决策树与随机森林及python测试

最新推荐文章于 2022-06-24 14:16:17 发布

原创最新推荐文章于 2022-06-24 14:16:17 发布 · 269 阅读

0 ·

CC 4.0 BY-SA版权

算法学习专栏收录该内容

10 篇文章

订阅专栏

本文通过决策树和随机森林两种方法对葡萄酒数据集进行分类预测。利用sklearn库中的load_wine数据集，通过训练模型得到分类准确率，并对新样本进行预测。

from sklearn.datasets import load_wine
from sklearn import tree
from sklearn.model_selection import train_test_split
import numpy as np
#决策树
def decision_tree():
    # 酒的分类
    wine_dataset = load_wine()

    # random_state=0，每次生成的随机数不同
    # x代表数据集,y代表分类标签
    x_train, x_test, y_train, y_test = train_test_split(wine_dataset["data"], wine_dataset["target"], random_state=0)

    clf=tree.DecisionTreeClassifier(max_depth=5)
    clf.fit(x_train,y_train)
    print(clf.score(x_train,y_train))
    print(clf.score(x_test, y_test))

    # 使用模型完成预测
    x_news = np.array([[13.2, 2.77, 2.51, 18.5, 96.6, 1.04, 2.55, 0.57, 1.47, 6.2, 1.05, 3.33, 820]])
    prediction = clf.predict(x_news)
    print(wine_dataset["target_names"][prediction])

def random_forest():
    # 酒的分类
    wine_dataset = load_wine()

    # random_state=0，每次生成的随机数不同
    # x代表数据集,y代表分类标签
    x_train, x_test, y_train, y_test = train_test_split(wine_dataset["data"], wine_dataset["target"], random_state=0)

    #设定随机森林中有6棵树
    forest=RandomForestClassifier(n_estimators=6,random_state=3)

    #拟合
    forest.fit(x_train,y_train)
    print(forest.score(x_train,y_train))
    print(forest.score(x_test, y_test))

    # 使用模型完成预测
    x_news = np.array([[13.2, 2.77, 2.51, 18.5, 96.6, 1.04, 2.55, 0.57, 1.47, 6.2, 1.05, 3.33, 820]])
    prediction = forest.predict(x_news)
    print(wine_dataset["target_names"][prediction])