def get_class_votes(self, X, ht):
# dist = {}
prediction_option = ht.leaf_prediction
# MC
if prediction_option == MAJORITY_CLASS:
dist = self.get_observed_class_distribution()
# NB
elif prediction_option == NAIVE_BAYES:
dist = do_naive_bayes_prediction(
X, self._observed_class_distribution,
self._attribute_observers)
# NBAdaptive
else:
if self._mc_correct_weight > self._nb_correct_weight:
dist = self.get_observed_class_distribution()
else:
dist = do_naive_bayes_prediction(
X, self._observed_class_distribution,
self._attribute_observers)
dist_sum = sum(dist.values()) # sum all values in dictionary
normalization_factor = dist_sum * self.get_error_estimation(
) * self.get_error_estimation()
if normalization_factor > 0.0:
normalize_values_in_dict(dist, normalization_factor)
return dist
def learn_from_instance(self, X, y, weight, ht):
"""Update the node with the provided instance.
Parameters
----------
X: numpy.ndarray of length equal to the number of features.
Instance attributes for updating the node.
y: int
Instance class.
weight: float
The instance's weight.
ht: HoeffdingTree
The Hoeffding Tree to update.
"""
y = ''.join(str(e) for e in y)
y = int(y, 2)
if self._observed_class_distribution == {}:
# All target_values equal, default to class 0
if 0 == y:
self._mc_correct_weight += weight
elif max(self._observed_class_distribution,
key=self._observed_class_distribution.get) == y:
self._mc_correct_weight += weight
nb_prediction = do_naive_bayes_prediction(
X, self._observed_class_distribution,
self._attribute_observers)
if max(nb_prediction, key=nb_prediction.get) == y:
self._nb_correct_weight += weight
super().learn_from_instance(X, y, weight, ht)
def get_class_votes(self, X, ht):
"""Get the votes per class for a given instance.
Parameters
----------
X: numpy.ndarray of length equal to the number of features.
Instance attributes.
ht: HoeffdingTree
Hoeffding Tree.
Returns
-------
dict (class_value, weight)
Class votes for the given instance.
"""
if self._mc_correct_weight > self._nb_correct_weight:
return self._observed_class_distribution
return do_naive_bayes_prediction(X,
self._observed_class_distribution,
self._attribute_observers)
def predict_proba(self, X):
""" Predicts the probability of each sample belonging to each one of the
known classes.
Parameters
----------
X: Numpy.ndarray, shape (n_samples, n_features)
A matrix of the samples we want to predict.
Returns
-------
numpy.ndarray
An array of shape (n_samples, n_features), in which each outer entry is
associated with the X entry of the same index. And where the list in
index [i] contains len(self.target_values) elements, each of which represents
the probability that the i-th sample of X belongs to a certain label.
"""
predictions = deque()
if self._observed_class_distribution == {}:
# Model is empty, all classes equal, default to zero
r, _ = get_dimensions(X)
return np.zeros(r)
else:
r, _ = get_dimensions(X)
for i in range(r):
votes = do_naive_bayes_prediction(
X[i], self._observed_class_distribution,
self._attribute_observers)
if self._classes is not None:
y_proba = np.zeros(int(max(self._classes)) + 1)
else:
y_proba = np.zeros(int(max(votes.keys())) + 1)
for key, value in votes.items():
y_proba[int(key)] = value
predictions.append(y_proba)
return np.array(predictions)
