def test_error_transform_num(self):
X, y = load_xy(0)
with pytest.raises(TypeError):
_internal.transform_num(X, num_bins='')
with pytest.raises(ValueError):
_internal.transform_num(X, num_bins=-1)
def _set_data_categoric(self, transform_num: bool,
num_bins: bool = None) -> np.ndarray:
"""Returns categorical data from the fitted dataset.
Parameters
----------
transform_num : :obj:`bool`
If True, then all numeric-type data are discretized using an
equal-frequency histogram. Otherwise, this method ignores these
attributes.
num_bins : :obj:`bool`, optional
Number of bins of the discretization histogram. This argument is
used only if ``transform_num`` is True. If this argument value is
:obj:`NoneType`, then it is set to min(2, c), where ``c`` is the
cubic root of the number of instances of the fitted dataset.
Returns
-------
:obj:`np.ndarray`
Processed categorical data. If no need for changes from the
original dataset, then this method does not create a copy of it to
prevent unnecessary memory usage. Otherwise, this method returns a
modified version of the original categorical data, thus consuming
more memory.
Raises
------
TypeError:
If either ``X`` or ``_attr_indexes_cat`` instance attributes are
:obj:`NoneType`. This can be avoided passing valid data to fit and
first calling ``_fill_col_ind_by_type`` instance method before this
method.
"""
if self.X is None:
raise TypeError("It is necessary to fit valid data into the "
'model before setting up categoric data. ("X" '
'attribute is "NoneType").')
if self._attr_indexes_cat is None:
raise TypeError("No information about indexes of categoric "
"attributes. Please be sure to call method "
'"_fill_col_ind_by_type" before this method.')
data_cat = self.X[:, self._attr_indexes_cat]
if transform_num:
data_num_discretized = _internal.transform_num(
self.X[:, self._attr_indexes_num], num_bins=num_bins)
if data_num_discretized is not None:
data_cat = np.concatenate((data_cat, data_num_discretized),
axis=1)
return data_cat
def _set_data_categoric(cls,
N,
C,
transform_num: bool,
num_bins: bool = None) -> np.ndarray:
data_cat = C.to_numpy()
if transform_num and not N.empty:
data_num_discretized = _internal.transform_num(N,
num_bins=num_bins)
if data_num_discretized is not None:
data_cat = np.concatenate((data_cat, data_num_discretized),
axis=1)
return data_cat