7 examples of 'convert groupby to dataframe pandas' in Python

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

59
def to_pandas(self):
60
    """Encode aggregation result as a pandas dataframe.
61
62
    Returns:
63
        Pandas dataframe with aggregation results.
64
    """
65
    return pandas.DataFrame(self.values)

317
def test_groupby_select_all_columns():
318
    # Check that when selecting all columns, the result has the same number
319
    # of columns as the original.
320
    DT = dt.Frame(id2=[1, 2] * 3, id4=[1] * 6, v3=[1, 3, 2, 3, 3, 3])
321
    res = DT[:, :, by(f.id2, f.id4)]
322
    assert_equals(res, dt.Frame(id2=[1, 1, 1, 2, 2, 2], id4=[1] * 6,
323
                                v3=[1, 2, 3, 3, 3, 3]))

31
def groupby(xs, keys):
32
    result = defaultdict(list)
33
    for (x, key) in zip(xs, keys):
34
        result[key].append(x)
35
    return result

29
def _concat(df, type):
30
    if df is None:
31
        df = pd.DataFrame(_object_blocks[type])
32
    else:
33
        _df = pd.DataFrame(_object_blocks[type])
34
        df = pd.concat([df, _df], sort=True)
35
    return df

309
@ApplyToDataframe
310
def ungroup():
311
  return UngroupDF

17
def groupby_deco(func):
18
    def func_wrapper(self, thing, *args, **kwargs):
19
        if isinstance(thing, pd.core.groupby.DataFrameGroupBy):
20
            agg = thing.apply(lambda x: func(self, x, *args, **kwargs))
21
            is_series = isinstance(agg, pd.core.series.Series)
22
            has_multiindex = isinstance(agg.index, pd.MultiIndex)
23
            if is_series and has_multiindex:
24
                return agg.unstack()
25
            else:
26
                return agg
27
        return func(self, thing, *args, **kwargs)
28
    return func_wrapper