在Python中使用决策树进行过拟合和欠拟合的检测

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor
import matplotlib.pyplot as plt
import numpy as np

# 生成数据集
X, y = make_classification(n_samples=1000, n_features=5, n_informative=3, n_redundant=2, random_state=42)

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 训练模型
dt = DecisionTreeRegressor(max_depth=10)
dt.fit(X_train, y_train)

# 绘制学习曲线
train_errors = []
test_errors = []
for i in range(1, 100):
    dt = DecisionTreeRegressor(max_depth=i)
    dt.fit(X_train, y_train)
    train_errors.append(dt.score(X_train, y_train))
    test_errors.append(dt.score(X_test, y_test))

plt.plot(np.arange(1, 100), train_errors, label='Training Score')
plt.plot(np.arange(1, 100), test_errors, label='Validation Score')
plt.xlabel('Tree Depth')
plt.ylabel('Score')
plt.legend()
plt.show()

# 训练深度为20的决策树
dt = DecisionTreeRegressor(max_depth=20)
dt.fit(X_train, y_train)

# 检查过拟合
train_score = dt.score(X_train, y_train)
test_score = dt.score(X_test, y_test)

print("Training Score: {:.2f}".format(train_score))
print("Test Score: {:.2f}".format(test_score))

Training Score: 1.00
Test Score: 0.42

from sklearn.tree import export_graphviz
import pydotplus
from IPython.display import Image

dot_data = export_graphviz(dt, out_file=None, feature_names=['Feature 1', 'Feature 2', 'Feature 3', 'Feature 4', 'Feature 5'])
graph = pydotplus.graph_from_dot_data(dot_data)
Image(graph.create_png())