def __init__(self, n_estimators, learning_rate, min_samples_split,
min_impurity, max_depth, regression, debug):
self.n_estimators = n_estimators
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split
self.min_impurity = min_impurity
self.max_depth = max_depth
self.init_estimate = None
self.regression = regression
self.debug = debug
self.multipliers = []
self.bar = progressbar.ProgressBar(widgets=bar_widgets)
# Square loss for regression
# Log loss for classification
self.loss = SquareLoss(grad_wrt_theta=False)
if not self.regression:
self.loss = LogisticLoss(grad_wrt_theta=False)
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
tree = RegressionTree(min_samples_split=self.min_samples_split,
min_impurity=min_impurity,
max_depth=self.max_depth)
self.trees.append(tree)
def __init__(self,
n_estimators=200,
learning_rate=0.001,
min_samples_split=2,
min_impurity=1e-7,
max_depth=2,
debug=False):
self.n_estimators = n_estimators # Number of trees
self.learning_rate = learning_rate
self.min_samples_split = min_samples_split # The minimum n of sampels to justify split
self.min_impurity = min_impurity # Minimum variance reduction to continue
self.max_depth = max_depth # Maximum depth for tree
self.debug = debug
self.bar = progressbar.ProgressBar(widgets=bar_widgets)
# Log loss for classification
self.loss = LogisticLoss(grad_wrt_theta=False)
# Initialize regression trees
self.trees = []
for _ in range(n_estimators):
tree = XGBoostRegressionTree(
min_samples_split=self.min_samples_split,
min_impurity=min_impurity,
max_depth=self.max_depth,
loss=self.loss)
self.trees.append(tree)
def __init__(self, learning_rate=.1, gradient_descent=True):
self.param = None
self.learning_rate = learning_rate
self.gradient_descent = gradient_descent
self.sigmoid = Sigmoid()
self.log_loss = LogisticLoss()