随机森林中的样本均值

Question

我确实参加了最高班。如何将Leaf类中的predict方法从取最大类更改为取样本均值？

class Leaf:
    
    def __init__(self, data, labels):
        self.data = data
        self.labels = labels
        self.prediction = self.predict()
        
    def predict(self):
        classes = {} 
        for label in self.labels:
            if label not in classes:
                classes[label] = 0
            classes[label] += 1
              
        prediction = max(classes, key=classes.get)
        return prediction   

测试代码：

%%time
n_trees = 1
my_forest_1 = random_forest(train_data, train_labels, n_trees)

Answer 1

这个我觉得： 取类值的总和，然后除以类的数量。 首先检查是否不为零：

class Leaf:
    def __init__(self, data, labels):
        self.data = data
        self.labels = labels
        self.prediction = self.predict()
    def predict(self):
        classes = {} 
        for label in self.labels:
            if label not in classes:
                classes[label] = 0
            classes[label] += 1
        if len(classes):
            prediction = sum(classes, key=classes.get) / len(classes)
        else:
            prediction = 0 # Default value for when there are no classes
        return prediction