Numpy实现DecisionTree(2)

class DecisionNode():

“”"Class that represents a decision node or leaf in the decision tree

Parameters:

---

feature_i: int

Feature index which we want to use as the threshold measure.

threshold: float

The value that we will compare feature values at feature_i against to

determine the prediction.

value: float

The class prediction if classification tree, or float value if regression tree.

true_branch: DecisionNode

Next decision node for samples where features value met the threshold.

false_branch: DecisionNode

Next decision node for samples where features value did not meet the threshold.

“”"

def init(self, feature_i=None, threshold=None,

value=None, true_branch=None, false_branch=None):

self.feature_i = feature_i # Index for the feature that is tested

self.threshold = threshold # Threshold value for feature

self.value = value # Value if the node is a leaf in the tree

self.true_branch = true_branch # ‘Left’ subtree

self.false_branch = false_branch # ‘Right’ subtree

Super class of RegressionTree and ClassificationTree

class DecisionTree(object):

“”"Super class of RegressionTree and ClassificationTree.

Parameters:

---

min_samples_split: int

The minimum number of samples needed to make a split when building a tree.

min_impurity: float

The minimum impurity required to split the tree further.

max_depth: int

The maximum depth of a tree.

loss: function

Loss function that is used for Gradient Boosting models to calculate impurity.

“”"

def init(self, min_samples_split=2, min_impurity=1e-7,

max_depth=float(“inf”), loss=None):

self.root = None # Root node in dec. tree

Minimum n of samples to justify split

self.min_samples_split = min_samples_split