def _train(self):
# Initialize model with zeros
y_pred = np.zeros(self.n_samples, np.float32)
# Or mean
# y_pred = np.full(self.n_samples, self.y_mean)
for n in range(self.n_estimators):
residuals = self.loss.grad(self.y, y_pred)
tree = Tree(regression=True, criterion=mse_criterion)
# Pass multiple target values to the tree learner
targets = {
# Residual values
'y': residuals,
# Actual target values
'actual': self.y,
# Predictions from previous step
'y_pred': y_pred
}
tree.train(self.X,
targets,
max_features=self.max_features,
min_samples_split=self.min_samples_split,
max_depth=self.max_depth,
loss=self.loss)
predictions = tree.predict(self.X)
y_pred += self.learning_rate * predictions
self.trees.append(tree)
def __init__(self, n_estimators=10, max_features=None, min_samples_split=10, max_depth=None, criterion='mse'):
super(RandomForestRegressor, self).__init__(n_estimators=n_estimators, max_features=max_features,
min_samples_split=min_samples_split, max_depth=max_depth)
if criterion == 'mse':
self.criterion = mse_criterion
else:
raise ValueError()
# Initialize empty regression trees
for _ in range(self.n_estimators):
self.trees.append(Tree(regression=True, criterion=self.criterion))
def __init__(self, n_estimators=10, max_features=None, min_samples_split=10, max_depth=None, criterion='entropy'):
super(RandomForestClassifier, self).__init__(n_estimators=n_estimators, max_features=max_features,
min_samples_split=min_samples_split, max_depth=max_depth,
criterion=criterion)
if criterion == 'entropy':
self.criterion = information_gain
else:
raise ValueError()
# Initialize empty trees
for _ in range(self.n_estimators):
self.trees.append(Tree(criterion=self.criterion))
def _train(self):
# Initialize model with zeros
y_pred = np.zeros(self.n_samples, np.float32)
# Or mean
# y_pred = np.full(self.n_samples, self.y_mean)
for n in range(self.n_estimators):
residuals = self.loss.grad(self.y, y_pred)
tree = Tree(regression=True, criterion=mse_criterion)
# Pass multiple target values to the tree learner
targets = {
# Residual values
'y': residuals,
# Actual target values
'actual': self.y,
# Predictions from previous step
'y_pred': y_pred
}
tree.train(self.X, targets, max_features=self.max_features,
min_samples_split=self.min_samples_split, max_depth=self.max_depth, loss=self.loss)
predictions = tree.predict(self.X)
y_pred += self.learning_rate * predictions
self.trees.append(tree)