4 examples of 'pandas groupby sum multiple columns' in Python

230
def get_column_sum(self, column):
231
    return self.spark_df.select(column).groupBy().sum().collect()[0][0]

38
def add_group_id(df, *groupby_cols, gid_colname='gid'):
39
    groupby_cols = list(groupby_cols)
40
    df_group = df.groupby(groupby_cols).apply(lambda g: pd.Series({
41
        'group_length': g.shape[0]
42
    })).reset_index()
43
    df_group[gid_colname] = df_group.index
44
    df_merge = pd.merge(df, df_group, how='outer', on=groupby_cols)
45
    df_merge['group_length'] = df_merge['group_length'].fillna(-1)
46
    df_merge[gid_colname] = df_merge[gid_colname].fillna(-1)
47
    df_merge['group_length'] = df_merge['group_length'].astype(int)
48
    df_merge[gid_colname] = df_merge[gid_colname].astype(int)
49
    return df_merge

236
def mean(self):
237
    # TODO, there is a lot of copy-paste with the code above
238
    # TODO, we should probably define groupby.aggregate
239
    func = _accumulate_groupby_mean
240
    start = (0, 0)
241
    if isinstance(self.grouper, Streaming):
242
        func = partial(func, index=self.index)
243
        example = self.root.example.groupby(self.grouper.example)
244
        if self.index is not None:
245
            example = example[self.index]
246
        example = example.mean()
247
        stream = self.root.stream.zip(self.grouper.stream)
248
        stream = stream.accumulate(func, start=start, returns_state=True)
249
    else:
250
        func = partial(func, grouper=self.grouper, index=self.index)
251
        example = self.root.example.groupby(self.grouper)
252
        if self.index is not None:
253
            example = example[self.index]
254
        example = example.mean()
255
        stream = self.root.stream.accumulate(func, start=start,
256
                                             returns_state=True)
257
    if isinstance(example, pd.DataFrame):
258
        return StreamingDataFrame(stream, example)
259
    else:
260
        return StreamingSeries(stream, example)

54
def sum(self):
55
    def sum(scol):
56
        return F.when(
57
            F.row_number().over(self._unbounded_window) >= self._min_periods,
58
            F.sum(scol).over(self._window)
59
        ).otherwise(F.lit(None))
60
61
    return self._apply_as_series_or_frame(sum)