def get_class_votes(self, X, ht):
# dist = {}
prediction_option = ht.leaf_prediction
# MC
if prediction_option == ht._MAJORITY_CLASS:
dist = self.get_observed_class_distribution()
# NB
elif prediction_option == ht._NAIVE_BAYES:
dist = do_naive_bayes_prediction(X, self._observed_class_distribution,
self._attribute_observers)
# NBAdaptive (default)
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:
dist = normalize_values_in_dict(dist, normalization_factor, inplace=False)
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: HoeffdingTreeClassifier
The Hoeffding Tree to update.
"""
if self._observed_class_distribution == {}:
# All classes 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 predict_proba(self, X):
""" Estimates the probability of each sample in X belonging to each of the class-labels.
Parameters
----------
X : Numpy.ndarray of shape (n_samples, n_features)
The matrix of samples one wants to predict the class probabilities for.
Returns
-------
A numpy.ndarray of shape (n_samples, n_labels), 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 class-label.
"""
predictions = deque()
r, _ = get_dimensions(X)
if self._observed_class_distribution == {}:
# Model is empty, all classes equal, default to zero
return np.zeros((r, 1))
else:
for i in range(r):
votes = do_naive_bayes_prediction(X[i], self._observed_class_distribution,
self._attribute_observers)
sum_values = sum(votes.values())
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 / sum_values if sum_values != 0 else 0.0
predictions.append(y_proba)
return np.array(predictions)
def get_class_votes(self, X, hot):
if self.get_weight_seen() >= 0:
return do_naive_bayes_prediction(
X, self._observed_class_distribution,
self._attribute_observers)
else:
return super().get_class_votes(X, hot)
def learn_from_instance(self, X, y, weight, hot):
if self._observed_class_distribution == {}:
# All classes 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, hot)
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 get_class_votes(self, X, vfdr):
"""Get the votes per class for a given instance.
Parameters
----------
X: numpy.ndarray of length equal to the number of features.
Instance attributes.
vfdr: AVFDR
Very Fast Decision Rules.
Returns
-------
dict (class_value, weight)
Class votes for the given instance.
"""
if self.get_weight_seen() >= vfdr.nb_threshold and vfdr.nb_prediction:
return do_naive_bayes_prediction(X, self.observed_class_distribution, self._attribute_observers)
else:
return self.observed_class_distribution
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: HoeffdingTreeClassifier
Hoeffding Tree.
Returns
-------
dict (class_value, weight)
Class votes for the given instance.
"""
if self.get_weight_seen() >= ht.nb_threshold:
return do_naive_bayes_prediction(
X, self._observed_class_distribution, self._attribute_observers
)
else:
return super().get_class_votes(X, ht)
def predict_one(self, X, *, tree=None):
prediction_option = tree.leaf_prediction
# MC
if prediction_option == tree._MAJORITY_CLASS:
dist = self.stats
# NB
elif prediction_option == tree._NAIVE_BAYES:
dist = do_naive_bayes_prediction(X, self.stats,
self.attribute_observers)
# NBAdaptive (default)
else:
dist = super().predict_one(X, tree=tree)
dist_sum = sum(dist.values()) # sum all values in dictionary
normalization_factor = dist_sum * self.error_estimation * self.error_estimation
if normalization_factor > 0.0:
dist = normalize_values_in_dict(dist,
normalization_factor,
inplace=False)
return dist
def get_class_votes(self, X, hot):
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)
