How to use 'pandas groupby concatenate strings' 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

39
@pytest.mark.functions
40
def test_deconcatenate_column_string_no_sep(dataframe):
41
    with pytest.raises(ValueError):
42
        df_orig = dataframe.concatenate_columns(
43
            column_names=["a", "decorated-elephant"],
44
            sep="-",
45
            new_column_name="index",
46
        )
47
        df = df_orig.deconcatenate_column(
48
            column_name="index", new_column_names=["A", "B"]
49
        )