# pylint: disable=E1103
import numpy as np

from pandas.compat import lrange, range, zip
from pandas.util._decorators import Appender, Substitution

from pandas.core.dtypes.cast import maybe_downcast_to_dtype
from pandas.core.dtypes.common import is_integer_dtype, is_list_like, is_scalar
from pandas.core.dtypes.generic import ABCDataFrame, ABCSeries

from pandas import compat
import pandas.core.common as com
from pandas.core.frame import _shared_docs
from pandas.core.groupby import Grouper
from pandas.core.index import Index, MultiIndex, _get_objs_combined_axis
from pandas.core.reshape.concat import concat
from pandas.core.reshape.util import cartesian_product
from pandas.core.series import Series


# Note: We need to make sure `frame` is imported before `pivot`, otherwise
# _shared_docs['pivot_table'] will not yet exist.  TODO: Fix this dependency
@Substitution('\ndata : DataFrame')
@Appender(_shared_docs['pivot_table'], indents=1)
def pivot_table(data, values=None, index=None, columns=None, aggfunc='mean',
                fill_value=None, margins=False, dropna=True,
                margins_name='All'):
    index = _convert_by(index)
    columns = _convert_by(columns)

    if isinstance(aggfunc, list):
        pieces = []
        keys = []
        for func in aggfunc:
            table = pivot_table(data, values=values, index=index,
                                columns=columns,
                                fill_value=fill_value, aggfunc=func,
                                margins=margins, margins_name=margins_name)
            pieces.append(table)
            keys.append(getattr(func, '__name__', func))

        return concat(pieces, keys=keys, axis=1)

    keys = index + columns

    values_passed = values is not None
    if values_passed:
        if is_list_like(values):
            values_multi = True
            values = list(values)
        else:
            values_multi = False
            values = [values]

        # GH14938 Make sure value labels are in data
        for i in values:
            if i not in data:
                raise KeyError(i)

        to_filter = []
        for x in keys + values:
            if isinstance(x, Grouper):
                x = x.key
            try:
                if x in data:
                    to_filter.append(x)
            except TypeError:
                pass
        if len(to_filter) < len(data.columns):
            data = data[to_filter]

    else:
        values = data.columns
        for key in keys:
            try:
                values = values.drop(key)
            except (TypeError, ValueError, KeyError):
                pass
        values = list(values)

    grouped = data.groupby(keys, observed=False)
    agged = grouped.agg(aggfunc)
    if dropna and isinstance(agged, ABCDataFrame) and len(agged.columns):
        agged = agged.dropna(how='all')

        # gh-21133
        # we want to down cast if
        # the original values are ints
        # as we grouped with a NaN value
        # and then dropped, coercing to floats
        for v in [v for v in values if v in data and v in agged]:
            if (is_integer_dtype(data[v]) and
                    not is_integer_dtype(agged[v])):
                agged[v] = maybe_downcast_to_dtype(agged[v], data[v].dtype)

    table = agged
    if table.index.nlevels > 1:
        # Related GH #17123
        # If index_names are integers, determine whether the integers refer
        # to the level position or name.
        index_names = agged.index.names[:len(index)]
        to_unstack = []
        for i in range(len(index), len(keys)):
            name = agged.index.names[i]
            if name is None or name in index_names:
                to_unstack.append(i)
            else:
                to_unstack.append(name)
        table = agged.unstack(to_unstack)

    if not dropna:
        from pandas import MultiIndex
        if table.index.nlevels > 1:
            m = MultiIndex.from_arrays(cartesian_product(table.index.levels),
                                       names=table.index.names)
            table = table.reindex(m, axis=0)

        if table.columns.nlevels > 1:
            m = MultiIndex.from_arrays(cartesian_product(table.columns.levels),
                                       names=table.columns.names)
            table = table.reindex(m, axis=1)

    if isinstance(table, ABCDataFrame):
        table = table.sort_index(axis=1)

    if fill_value is not None:
        table = table.fillna(value=fill_value, downcast='infer')

    if margins:
        if dropna:
            data = data[data.notna().all(axis=1)]
        table = _add_margins(table, data, values, rows=index,
                             cols=columns, aggfunc=aggfunc,
                             observed=dropna,
                             margins_name=margins_name, fill_value=fill_value)

    # discard the top level
    if (values_passed and not values_multi and not table.empty and
            (table.columns.nlevels > 1)):
        table = table[values[0]]

    if len(index) == 0 and len(columns) > 0:
        table = table.T

    # GH 15193 Make sure empty columns are removed if dropna=True
    if isinstance(table, ABCDataFrame) and dropna:
        table = table.dropna(how='all', axis=1)

    return table


def _add_margins(table, data, values, rows, cols, aggfunc,
                 observed=None, margins_name='All', fill_value=None):
    if not isinstance(margins_name, compat.string_types):
        raise ValueError('margins_name argument must be a string')

    msg = u'Conflicting name "{name}" in margins'.format(name=margins_name)
    for level in table.index.names:
        if margins_name in table.index.get_level_values(level):
            raise ValueError(msg)

    grand_margin = _compute_grand_margin(data, values, aggfunc, margins_name)

    # could be passed a Series object with no 'columns'
    if hasattr(table, 'columns'):
        for level in table.columns.names[1:]:
            if margins_name in table.columns.get_level_values(level):
                raise ValueError(msg)

    if len(rows) > 1:
        key = (margins_name,) + ('',) * (len(rows) - 1)
    else:
        key = margins_name

    if not values and isinstance(table, ABCSeries):
        # If there are no values and the table is a series, then there is only
        # one column in the data. Compute grand margin and return it.
        return table.append(Series({key: grand_margin[margins_name]}))

    if values:
        marginal_result_set = _generate_marginal_results(table, data, values,
                                                         rows, cols, aggfunc,
                                                         observed,
                                                         grand_margin,
                                                         margins_name)
        if not isinstance(marginal_result_set, tuple):
            return marginal_result_set
        result, margin_keys, row_margin = marginal_result_set
    else:
        marginal_result_set = _generate_marginal_results_without_values(
            table, data, rows, cols, aggfunc, observed, margins_name)
        if not isinstance(marginal_result_set, tuple):
            return marginal_result_set
        result, margin_keys, row_margin = marginal_result_set
    row_margin = row_margin.reindex(result.columns, fill_value=fill_value)
    # populate grand margin
    for k in margin_keys:
        if isinstance(k, compat.string_types):
            row_margin[k] = grand_margin[k]
        else:
            row_margin[k] = grand_margin[k[0]]

    from pandas import DataFrame
    margin_dummy = DataFrame(row_margin, columns=[key]).T

    row_names = result.index.names
    try:
        for dtype in set(result.dtypes):
            cols = result.select_dtypes([dtype]).columns
            margin_dummy[cols] = margin_dummy[cols].astype(dtype)
        result = result.append(margin_dummy)
    except TypeError:

        # we cannot reshape, so coerce the axis
        result.index = result.index._to_safe_for_reshape()
        result = result.append(margin_dummy)
    result.index.names = row_names

    return result


def _compute_grand_margin(data, values, aggfunc,
                          margins_name='All'):

    if values:
        grand_margin = {}
        for k, v in data[values].iteritems():
            try:
                if isinstance(aggfunc, compat.string_types):
                    grand_margin[k] = getattr(v, aggfunc)()
                elif isinstance(aggfunc, dict):
                    if isinstance(aggfunc[k], compat.string_types):
                        grand_margin[k] = getattr(v, aggfunc[k])()
                    else:
                        grand_margin[k] = aggfunc[k](v)
                else:
                    grand_margin[k] = aggfunc(v)
            except TypeError:
                pass
        return grand_margin
    else:
        return {margins_name: aggfunc(data.index)}


def _generate_marginal_results(table, data, values, rows, cols, aggfunc,
                               observed,
                               grand_margin,
                               margins_name='All'):
    if len(cols) > 0:
        # need to "interleave" the margins
        table_pieces = []
        margin_keys = []

        def _all_key(key):
            return (key, margins_name) + ('',) * (len(cols) - 1)

        if len(rows) > 0:
            margin = data[rows + values].groupby(
                rows, observed=observed).agg(aggfunc)
            cat_axis = 1

            for key, piece in table.groupby(level=0,
                                            axis=cat_axis,
                                            observed=observed):
                all_key = _all_key(key)

                # we are going to mutate this, so need to copy!
                piece = piece.copy()
                try:
                    piece[all_key] = margin[key]
                except TypeError:

                    # we cannot reshape, so coerce the axis
                    piece.set_axis(piece._get_axis(
                                   cat_axis)._to_safe_for_reshape(),
                                   axis=cat_axis, inplace=True)
                    piece[all_key] = margin[key]

                table_pieces.append(piece)
                margin_keys.append(all_key)
        else:
            margin = grand_margin
            cat_axis = 0
            for key, piece in table.groupby(level=0,
                                            axis=cat_axis,
                                            observed=observed):
                all_key = _all_key(key)
                table_pieces.append(piece)
                table_pieces.append(Series(margin[key], index=[all_key]))
                margin_keys.append(all_key)

        result = concat(table_pieces, axis=cat_axis)

        if len(rows) == 0:
            return result
    else:
        result = table
        margin_keys = table.columns

    if len(cols) > 0:
        row_margin = data[cols + values].groupby(
            cols, observed=observed).agg(aggfunc)
        row_margin = row_margin.stack()

        # slight hack
        new_order = [len(cols)] + lrange(len(cols))
        row_margin.index = row_margin.index.reorder_levels(new_order)
    else:
        row_margin = Series(np.nan, index=result.columns)

    return result, margin_keys, row_margin


def _generate_marginal_results_without_values(
        table, data, rows, cols, aggfunc,
        observed, margins_name='All'):
    if len(cols) > 0:
        # need to "interleave" the margins
        margin_keys = []

        def _all_key():
            if len(cols) == 1:
                return margins_name
            return (margins_name, ) + ('', ) * (len(cols) - 1)

        if len(rows) > 0:
            margin = data[rows].groupby(rows,
                                        observed=observed).apply(aggfunc)
            all_key = _all_key()
            table[all_key] = margin
            result = table
            margin_keys.append(all_key)

        else:
            margin = data.groupby(level=0,
                                  axis=0,
                                  observed=observed).apply(aggfunc)
            all_key = _all_key()
            table[all_key] = margin
            result = table
            margin_keys.append(all_key)
            return result
    else:
        result = table
        margin_keys = table.columns