Python DataFrame.reindex方法代碼示例

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import reindex [as 別名]
def _concat_frames(frames, index, columns=None, axis=0):
    if axis == 0:
        all_index = [np.asarray(x.index) for x in frames]
        new_index = Index(np.concatenate(all_index))

        if columns is None:
            new_columns = frames[0].columns
        else:
            new_columns = columns
    else:
        all_columns = [np.asarray(x.columns) for x in frames]
        new_columns = Index(np.concatenate(all_columns))
        new_index = index

    new_values = np.concatenate([x.values for x in frames], axis=axis)
    result = DataFrame(new_values, index=new_index, columns=new_columns)
    return result.reindex(index=index, columns=columns)

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import reindex [as 別名]
def _concat_frames(frames, index, columns=None, axis=0):
    if len(frames) == 1:
        return frames[0]

    if axis == 0:
        new_index = _concat_indexes([x.index for x in frames])
        if columns is None:
            new_columns = frames[0].columns
        else:
            new_columns = columns
    else:
        new_columns = _concat_indexes([x.columns for x in frames])
        new_index = index

    if frames[0]._is_mixed_type:
        new_data = {}
        for col in new_columns:
            new_data[col] = np.concatenate([x[col].values for x in frames])
        return DataFrame(new_data, index=new_index, columns=new_columns)
    else:
        new_values = np.concatenate([x.values for x in frames], axis=axis)
        result = DataFrame(new_values, index=new_index, columns=new_columns)
        return result.reindex(index=index, columns=columns)

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import reindex [as 別名]
    def describe(self):
        """ Describes this Categorical

        Returns
        -------
        description: `DataFrame`
            A dataframe with frequency and counts by level.
        """
        # Hack?
        from pandas.core.frame import DataFrame
        counts = DataFrame({
            'codes' : self._codes,
            'values' : self._codes }
                           ).groupby('codes').count()

        counts.index = self.levels.take(counts.index)
        counts = counts.reindex(self.levels)
        freqs = counts / float(counts.sum())

        from pandas.tools.merge import concat
        result = concat([counts,freqs],axis=1)
        result.index.name = 'levels'
        result.columns = ['counts','freqs']
        return result

# 需要導入模塊: from pandas.core.frame import DataFrame [as 別名]
# 或者: from pandas.core.frame.DataFrame import reindex [as 別名]
    def transform(self, func):
        """
        For given DataFrame, group index by given mapper function or dict, take
        the sub-DataFrame (reindex) for this group and call apply(func)
        on this sub-DataFrame. Return a DataFrame of the results for each
        key.

        Note: this function does not aggregate like groupby/tgroupby,
        the results of the given function on the subDataFrame should be another
        DataFrame.

        Parameters
        ----------
        mapper : function, dict-like, or string
            Mapping or mapping function. If string given, must be a column
            name in the frame
        func : function
            Function to apply to each subframe

        Note
        ----
        Each subframe is endowed the attribute 'groupName' in case
        you need to know which group you are working on.

        Example
        --------
        >>> grouped = df.groupby(lambda x: mapping[x])
        >>> grouped.transform(lambda x: (x - x.mean()) / x.std())
        """
        applied = []

        obj = self._get_obj_with_exclusions()
        for val, inds in self.primary.indices.iteritems():
            subframe = obj.take(inds, axis=self.axis)
            subframe.groupName = val

            try:
                res = subframe.apply(func, axis=self.axis)
            except Exception: # pragma: no cover
                res = func(subframe)

            # broadcasting
            if isinstance(res, Series):
                if res.index is obj.index:
                    subframe.T.values[:] = res
                else:
                    subframe.values[:] = res

                applied.append(subframe)
            else:
                applied.append(res)

        if self.axis == 0:
            all_index = [np.asarray(x.index) for x in applied]
            new_index = Index(np.concatenate(all_index))
            new_columns = obj.columns
        else:
            all_columns = [np.asarray(x.columns) for x in applied]
            new_columns = Index(np.concatenate(all_columns))
            new_index = obj.index

        new_values = np.concatenate([x.values for x in applied],
                                    axis=self.axis)
        result = DataFrame(new_values, index=new_index, columns=new_columns)
        return result.reindex(index=obj.index, columns=obj.columns)