常见的机器学习算法（十）决策树、随机森林、极限树

红太狼 2023-02-12 13:29 39阅读 0赞

直接调用sklearn的API：

from sklearn import tree                              #决策树分类器#
    module = tree.DecisionTreeClassifier(criterion='gini')
    module.fit(x, y)
    module.score(x, y)
    module.predict(test)

from sklearn.ensemble import RandomForestClassifier  #随机森林#
    from sklearn.ensemble import RandomForestRegressor
    module = RandomForestClassifier()
    module.fit(x, y)
    module.predict(test)

**整体代码1：**

from sklearn.datasets import load_iris
    from sklearn.tree import DecisionTreeClassifier
    from sklearn.model_selection import cross_val_score  # 交叉验证函数
    
    iris = load_iris()
    dtc = DecisionTreeClassifier()
    dtc.fit(iris.data, iris.target)
    
    # 使用决策树分类器作为评估模型，iris.data鸢尾花数据作为特征，iris.target鸢尾花分类标签作为目标结果，设定cv为10，使用10折交叉验证，得到最终的交叉验证得分。
    print(cross_val_score(dtc, iris.data, iris.target, cv=10))
    print('-----------------------------')
    print(dtc.predict(iris.data))#预测出对应标签

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2_size_16_color_FFFFFF_t_70][]

**整体代码2：**

from sklearn.model_selection import cross_val_score #交叉验证
    from sklearn.datasets import make_blobs
    from sklearn.tree import DecisionTreeClassifier #决策树
    from sklearn.ensemble import RandomForestClassifier #随机森林
    from sklearn.ensemble import ExtraTreesClassifier #极限树
    
    #创建100个类,共10000个样本，每个样本10个特征
    x ,y = make_blobs(n_samples=10000, n_features=10, centers=100, random_state=0)
    
    dtc = DecisionTreeClassifier(random_state=0)
    score_dtc = cross_val_score(dtc, x, y)
    print('score_dtc均值: ', score_dtc.mean())
    
    rfc = RandomForestClassifier(n_estimators=10, random_state=0)
    score_rfc = cross_val_score(rfc, x, y)
    print('score_rfc均值: ', score_rfc.mean())
    
    etc = ExtraTreesClassifier(n_estimators=10, random_state=0)
    score_etc = cross_val_score(etc, x, y)
    print('score_etc均值: ', score_etc.mean())

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2_size_16_color_FFFFFF_t_70 1][]

性能对比： 极限树 > 随机森林 > 决策树

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20200526151933680.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2,size_16,color_FFFFFF,t_70
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2_size_16_color_FFFFFF_t_70 1]: https://img-blog.csdnimg.cn/20200526164542659.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzM5OTM4NjY2,size_16,color_FFFFFF,t_70