def transform(self, X, y=None):
"""Transforms input data by selecting features. If the component_obj does not have a transform method, will raise an MethodPropertyNotFoundError exception.
Arguments:
X (ww.DataTable, pd.DataFrame): Data to transform.
y (ww.DataColumn, pd.Series, optional): Target data. Ignored.
Returns:
ww.DataTable: Transformed X
"""
X = _convert_to_woodwork_structure(X)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
self.input_feature_names = list(X.columns.values)
try:
X_t = self._component_obj.transform(X)
except AttributeError:
raise MethodPropertyNotFoundError(
"Feature selector requires a transform method or a component_obj that implements transform"
)
X_dtypes = X.dtypes.to_dict()
selected_col_names = self.get_names()
col_types = {key: X_dtypes[key] for key in selected_col_names}
features = pd.DataFrame(X_t, columns=selected_col_names,
index=X.index).astype(col_types)
return _convert_to_woodwork_structure(features)
def feature_importance(self):
"""Returns importance associated with each feature.
Returns:
np.ndarray: Importance associated with each feature
"""
try:
return self._component_obj.feature_importances_
except AttributeError:
raise MethodPropertyNotFoundError("Estimator requires a feature_importance property or a component_obj that implements feature_importances_")
def transform(self, X, y=None):
"""Transforms data X
Arguments:
X (pd.DataFrame): Data to transform
y (pd.Series, optional): Target data
Returns:
pd.DataFrame: Transformed X
"""
try:
X_t = self._component_obj.transform(X)
except AttributeError:
raise MethodPropertyNotFoundError("Transformer requires a transform method or a component_obj that implements transform")
if not isinstance(X_t, pd.DataFrame) and isinstance(X, pd.DataFrame):
return pd.DataFrame(X_t, columns=X.columns, index=X.index)
return pd.DataFrame(X_t)
def predict_proba(self, X):
"""Make probability estimates for labels.
Arguments:
X (ww.DataTable, pd.DataFrame, or np.ndarray): Features
Returns:
ww.DataTable: Probability estimates
"""
try:
X = infer_feature_types(X)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
pred_proba = self._component_obj.predict_proba(X)
except AttributeError:
raise MethodPropertyNotFoundError("Estimator requires a predict_proba method or a component_obj that implements predict_proba")
return infer_feature_types(pred_proba)
def predict(self, X):
"""Make predictions using selected features.
Arguments:
X (ww.DataTable, pd.DataFrame, or np.ndarray): Data of shape [n_samples, n_features]
Returns:
ww.DataColumn: Predicted values
"""
try:
X = infer_feature_types(X)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
predictions = self._component_obj.predict(X)
except AttributeError:
raise MethodPropertyNotFoundError("Estimator requires a predict method or a component_obj that implements predict")
return infer_feature_types(predictions)
def fit(self, X, y=None):
"""Fits component to data
Arguments:
X (list, ww.DataTable, pd.DataFrame or np.ndarray): The input training data of shape [n_samples, n_features]
y (list, ww.DataColumn, pd.Series, np.ndarray, optional): The target training data of length [n_samples]
Returns:
self
"""
X = infer_feature_types(X)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
if y is not None:
y = infer_feature_types(y)
y = _convert_woodwork_types_wrapper(y.to_series())
try:
self._component_obj.fit(X, y)
return self
except AttributeError:
raise MethodPropertyNotFoundError("Component requires a fit method or a component_obj that implements fit")
def transform(self, X, y=None):
"""Transforms data X.
Arguments:
X (ww.DataTable, pd.DataFrame): Data to transform.
y (ww.DataColumn, pd.Series, optional): Target data.
Returns:
ww.DataTable: Transformed X
"""
try:
X = _convert_to_woodwork_structure(X)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
if y is not None:
y = _convert_to_woodwork_structure(y)
y = _convert_woodwork_types_wrapper(y.to_series())
X_t = self._component_obj.transform(X, y)
except AttributeError:
raise MethodPropertyNotFoundError(
"Transformer requires a transform method or a component_obj that implements transform"
)
X_t_df = pd.DataFrame(X_t, columns=X.columns, index=X.index)
return _convert_to_woodwork_structure(X_t_df)
