def clear(self) -> None:
"""
Clears (unfits) the model.
Raises
------
UnfittedModelError
Raised when trying to clear a model that has not been fitted yet.
Try using the fit method to ``fit`` the model first.
"""
if not self._is_fitted:
raise UnfittedModelError('This model has not been fitted yet.')
self._is_fitted = False
self._X = np.ndarray((0, 0))
self._y = np.ndarray((0, ))
self._X_n = int()
self._unique_y = np.ndarray((0, ))
self._unique_y_counts = np.ndarray((0, ))
self._unique_y_probabilities = np.ndarray((0, ))
self._majority_label = None
self._is_structured = False
self._categorical_indices = np.ndarray((0, ))
self._numerical_indices = np.ndarray((0, ))
def predict_proba(self, X: np.ndarray) -> np.ndarray:
"""
Calculates label probabilities for new instances with the fitted model.
Parameters
----------
X : numpy.ndarray
The data for which labels probabilities will be predicted.
Raises
------
IncorrectShapeError
X is not a 2-dimensional array, it has 0 rows or it has a different
number of columns than the training data.
UnfittedModelError
Raised when trying to predict data when the model has not been
fitted yet. Try using the ``fit`` method to fit the model first.
RuntimeError
Raised when trying to use this method when the predictor is
initialised as a regressor.
ValueError
X has a different dtype than the data used to fit the model.
Returns
-------
probabilities : numpy.ndarray
Probabilities of each instance belonging to every class. The labels
in the return array are ordered by lexicographic order.
"""
if not self._is_classifier:
raise RuntimeError('This functionality is not available for a '
'regressor.')
if not self._is_fitted:
raise UnfittedModelError('This model has not been fitted yet.')
if not fuav.is_2d_array(X):
raise IncorrectShapeError('X must be a 2-dimensional array. If '
'you want to predict a single data '
'point please format it as a single row '
'in a 2-dimensional array.')
if not fuav.are_similar_dtype_arrays(X, self._X):
raise ValueError('X must have the same dtype as the training '
'data.')
if not X.shape[0]:
raise IncorrectShapeError('X must have at least one row.')
# No need to check for columns in a structured array -> this is handled
# by the dtype checker.
if not fuav.is_structured_array(X):
if X.shape[1] != self._X.shape[1]:
raise IncorrectShapeError(('X must have the same number of '
'columns as the training data '
'({}).').format(self._X.shape[1]))
probabilities = np.empty((X.shape[0], self._unique_y.shape[0]))
if self._k < self._X_n:
distances = self._get_distances(X)
knn = np.argpartition(distances, self._k, axis=0)
probabilities = []
for column in knn.T:
close_labels = self._y[column[:self._k]]
values, counts = np.unique(close_labels, return_counts=True)
total_counts = np.sum(counts)
probs = np.zeros((self._unique_y.shape[0], ))
for i in range(values.shape[0]):
ind = np.where(self._unique_y == values[i])[0]
probs[ind] = counts[i] / total_counts
probabilities.append(probs)
probabilities = np.array(probabilities)
else:
probabilities = np.tile(self._unique_y_probabilities,
(X.shape[0], 1))
return probabilities
def predict(self, X: np.ndarray) -> np.ndarray:
"""
Predicts labels of new instances with the fitted model.
Parameters
----------
X : numpy.ndarray
The data for which labels will be predicted.
Raises
------
IncorrectShapeError
X is not a 2-dimensional array, it has 0 rows or it has a different
number of columns than the training data.
UnfittedModelError
Raised when trying to predict data when the model has not been
fitted yet. Try using the ``fit`` method to fit the model first.
ValueError
X has a different dtype than the data used to fit the model.
Returns
-------
predictions : numpy.ndarray
Predicted class labels for each data point.
"""
# pylint: disable=too-many-locals,too-many-branches
if not self._is_fitted:
raise UnfittedModelError('This model has not been fitted yet.')
if not fuav.is_2d_array(X):
raise IncorrectShapeError('X must be a 2-dimensional array. If '
'you want to predict a single data '
'point please format it as a single row '
'in a 2-dimensional array.')
if not fuav.are_similar_dtype_arrays(X, self._X):
raise ValueError('X must have the same dtype as the training '
'data.')
if not X.shape[0]:
raise IncorrectShapeError('X must have at least one row.')
# No need to check for columns in a structured array -> this is handled
# by the dtype checker.
if not fuav.is_structured_array(X):
if X.shape[1] != self._X.shape[1]:
raise IncorrectShapeError(('X must have the same number of '
'columns as the training data '
'({}).').format(self._X.shape[1]))
predictions = np.empty((X.shape[0], ))
if self._k < self._X_n:
distances = self._get_distances(X)
# If there are 3 nearest neighbours within distances 1, 2 and 2 and
# k is set to 2, then argpartition will always take the first
# within distance 2.
knn = np.argpartition(distances, self._k, axis=0)
predictions = []
for column in knn.T:
close_labels = self._y[column[:self._k]]
if self._is_classifier:
values, counts = np.unique(close_labels,
return_counts=True)
# If there is a tie in the counts take into consideration
# the overall label count in the training data to resolve
# it.
top_label_index = counts == counts.max()
top_label_unique_sorted = np.sort(values[top_label_index])
assert len(top_label_unique_sorted.shape) == 1, \
'This should be a flat array.'
if top_label_unique_sorted.shape[0] > 1:
# Resolve the tie.
# Get count of these label for the training data.
labels_filter = np.array(self._unique_y.shape[0] *
[False])
for top_prediction in top_label_unique_sorted:
unique_y_filter = self._unique_y == top_prediction
np.logical_or(labels_filter,
unique_y_filter,
out=labels_filter)
g_top_label = self._unique_y[labels_filter]
g_top_label_counts = (
self._unique_y_counts[labels_filter])
# What if any of the global labels have the same count?
g_top_label_index = g_top_label_counts == np.max(
g_top_label_counts)
g_top_label_sorted = np.sort(
g_top_label[g_top_label_index])
prediction = g_top_label_sorted[0]
else:
prediction = top_label_unique_sorted[0]
else:
prediction = close_labels.mean()
predictions.append(prediction)
predictions = np.array(predictions)
else:
predictions = np.array(X.shape[0] * [self._majority_label])
return predictions