrameGroupBy.cumprod \
pandas.core.groupby.DataFrameGroupBy.cumsum \
pandas.core.groupby.DataFrameGroupBy.diff \
pandas.core.groupby.DataFrameGroupBy.ffill \
pandas.core.groupby.DataFrameGroupBy.max \
Expand All @@ -283,11 +278,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
pandas.core.groupby.DataFrameGroupBy.std \
pandas.core.groupby.DataFrameGroupBy.sum \
pandas.core.groupby.DataFrameGroupBy.var \
pandas.core.groupby.SeriesGroupBy.count \
pandas.core.groupby.SeriesGroupBy.cummax \
pandas.core.groupby.SeriesGroupBy.cummin \
pandas.core.groupby.SeriesGroupBy.cumprod \
pandas.core.groupby.SeriesGroupBy.cumsum \
pandas.core.groupby.SeriesGroupBy.diff \
pandas.core.groupby.SeriesGroupBy.ffill \
pandas.core.groupby.SeriesGroupBy.max \
Expand Down
194 changes: 189 additions & 5 deletions pandas/core/groupby/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2028,7 +2028,7 @@ def all(self, skipna: bool = True):

@final
@Substitution(name="groupby")
@Appender(_common_see_also)
@Substitution(see_also=_common_see_also)
def count(self) -> NDFrameT:
"""
Compute count of group, excluding missing values.
Expand All @@ -2037,6 +2037,38 @@ def count(self) -> NDFrameT:
-------
Series or DataFrame
Count of values within each group.
%(see_also)s
Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([1, 2, np.nan], index=lst)
>>> ser
a 1.0
a 2.0
b NaN
dtype: float64
>>> ser.groupby(level=0).count()
a 2
b 0
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, np.nan, 3], [1, np.nan, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["cow", "horse", "bull"])
>>> df
a b c
cow 1 NaN 3
horse 1 NaN 6
bull 7 8.0 9
>>> df.groupby("a").count()
b c
a
1 0 2
7 1 1
"""
data = self._get_data_to_aggregate()
ids, _, ngroups = self.grouper.group_info
Expand Down Expand Up @@ -3890,7 +3922,7 @@ def rank(

@final
@Substitution(name="groupby")
@Appender(_common_see_also)
@Substitution(see_also=_common_see_also)
def cumprod(
self, axis: Axis | lib.NoDefault = lib.no_default, *args, **kwargs
) -> NDFrameT:
Expand All @@ -3900,6 +3932,41 @@ def cumprod(
Returns
-------
Series or DataFrame
%(see_also)s
Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([6, 2, 0], index=lst)
>>> ser
a 6
a 2
b 0
dtype: int64
>>> ser.groupby(level=0).cumprod()
a 6
a 12
b 0
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["cow", "horse", "bull"])
>>> df
a b c
cow 1 8 2
horse 1 2 5
bull 2 6 9
>>> df.groupby("a").groups
{1: ['cow', 'horse'], 2: ['bull']}
>>> df.groupby("a").cumprod()
b c
cow 8 2
horse 16 10
bull 6 9
"""
nv.validate_groupby_func("cumprod", args, kwargs, ["numeric_only", "skipna"])
if axis is not lib.no_default:
Expand All @@ -3916,7 +3983,7 @@ def cumprod(

@final
@Substitution(name="groupby")
@Appender(_common_see_also)
@Substitution(see_also=_common_see_also)
def cumsum(
self, axis: Axis | lib.NoDefault = lib.no_default, *args, **kwargs
) -> NDFrameT:
Expand All @@ -3926,6 +3993,41 @@ def cumsum(
Returns
-------
Series or DataFrame
%(see_also)s
Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([6, 2, 0], index=lst)
>>> ser
a 6
a 2
b 0
dtype: int64
>>> ser.groupby(level=0).cumsum()
a 6
a 8
b 0
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 2, 5], [2, 6, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["fox", "gorilla", "lion"])
>>> df
a b c
fox 1 8 2
gorilla 1 2 5
lion 2 6 9
>>> df.groupby("a").groups
{1: ['fox', 'gorilla'], 2: ['lion']}
>>> df.groupby("a").cumsum()
b c
fox 8 2
gorilla 10 7
lion 6 9
"""
nv.validate_groupby_func("cumsum", args, kwargs, ["numeric_only", "skipna"])
if axis is not lib.no_default:
Expand All @@ -3942,7 +4044,7 @@ def cumsum(

@final
@Substitution(name="groupby")
@Appender(_common_see_also)
@Substitution(see_also=_common_see_also)
def cummin(
self,
axis: AxisInt | lib.NoDefault = lib.no_default,
Expand All @@ -3955,6 +4057,47 @@ def cummin(
Returns
-------
Series or DataFrame
%(see_also)s
Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = pd.Series([1, 6, 2, 3, 0, 4], index=lst)
>>> ser
a 1
a 6
a 2
b 3
b 0
b 4
dtype: int64
>>> ser.groupby(level=0).cummin()
a 1
a 1
a 1
b 3
b 0
b 0
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, 0, 2], [1, 1, 5], [6, 6, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["snake", "rabbit", "turtle"])
>>> df
a b c
snake 1 0 2
rabbit 1 1 5
turtle 6 6 9
>>> df.groupby("a").groups
{1: ['snake', 'rabbit'], 6: ['turtle']}
>>> df.groupby("a").cummin()
b c
snake 0 2
rabbit 0 2
turtle 6 9
"""
skipna = kwargs.get("skipna", True)
if axis is not lib.no_default:
Expand All @@ -3976,7 +4119,7 @@ def cummin(

@final
@Substitution(name="groupby")
@Appender(_common_see_also)
@Substitution(see_also=_common_see_also)
def cummax(
self,
axis: AxisInt | lib.NoDefault = lib.no_default,
Expand All @@ -3989,6 +4132,47 @@ def cummax(
Returns
-------
Series or DataFrame
%(see_also)s
Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'a', 'b', 'b', 'b']
>>> ser = pd.Series([1, 6, 2, 3, 1, 4], index=lst)
>>> ser
a 1
a 6
a 2
b 3
b 1
b 4
dtype: int64
>>> ser.groupby(level=0).cummax()
a 1
a 6
a 6
b 3
b 3
b 4
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, 8, 2], [1, 1, 0], [2, 6, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["cow", "horse", "bull"])
>>> df
a b c
cow 1 8 2
horse 1 1 0
bull 2 6 9
>>> df.groupby("a").groups
{1: ['cow', 'horse'], 2: ['bull']}
>>> df.groupby("a").cummax()
b c
cow 8 2
horse 8 2
bull 6 9
"""
skipna = kwargs.get("skipna", True)
if axis is not lib.no_default:
Expand Down