DecisionTree.py 文件源码

def buildTree(self, data, features):
        classification = data[:, -1]
        uniqueValues = set(classification)
        if len(uniqueValues) == 1:
            return classification[0]
        if len(data[0]) == 1:
            return self.majorityCnt(classification)

        infomatinoGain = InformationGain()
        bestFeature = infomatinoGain.chooseBestFeatureToSplit(data)
        bestFeatureLabel = features[bestFeature]
        decisionTree = {bestFeatureLabel: {}}
        featureValues = set(data[:, bestFeature])
        tmpFeatures = np.delete(features, bestFeature, axis=0)
        for value in featureValues:
            subData = infomatinoGain.splitData(data, bestFeature, value)
            decisionTree[bestFeatureLabel][value] = self.buildTree(subData, tmpFeatures)
        return decisionTree