Skip to content

DOC: Fixing EX01 - Added more examples #53540

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 5 commits into from
Jun 7, 2023
Merged

DOC: Fixing EX01 - Added more examples #53540

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7610718
Added examples groupby
DeaMariaLeon Jun 6, 2023
27122dc
Merge remote-tracking branch 'upstream/main' into examples-Jun6-2
DeaMariaLeon Jun 6, 2023
f82a9a6
Removed decorator & added 'See Also' inside docstring
DeaMariaLeon Jun 7, 2023
2305098
Merge remote-tracking branch 'upstream/main' into examples-Jun6-2
DeaMariaLeon Jun 7, 2023
2ce2efb
Added @Substitution instead of repeating 'see_also'
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
12 changes: 0 additions & 12 deletions ci/code_checks.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,16 +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.__iter__ \
pandas.core.groupby.SeriesGroupBy.__iter__ \
pandas.core.groupby.DataFrameGroupBy.groups \
pandas.core.groupby.SeriesGroupBy.groups \
pandas.core.groupby.DataFrameGroupBy.indices \
pandas.core.groupby.SeriesGroupBy.indices \
pandas.core.groupby.DataFrameGroupBy.get_group \
pandas.core.groupby.SeriesGroupBy.get_group \
pandas.core.groupby.DataFrameGroupBy.all \
pandas.core.groupby.DataFrameGroupBy.any \
pandas.core.groupby.DataFrameGroupBy.count \
pandas.core.groupby.DataFrameGroupBy.cummax \
pandas.core.groupby.DataFrameGroupBy.cummin \
Expand All @@ -293,8 +283,6 @@ 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.all \
pandas.core.groupby.SeriesGroupBy.any \
pandas.core.groupby.SeriesGroupBy.count \
pandas.core.groupby.SeriesGroupBy.cummax \
pandas.core.groupby.SeriesGroupBy.cummin \
Expand Down
193 changes: 193 additions & 0 deletions pandas/core/groupby/groupby.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -720,6 +720,33 @@ def __repr__(self) -> str:
def groups(self) -> dict[Hashable, np.ndarray]:
"""
Dict {group name -> group labels}.

Examples
--------

For SeriesGroupBy:

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

For DataFrameGroupBy:

>>> data = [[1, 2, 3], [1, 5, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"])
>>> df
a b c
0 1 2 3
1 1 5 6
2 7 8 9
>>> df.groupby(by=["a"]).groups
{1: [0, 1], 7: [2]}
"""
return self.grouper.groups

Expand All @@ -733,6 +760,34 @@ def ngroups(self) -> int:
def indices(self) -> dict[Hashable, npt.NDArray[np.intp]]:
"""
Dict {group name -> group indices}.

Examples
--------

For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([1, 2, 3], index=lst)
>>> ser
a 1
a 2
b 3
dtype: int64
>>> ser.groupby(level=0).indices
{'a': array([0, 1]), 'b': array([2])}

For DataFrameGroupBy:

>>> data = [[1, 2, 3], [1, 5, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["owl", "toucan", "eagle"])
>>> df
a b c
owl 1 2 3
toucan 1 5 6
eagle 7 8 9
>>> df.groupby(by=["a"]).indices
{1: array([0, 1]), 7: array([2])}
"""
return self.grouper.indices

Expand Down Expand Up @@ -867,6 +922,38 @@ def get_group(self, name, obj=None) -> DataFrame | Series:
Returns
-------
same type as obj

Examples
--------

For SeriesGroupBy:

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

For DataFrameGroupBy:

>>> data = [[1, 2, 3], [1, 5, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["owl", "toucan", "eagle"])
>>> df
a b c
owl 1 2 3
toucan 1 5 6
eagle 7 8 9
>>> df.groupby(by=["a"]).get_group(1)
a b c
owl 1 2 3
toucan 1 5 6
"""
if obj is None:
obj = self._selected_obj
Expand All @@ -886,6 +973,47 @@ def __iter__(self) -> Iterator[tuple[Hashable, NDFrameT]]:
-------
Generator yielding sequence of (name, subsetted object)
for each group

Examples
--------

For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([1, 2, 3], index=lst)
>>> ser
a 1
a 2
b 3
dtype: int64
>>> for x, y in ser.groupby(level=0):
... print(f'{x}\\n{y}\\n')
a
a 1
a 2
dtype: int64
b
b 3
dtype: int64

For DataFrameGroupBy:

>>> data = [[1, 2, 3], [1, 5, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"])
>>> df
a b c
0 1 2 3
1 1 5 6
2 7 8 9
>>> for x, y in df.groupby(by=["a"]):
... print(f'{x}\\n{y}\\n')
(1,)
a b c
0 1 2 3
1 1 5 6
(7,)
a b c
2 7 8 9
"""
keys = self.keys
level = self.level
Expand Down Expand Up @@ -1802,6 +1930,38 @@ def any(self, skipna: bool = True):
Series or DataFrame
DataFrame or Series of boolean values, where a value is True if any element
is True within its respective group, False otherwise.

Examples
--------
For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([1, 2, 0], index=lst)
>>> ser
a 1
a 2
b 0
dtype: int64
>>> ser.groupby(level=0).any()
a True
b False
dtype: bool

For DataFrameGroupBy:

>>> data = [[1, 0, 3], [1, 0, 6], [7, 1, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["ostrich", "penguin", "parrot"])
>>> df
a b c
ostrich 1 0 3
penguin 1 0 6
parrot 7 1 9
>>> df.groupby(by=["a"]).any()
b c
a
1 False True
7 True True
"""
return self._cython_agg_general(
"any",
Expand All @@ -1826,6 +1986,39 @@ def all(self, skipna: bool = True):
Series or DataFrame
DataFrame or Series of boolean values, where a value is True if all elements
are True within its respective group, False otherwise.

Examples
--------

For SeriesGroupBy:

>>> lst = ['a', 'a', 'b']
>>> ser = pd.Series([1, 2, 0], index=lst)
>>> ser
a 1
a 2
b 0
dtype: int64
>>> ser.groupby(level=0).all()
a True
b False
dtype: bool

For DataFrameGroupBy:

>>> data = [[1, 0, 3], [1, 5, 6], [7, 8, 9]]
>>> df = pd.DataFrame(data, columns=["a", "b", "c"],
... index=["ostrich", "penguin", "parrot"])
>>> df
a b c
ostrich 1 0 3
penguin 1 5 6
parrot 7 8 9
>>> df.groupby(by=["a"]).all()
b c
a
1 False True
7 True True
"""
return self._cython_agg_general(
"all",
Expand Down