def fit(self, X, y=None):
X = _convert_to_woodwork_structure(X)
if not is_all_numeric(X):
raise ValueError("PCA input must be all numeric")
X = _convert_woodwork_types_wrapper(X.to_dataframe())
self._component_obj.fit(X)
return self
def fit_transform(self, X, y=None):
X = _convert_to_woodwork_structure(X)
if not is_all_numeric(X):
raise ValueError("PCA input must be all numeric")
X = _convert_woodwork_types_wrapper(X.to_dataframe())
X_t = self._component_obj.fit_transform(X, y)
return pd.DataFrame(
X_t,
index=X.index,
columns=[f"component_{i}" for i in range(X_t.shape[1])])
def fit(self, X, y):
X = _convert_to_woodwork_structure(X)
if not is_all_numeric(X):
raise ValueError("LDA input must be all numeric")
y = _convert_to_woodwork_structure(y)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
y = _convert_woodwork_types_wrapper(y.to_series())
n_features = X.shape[1]
n_classes = y.nunique()
n_components = self.parameters['n_components']
if n_components is not None and n_components > min(
n_classes, n_features):
raise ValueError(f"n_components value {n_components} is too large")
self._component_obj.fit(X, y)
return self
def _convert_numeric_dataset_pandas(X, y):
"""Convert numeric and non-null data to pandas datatype. Raises ValueError if there is null or non-numeric data.
Used with data sampler strategies.
Arguments:
X (pd.DataFrame, np.ndarray, ww.DataTable): Data to transform
y (pd.Series, np.ndarray, ww.DataColumn): Target data
Returns:
Tuple(pd.DataFrame, pd.Series): Transformed X and y"""
X_ww = infer_feature_types(X)
if not is_all_numeric(X_ww):
raise ValueError('Values not all numeric or there are null values provided in the dataset')
y_ww = infer_feature_types(y)
X_ww = _convert_woodwork_types_wrapper(X_ww.to_dataframe())
y_ww = _convert_woodwork_types_wrapper(y_ww.to_series())
return X_ww, y_ww