《解锁决策树算法：机器学习领域的实用利器及其多面应用》

import numpy as np
from collections import Counter
from math import log

def entropy(y):
    counter = Counter(y)
    res = 0.0
    for num in counter.values():
        p = num / len(y)
        res -= p * log(p, 2)
    return res

def split(X, y, d, value):
    index_a = (X[:, d] <= value)
    index_b = (X[:, d] > value)
    return X[index_a], X[index_b], y[index_a], y[index_b]

def try_split(X, y):
    best_entropy = float('inf')
    best_d, best_v = -1, -1
    for d in range(X.shape[1]):
        sorted_index = np.argsort(X[:, d])
        for i in range(1, len(X)):
            if X[sorted_index[i], d]!= X[sorted_index[i - 1], d]:
                v = (X[sorted_index[i], d] + X[sorted_index[i - 1], d]) / 2
                X_l, X_r, y_l, y_r = split(X, y, d, v)
                p_l, p_r = len(X_l) / len(X), len(X_r) / len(X)
                e = p_l * entropy(y_l) + p_r * entropy(y_r)
                if e < best_entropy:
                    best_entropy, best_d, best_v = e, d, v
    return best_entropy, best_d, best_v

# 使用示例（这里需要自行准备数据集X和标签y）
# X, y =...  # 数据集和标签
# best_entropy, best_d, best_v = try_split(X, y)
# print("Best Entropy:", best_entropy)
# print("Best Feature:", best_d)
# print("Best Value:", best_v)

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
from sklearn.metrics import accuracy_score, mean_squared_error

# 加载数据集
iris = load_iris()
X, y = iris.data, iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 构建分类决策树模型（CART分类树）
clf = DecisionTreeClassifier(criterion='gini', max_depth=None, min_samples_split=2, min_samples_leaf=1, random_state=42)
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print("Classification Accuracy:", accuracy_score(y_test, y_pred))

# 构建回归决策树模型（CART回归树，这里以随机生成的数据集为例）
# 注意：为了演示回归树，这里使用了一个简单的随机数据集，实际使用时请替换为真实数据集
np.random.seed(42)
X_reg = np.random.rand(100, 1) * 10  # 特征数据
y_reg = 2 * X_reg.squeeze() + 1 + np.random.randn(100) * 2  # 目标数据（带噪声的线性关系）
X_train_reg, X_test_reg, y_train_reg, y_test_reg = train_test_split(X_reg, y_reg, test_size=0.3, random_state=42)

reg = DecisionTreeRegressor(criterion='squared_error', max_depth=None, min_samples_split=2, min_samples_leaf=1, random_state=42)
reg.fit(X_train_reg, y_train_reg)
y_pred_reg = reg.predict(X_test_reg)
print("Regression MSE:", mean_squared_error(y_test_reg, y_pred_reg))

from sklearn.datasets import load_iris
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt

# 加载数据
iris = load_iris()
X = iris.data
y = iris.target

# 拆分数据
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0, test_size=1 / 4)

# 训练模型
dt_model = DecisionTreeClassifier(max_depth=4)
dt_model.fit(X_train, y_train)

# 可视化决策树
plt.figure(figsize=(15, 9))
plot_tree(dt_model, filled=True, feature_names=iris.feature_names, class_names=iris.target_names)
plt.show()