Dataframe with list columns of every possible primitive type. Returns ------- df: pandas.DataFrame schema: pyarrow.Schema Arrow schema definition that is in line with the constructed df. parquet_compatible: bool Exclude types not supported by parquet
(include_index=False, parquet_compatible=False)
| 81 | |
| 82 | |
| 83 | def dataframe_with_lists(include_index=False, parquet_compatible=False): |
| 84 | """ |
| 85 | Dataframe with list columns of every possible primitive type. |
| 86 | |
| 87 | Returns |
| 88 | ------- |
| 89 | df: pandas.DataFrame |
| 90 | schema: pyarrow.Schema |
| 91 | Arrow schema definition that is in line with the constructed df. |
| 92 | parquet_compatible: bool |
| 93 | Exclude types not supported by parquet |
| 94 | """ |
| 95 | arrays = OrderedDict() |
| 96 | fields = [] |
| 97 | |
| 98 | fields.append(pa.field('int64', pa.list_(pa.int64()))) |
| 99 | arrays['int64'] = [ |
| 100 | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9], |
| 101 | [0, 1, 2, 3, 4], |
| 102 | None, |
| 103 | [], |
| 104 | np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9] * 2, |
| 105 | dtype=np.int64)[::2] |
| 106 | ] |
| 107 | fields.append(pa.field('double', pa.list_(pa.float64()))) |
| 108 | arrays['double'] = [ |
| 109 | [0., 1., 2., 3., 4., 5., 6., 7., 8., 9.], |
| 110 | [0., 1., 2., 3., 4.], |
| 111 | None, |
| 112 | [], |
| 113 | np.array([0., 1., 2., 3., 4., 5., 6., 7., 8., 9.] * 2)[::2], |
| 114 | ] |
| 115 | fields.append(pa.field('bytes_list', pa.list_(pa.binary()))) |
| 116 | arrays['bytes_list'] = [ |
| 117 | [b"1", b"f"], |
| 118 | None, |
| 119 | [b"1"], |
| 120 | [b"1", b"2", b"3"], |
| 121 | [], |
| 122 | ] |
| 123 | fields.append(pa.field('str_list', pa.list_(pa.string()))) |
| 124 | arrays['str_list'] = [ |
| 125 | ["1", "ä"], |
| 126 | None, |
| 127 | ["1"], |
| 128 | ["1", "2", "3"], |
| 129 | [], |
| 130 | ] |
| 131 | |
| 132 | date_data = [ |
| 133 | [], |
| 134 | [date(2018, 1, 1), date(2032, 12, 30)], |
| 135 | [date(2000, 6, 7)], |
| 136 | None, |
| 137 | [date(1969, 6, 9), date(1972, 7, 3)] |
| 138 | ] |
| 139 | time_data = [ |
| 140 | [time(23, 11, 11), time(1, 2, 3), time(23, 59, 59)], |