from collections.abc import (
    Callable,
    Hashable,
    Mapping,
    Sequence,
)
import datetime
from typing import (
    Literal,
    overload,
)

import numpy as np
import pandas as pd
from pandas.core.frame import DataFrame
from pandas.core.groupby.grouper import Grouper
from pandas.core.indexes.base import Index
from pandas.core.series import Series
from typing_extensions import TypeAlias

from pandas._typing import (
    AnyArrayLike,
    ArrayLike,
    HashableT1,
    HashableT2,
    HashableT3,
    Label,
    Scalar,
    ScalarT,
    npt,
)

_PivotAggCallable: TypeAlias = Callable[[Series], ScalarT]

_PivotAggFunc: TypeAlias = (
    _PivotAggCallable
    | np.ufunc
    | Literal["mean", "sum", "count", "min", "max", "median", "std", "var"]
)

_NonIterableHashable: TypeAlias = (
    str
    | datetime.date
    | datetime.datetime
    | datetime.timedelta
    | bool
    | int
    | float
    | complex
    | pd.Timestamp
    | pd.Timedelta
)

_PivotTableIndexTypes: TypeAlias = (
    Label | Sequence[HashableT1] | Series | Grouper | None
)
_PivotTableColumnsTypes: TypeAlias = (
    Label | Sequence[HashableT2] | Series | Grouper | None
)
_PivotTableValuesTypes: TypeAlias = Label | Sequence[HashableT3] | None

_ExtendedAnyArrayLike: TypeAlias = AnyArrayLike | ArrayLike

@overload
def pivot_table(
    data: DataFrame,
    values: _PivotTableValuesTypes = ...,
    index: _PivotTableIndexTypes = ...,
    columns: _PivotTableColumnsTypes = ...,
    aggfunc: (
        _PivotAggFunc | Sequence[_PivotAggFunc] | Mapping[Hashable, _PivotAggFunc]
    ) = ...,
    fill_value: Scalar | None = ...,
    margins: bool = ...,
    dropna: bool = ...,
    margins_name: str = ...,
    observed: bool = ...,
    sort: bool = ...,
) -> DataFrame:
    """
Create a spreadsheet-style pivot table as a DataFrame.

The levels in the pivot table will be stored in MultiIndex objects
(hierarchical indexes) on the index and columns of the result DataFrame.

Parameters
----------
data : DataFrame
values : list-like or scalar, optional
    Column or columns to aggregate.
index : column, Grouper, array, or list of the previous
    Keys to group by on the pivot table index. If a list is passed,
    it can contain any of the other types (except list). If an array is
    passed, it must be the same length as the data and will be used in
    the same manner as column values.
columns : column, Grouper, array, or list of the previous
    Keys to group by on the pivot table column. If a list is passed,
    it can contain any of the other types (except list). If an array is
    passed, it must be the same length as the data and will be used in
    the same manner as column values.
aggfunc : function, list of functions, dict, default "mean"
    If a list of functions is passed, the resulting pivot table will have
    hierarchical columns whose top level are the function names
    (inferred from the function objects themselves).
    If a dict is passed, the key is column to aggregate and the value is
    function or list of functions. If ``margin=True``, aggfunc will be
    used to calculate the partial aggregates.
fill_value : scalar, default None
    Value to replace missing values with (in the resulting pivot table,
    after aggregation).
margins : bool, default False
    If ``margins=True``, special ``All`` columns and rows
    will be added with partial group aggregates across the categories
    on the rows and columns.
dropna : bool, default True
    Do not include columns whose entries are all NaN. If True,
    rows with a NaN value in any column will be omitted before
    computing margins.
margins_name : str, default 'All'
    Name of the row / column that will contain the totals
    when margins is True.
observed : bool, default False
    This only applies if any of the groupers are Categoricals.
    If True: only show observed values for categorical groupers.
    If False: show all values for categorical groupers.

    .. deprecated:: 2.2.0

        The default value of ``False`` is deprecated and will change to
        ``True`` in a future version of pandas.

sort : bool, default True
    Specifies if the result should be sorted.

    .. versionadded:: 1.3.0

Returns
-------
DataFrame
    An Excel style pivot table.

See Also
--------
DataFrame.pivot : Pivot without aggregation that can handle
    non-numeric data.
DataFrame.melt: Unpivot a DataFrame from wide to long format,
    optionally leaving identifiers set.
wide_to_long : Wide panel to long format. Less flexible but more
    user-friendly than melt.

Notes
-----
Reference :ref:`the user guide <reshaping.pivot>` for more examples.

Examples
--------
>>> df = pd.DataFrame({"A": ["foo", "foo", "foo", "foo", "foo",
...                          "bar", "bar", "bar", "bar"],
...                    "B": ["one", "one", "one", "two", "two",
...                          "one", "one", "two", "two"],
...                    "C": ["small", "large", "large", "small",
...                          "small", "large", "small", "small",
...                          "large"],
...                    "D": [1, 2, 2, 3, 3, 4, 5, 6, 7],
...                    "E": [2, 4, 5, 5, 6, 6, 8, 9, 9]})
>>> df
     A    B      C  D  E
0  foo  one  small  1  2
1  foo  one  large  2  4
2  foo  one  large  2  5
3  foo  two  small  3  5
4  foo  two  small  3  6
5  bar  one  large  4  6
6  bar  one  small  5  8
7  bar  two  small  6  9
8  bar  two  large  7  9

This first example aggregates values by taking the sum.

>>> table = pd.pivot_table(df, values='D', index=['A', 'B'],
...                        columns=['C'], aggfunc="sum")
>>> table
C        large  small
A   B
bar one    4.0    5.0
    two    7.0    6.0
foo one    4.0    1.0
    two    NaN    6.0

We can also fill missing values using the `fill_value` parameter.

>>> table = pd.pivot_table(df, values='D', index=['A', 'B'],
...                        columns=['C'], aggfunc="sum", fill_value=0)
>>> table
C        large  small
A   B
bar one      4      5
    two      7      6
foo one      4      1
    two      0      6

The next example aggregates by taking the mean across multiple columns.

>>> table = pd.pivot_table(df, values=['D', 'E'], index=['A', 'C'],
...                        aggfunc={'D': "mean", 'E': "mean"})
>>> table
                D         E
A   C
bar large  5.500000  7.500000
    small  5.500000  8.500000
foo large  2.000000  4.500000
    small  2.333333  4.333333

We can also calculate multiple types of aggregations for any given
value column.

>>> table = pd.pivot_table(df, values=['D', 'E'], index=['A', 'C'],
...                        aggfunc={'D': "mean",
...                                 'E': ["min", "max", "mean"]})
>>> table
                  D   E
               mean max      mean  min
A   C
bar large  5.500000   9  7.500000    6
    small  5.500000   9  8.500000    8
foo large  2.000000   5  4.500000    4
    small  2.333333   6  4.333333    2
    """
    pass

# Can only use Index or ndarray when index or columns is a Grouper
@overload
def pivot_table(
    data: DataFrame,
    values: _PivotTableValuesTypes = ...,
    *,
    index: Grouper,
    columns: _PivotTableColumnsTypes | Index | npt.NDArray = ...,
    aggfunc: (
        _PivotAggFunc | Sequence[_PivotAggFunc] | Mapping[Hashable, _PivotAggFunc]
    ) = ...,
    fill_value: Scalar | None = ...,
    margins: bool = ...,
    dropna: bool = ...,
    margins_name: str = ...,
    observed: bool = ...,
    sort: bool = ...,
) -> DataFrame: ...
@overload
def pivot_table(
    data: DataFrame,
    values: _PivotTableValuesTypes = ...,
    index: _PivotTableIndexTypes | Index | npt.NDArray = ...,
    *,
    columns: Grouper,
    aggfunc: (
        _PivotAggFunc | Sequence[_PivotAggFunc] | Mapping[Hashable, _PivotAggFunc]
    ) = ...,
    fill_value: Scalar | None = ...,
    margins: bool = ...,
    dropna: bool = ...,
    margins_name: str = ...,
    observed: bool = ...,
    sort: bool = ...,
) -> DataFrame: ...
def pivot(
    data: DataFrame,
    *,
    index: _NonIterableHashable | Sequence[HashableT1] = ...,
    columns: _NonIterableHashable | Sequence[HashableT2] = ...,
    values: _NonIterableHashable | Sequence[HashableT3] = ...,
) -> DataFrame:
    """
Return reshaped DataFrame organized by given index / column values.

Reshape data (produce a "pivot" table) based on column values. Uses
unique values from specified `index` / `columns` to form axes of the
resulting DataFrame. This function does not support data
aggregation, multiple values will result in a MultiIndex in the
columns. See the :ref:`User Guide <reshaping>` for more on reshaping.

Parameters
----------
data : DataFrame
columns : str or object or a list of str
    Column to use to make new frame's columns.
index : str or object or a list of str, optional
    Column to use to make new frame's index. If not given, uses existing index.
values : str, object or a list of the previous, optional
    Column(s) to use for populating new frame's values. If not
    specified, all remaining columns will be used and the result will
    have hierarchically indexed columns.

Returns
-------
DataFrame
    Returns reshaped DataFrame.

Raises
------
ValueError:
    When there are any `index`, `columns` combinations with multiple
    values. `DataFrame.pivot_table` when you need to aggregate.

See Also
--------
DataFrame.pivot_table : Generalization of pivot that can handle
    duplicate values for one index/column pair.
DataFrame.unstack : Pivot based on the index values instead of a
    column.
wide_to_long : Wide panel to long format. Less flexible but more
    user-friendly than melt.

Notes
-----
For finer-tuned control, see hierarchical indexing documentation along
with the related stack/unstack methods.

Reference :ref:`the user guide <reshaping.pivot>` for more examples.

Examples
--------
>>> df = pd.DataFrame({'foo': ['one', 'one', 'one', 'two', 'two',
...                            'two'],
...                    'bar': ['A', 'B', 'C', 'A', 'B', 'C'],
...                    'baz': [1, 2, 3, 4, 5, 6],
...                    'zoo': ['x', 'y', 'z', 'q', 'w', 't']})
>>> df
    foo   bar  baz  zoo
0   one   A    1    x
1   one   B    2    y
2   one   C    3    z
3   two   A    4    q
4   two   B    5    w
5   two   C    6    t

>>> df.pivot(index='foo', columns='bar', values='baz')
bar  A   B   C
foo
one  1   2   3
two  4   5   6

>>> df.pivot(index='foo', columns='bar')['baz']
bar  A   B   C
foo
one  1   2   3
two  4   5   6

>>> df.pivot(index='foo', columns='bar', values=['baz', 'zoo'])
      baz       zoo
bar   A  B  C   A  B  C
foo
one   1  2  3   x  y  z
two   4  5  6   q  w  t

You could also assign a list of column names or a list of index names.

>>> df = pd.DataFrame({
...        "lev1": [1, 1, 1, 2, 2, 2],
...        "lev2": [1, 1, 2, 1, 1, 2],
...        "lev3": [1, 2, 1, 2, 1, 2],
...        "lev4": [1, 2, 3, 4, 5, 6],
...        "values": [0, 1, 2, 3, 4, 5]})
>>> df
    lev1 lev2 lev3 lev4 values
0   1    1    1    1    0
1   1    1    2    2    1
2   1    2    1    3    2
3   2    1    2    4    3
4   2    1    1    5    4
5   2    2    2    6    5

>>> df.pivot(index="lev1", columns=["lev2", "lev3"], values="values")
lev2    1         2
lev3    1    2    1    2
lev1
1     0.0  1.0  2.0  NaN
2     4.0  3.0  NaN  5.0

>>> df.pivot(index=["lev1", "lev2"], columns=["lev3"], values="values")
      lev3    1    2
lev1  lev2
   1     1  0.0  1.0
         2  2.0  NaN
   2     1  4.0  3.0
         2  NaN  5.0

A ValueError is raised if there are any duplicates.

>>> df = pd.DataFrame({"foo": ['one', 'one', 'two', 'two'],
...                    "bar": ['A', 'A', 'B', 'C'],
...                    "baz": [1, 2, 3, 4]})
>>> df
   foo bar  baz
0  one   A    1
1  one   A    2
2  two   B    3
3  two   C    4

Notice that the first two rows are the same for our `index`
and `columns` arguments.

>>> df.pivot(index='foo', columns='bar', values='baz')
Traceback (most recent call last):
   ...
ValueError: Index contains duplicate entries, cannot reshape
    """
    pass
@overload
def crosstab(
    index: list | _ExtendedAnyArrayLike | list[Sequence | _ExtendedAnyArrayLike],
    columns: list | _ExtendedAnyArrayLike | list[Sequence | _ExtendedAnyArrayLike],
    values: list | _ExtendedAnyArrayLike,
    rownames: list[HashableT1] | None = ...,
    colnames: list[HashableT2] | None = ...,
    *,
    aggfunc: str | np.ufunc | Callable[[Series], float],
    margins: bool = ...,
    margins_name: str = ...,
    dropna: bool = ...,
    normalize: bool | Literal[0, 1, "all", "index", "columns"] = ...,
) -> DataFrame: ...
@overload
def crosstab(
    index: list | _ExtendedAnyArrayLike | list[Sequence | _ExtendedAnyArrayLike],
    columns: list | _ExtendedAnyArrayLike | list[Sequence | _ExtendedAnyArrayLike],
    values: None = ...,
    rownames: list[HashableT1] | None = ...,
    colnames: list[HashableT2] | None = ...,
    aggfunc: None = ...,
    margins: bool = ...,
    margins_name: str = ...,
    dropna: bool = ...,
    normalize: bool | Literal[0, 1, "all", "index", "columns"] = ...,
) -> DataFrame: ...