def set_types(self,
logical_types=None,
semantic_tags=None,
retain_index_tags=True):
"""Update the logical type and semantic tags for any columns names in the provided types dictionaries,
updating the Woodwork typing information for the DataFrame.
Args:
logical_types (dict[str -> str], optional): A dictionary defining the new logical types for the
specified columns.
semantic_tags (dict[str -> str/list/set], optional): A dictionary defining the new semantic_tags for the
specified columns.
retain_index_tags (bool, optional): If True, will retain any index or time_index
semantic tags set on the column. If False, will replace all semantic tags any time a column's
semantic tags or logical type changes. Defaults to True.
"""
if self._schema is None:
_raise_init_error()
logical_types = logical_types or {}
logical_types = {
col_name: _parse_logical_type(ltype, col_name)
for col_name, ltype in logical_types.items()
}
self._schema.set_types(logical_types=logical_types,
semantic_tags=semantic_tags,
retain_index_tags=retain_index_tags)
# go through changed ltypes and update dtype if necessary
for col_name, logical_type in logical_types.items():
series = self._dataframe[col_name]
updated_series = _update_column_dtype(series, logical_type)
if updated_series is not series:
self._dataframe[col_name] = updated_series
def test_parse_logical_type_errors():
error = 'Must use an Ordinal instance with order values defined'
with pytest.raises(TypeError, match=error):
_parse_logical_type('Ordinal', 'col_name')
with pytest.raises(TypeError, match=error):
_parse_logical_type(Ordinal, 'col_name')
error = "Invalid logical type specified for 'col_name'"
with pytest.raises(TypeError, match=error):
_parse_logical_type(int, 'col_name')
def test_parse_logical_type_errors():
error = "Invalid logical type specified for 'col_name'"
with pytest.raises(TypeError, match=error):
_parse_logical_type(int, "col_name")
def test_parse_logical_type():
assert isinstance(_parse_logical_type("Datetime", "col_name"), Datetime)
assert isinstance(_parse_logical_type(Datetime, "col_name"), Datetime)
ymd_format = Datetime(datetime_format="%Y-%m-%d")
assert _parse_logical_type(ymd_format, "col_name") == ymd_format
def test_parse_logical_type():
assert _parse_logical_type('Datetime', 'col_name') == Datetime
assert _parse_logical_type(Datetime, 'col_name') == Datetime
ymd_format = Datetime(datetime_format='%Y-%m-%d')
assert _parse_logical_type(ymd_format, 'col_name') == ymd_format