def normalize_sample(self, X):
"""
Normalize the features in order to have the same influence during
training.
Parameters
----------
X: list or array or numpy.ndarray
features.
Returns
-------
array:
normalized samples
"""
normalized_sample = []
for i in range(len(X)):
if (self._nominal_attributes is not None and i
not in self._nominal_attributes) and self.samples_seen > 1:
mean = self.sum_of_attribute_values[i] / self.samples_seen
sd = compute_sd(self.sum_of_attribute_squares[i],
self.sum_of_attribute_values[i],
self.samples_seen)
if sd > 0:
normalized_sample.append(float(X[i] - mean) / (3 * sd))
else:
normalized_sample.append(0.0)
else:
normalized_sample.append(0.0)
if self.samples_seen > 1:
normalized_sample.append(
1.0) # Value to be multiplied with the constant factor
else:
normalized_sample.append(0.0)
return np.asarray(normalized_sample)
def predict(self, X):
"""Predicts the target value using mean class or the perceptron.
Parameters
----------
X: numpy.ndarray of shape (n_samples, n_features)
Samples for which we want to predict the labels.
Returns
-------
numpy.ndarray
Predicted target values.
"""
predictions = []
if self.samples_seen > 0:
r, _ = get_dimensions(X)
for i in range(r):
if self.leaf_prediction == _TARGET_MEAN:
votes = self.get_votes_for_instance(
X[i]) # Gets observed data statistics
if votes == {}:
# Tree is empty, all target_values equal, default to zero
predictions.append(0)
else:
number_of_samples_seen = votes[0]
sum_of_values = votes[1]
predictions.append(sum_of_values /
number_of_samples_seen)
elif self.leaf_prediction == _PERCEPTRON:
if self.samples_seen > 1:
perceptron_weights = self.get_weights_for_instance(
X[i])
if perceptron_weights is None:
predictions.append(0.0)
continue
normalized_sample = self.normalize_sample(X[i])
normalized_prediction = np.dot(perceptron_weights,
normalized_sample)
# De-normalize prediction
mean = self.sum_of_values / self.samples_seen
sd = compute_sd(self.sum_of_squares,
self.sum_of_values, self.samples_seen)
predictions.append(normalized_prediction * sd * 3 +
mean)
else:
predictions.append(0.0)
else:
# Model is empty
predictions.append(0.0)
return np.asarray(predictions)
def normalize_target_value(self, y):
"""
Normalize the target in order to have the same influence during the process of
training.
Parameters
----------
y: float
target value
Returns
-------
float:
normalized target value
"""
if self.samples_seen > 1:
mean = self.sum_of_values / self.samples_seen
sd = compute_sd(self.sum_of_squares, self.sum_of_values, self.samples_seen)
if sd > 0:
return float(y - mean) / (3 * sd)
return 0.0
