决策树和随机森林对红酒数据集进行预测

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_wine
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier,plot_tree
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.svm import SVC

# 加载红酒数据集
wine = load_wine()
X = wine.data
y = wine.target

# 分割数据集为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 检查训练集和测试集特征的形状
print("训练集特征形状：", X_train.shape)
print("测试集特征形状：", X_test.shape)

# 创建决策树算法（最大层数设置为5）并训练
decision_tree = DecisionTreeClassifier(max_depth=5)
decision_tree.fit(X_train, y_train)

import matplotlib.pyplot as plt
plt.figure(figsize=(12, 12))
plot_tree(decision_tree, fontsize=10)
plt.show()

# 创建随机森林算法（参数设置：有放回的抽取样本；随机抽取的特征数为3；决策树数量为100）并训练
random_forest = RandomForestClassifier(bootstrap=True, max_features=3, n_estimators=100)
random_forest.fit(X_train, y_train)

# 创建支持向量机算法（参数设置：径向基内核）并训练
svm = SVC(kernel='rbf')
svm.fit(X_train, y_train)

# 使用训练好的模型预测测试集的标签
y_pred_dt = decision_tree.predict(X_test)
y_pred_rf = random_forest.predict(X_test)
y_pred_svm = svm.predict(X_test)

# 计算模型的分类准确率（模型得分）
accuracy_dt = accuracy_score(y_test, y_pred_dt)
accuracy_rf = accuracy_score(y_test, y_pred_rf)
accuracy_svm = accuracy_score(y_test, y_pred_svm)

print("决策树模型分类准确率：", accuracy_dt)
print("随机森林模型分类准确率：", accuracy_rf)
print("支持向量机模型分类准确率：", accuracy_svm)