def predict(self, X, y=None, objective=None):
"""Make predictions using selected features.
Arguments:
X (ww.DataTable, pd.DataFrame, or np.ndarray): Data of shape [n_samples, n_features]
y (ww.DataColumn, pd.Series, np.ndarray, None): The target training targets of length [n_samples]
objective (Object or string): The objective to use to make predictions
Returns:
ww.DataColumn: Predicted values.
"""
if X is None:
X = pd.DataFrame()
X = infer_feature_types(X)
y = infer_feature_types(y)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
y = _convert_woodwork_types_wrapper(y.to_series())
features = self.compute_estimator_features(X, y)
features = _convert_woodwork_types_wrapper(features.to_dataframe())
features_no_nan, y = drop_rows_with_nans(features, y)
y_arg = None
if self.estimator.predict_uses_y:
y_arg = y
predictions = self.estimator.predict(features_no_nan,
y_arg).to_series()
predictions = predictions.rename(self.input_target_name)
padded = pad_with_nans(
predictions, max(0, features.shape[0] - predictions.shape[0]))
return infer_feature_types(padded)
def _predict(self, X, y, objective=None, pad=False):
features = self.compute_estimator_features(X, y)
features = _convert_woodwork_types_wrapper(features.to_dataframe())
features_no_nan, y_no_nan = drop_rows_with_nans(features, y)
if objective is not None:
objective = get_objective(objective, return_instance=True)
if not objective.is_defined_for_problem_type(self.problem_type):
raise ValueError(
f"Objective {objective.name} is not defined for time series binary classification."
)
if self.threshold is None:
predictions = self._estimator_predict(features_no_nan,
y_no_nan).to_series()
else:
proba = self._estimator_predict_proba(features_no_nan,
y_no_nan).to_dataframe()
proba = proba.iloc[:, 1]
if objective is None:
predictions = proba > self.threshold
else:
predictions = objective.decision_function(
proba, threshold=self.threshold, X=features_no_nan)
if pad:
predictions = pad_with_nans(
predictions, max(0, features.shape[0] - predictions.shape[0]))
return infer_feature_types(predictions)
def predict(self, X, y=None, objective=None):
"""Make predictions using selected features.
Arguments:
X (ww.DataTable, pd.DataFrame, or np.ndarray): Data of shape [n_samples, n_features]
y (ww.DataColumn, pd.Series, np.ndarray, None): The target training targets of length [n_samples]
objective (Object or string): The objective to use to make predictions
Returns:
ww.DataColumn: Predicted values.
"""
X, y = self._convert_to_woodwork(X, y)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
y = _convert_woodwork_types_wrapper(y.to_series())
y = self._encode_targets(y)
n_features = max(len(y), X.shape[0])
predictions = self._predict(X, y, objective=objective, pad=False)
predictions = _convert_woodwork_types_wrapper(predictions.to_series())
# In case gap is 0 and this is a baseline pipeline, we drop the nans in the
# predictions before decoding them
predictions = pd.Series(self._decode_targets(predictions.dropna()),
name=self.input_target_name)
padded = pad_with_nans(predictions,
max(0, n_features - predictions.shape[0]))
return infer_feature_types(padded)
def _predict(self, X, y, objective=None, pad=False):
features = self.compute_estimator_features(X, y)
features = _convert_woodwork_types_wrapper(features.to_dataframe())
features_no_nan, y_no_nan = drop_rows_with_nans(features, y)
predictions = self._estimator_predict(features_no_nan, y_no_nan)
if pad:
padded = pad_with_nans(predictions.to_series(), max(0, features.shape[0] - predictions.shape[0]))
return infer_feature_types(padded)
return predictions
def predict_proba(self, X, y=None):
if y is None:
raise ValueError("Cannot predict Time Series Baseline Estimator if y is None")
y = infer_feature_types(y)
y = _convert_woodwork_types_wrapper(y.to_series())
preds = self.predict(X, y).to_series().dropna(axis=0, how='any').astype('int')
proba_arr = np.zeros((len(preds), y.max() + 1))
proba_arr[np.arange(len(preds)), preds] = 1
padded = pad_with_nans(pd.DataFrame(proba_arr), len(y) - len(preds))
return infer_feature_types(padded)
def predict_proba(self, X, y=None):
"""Make probability estimates for labels.
Arguments:
X (ww.DataTable, pd.DataFrame or np.ndarray): Data of shape [n_samples, n_features]
Returns:
ww.DataTable: Probability estimates
"""
X, y = self._convert_to_woodwork(X, y)
X = _convert_woodwork_types_wrapper(X.to_dataframe())
y = _convert_woodwork_types_wrapper(y.to_series())
y = self._encode_targets(y)
features = self.compute_estimator_features(X, y)
features = _convert_woodwork_types_wrapper(features.to_dataframe())
features_no_nan, y_no_nan = drop_rows_with_nans(features, y)
proba = self._estimator_predict_proba(features_no_nan, y_no_nan).to_dataframe()
proba.columns = self._encoder.classes_
padded = pad_with_nans(proba, max(0, features.shape[0] - proba.shape[0]))
return infer_feature_types(padded)
