python决策树可视化代码包括信息熵的计算

好的，以下是Python决策树可视化代码，包括信息熵的计算：

import pandas as pd
import numpy as np
import math
import graphviz
from sklearn.tree import DecisionTreeClassifier, export_graphviz

# 计算信息熵
def calc_entropy(data):
    n = len(data)
    label_counts = {}
    for feat_vec in data:
        current_label = feat_vec[-1]
        if current_label not in label_counts:
            label_counts[current_label] = 0
        label_counts[current_label] += 1
    entropy = 0.0
    for key in label_counts:
        prob = float(label_counts[key]) / n
        entropy -= prob * math.log(prob, 2)
    return entropy

# 划分数据集
def split_data(data, axis, value):
    ret_data = []
    for feat_vec in data:
        if feat_vec[axis] == value:
            reduced_feat_vec = feat_vec[:axis]
            reduced_feat_vec.extend(feat_vec[axis+1:])
            ret_data.append(reduced_feat_vec)
    return ret_data

# 选择最优划分特征
def choose_best_feature(data):
    num_features = len(data[0]) - 1
    base_entropy = calc_entropy(data)
    best_info_gain = 0.0
    best_feature = -1
    for i in range(num_features):
        feat_list = [example[i] for example in data]
        unique_vals = set(feat_list)
        new_entropy = 0.0
        for value in unique_vals:
            sub_data = split_data(data, i, value)
            prob = len(sub_data) / float(len(data))
            new_entropy += prob * calc_entropy(sub_data)
        info_gain = base_entropy - new_entropy
        if info_gain > best_info_gain:
            best_info_gain = info_gain
            best_feature = i
    return best_feature

# 统计类别数并返回出现次数最多的类别
def majority_cnt(class_list):
    class_count = {}
    for vote in class_list:
        if vote not in class_count:
            class_count[vote] = 0
        class_count[vote] += 1
    sorted_class_count = sorted(class_count.items(), key=lambda x:x[1], reverse=True)
    return sorted_class_count[0][0]

# 创建决策树
def create_decision_tree(data, labels):
    class_list = [example[-1] for example in data]
    if class_list.count(class_list[0]) == len(class_list):
        return class_list[0]
    if len(data[0]) == 1:
        return majority_cnt(class_list)
    best_feat = choose_best_feature(data)
    best_feat_label = labels[best_feat]
    my_tree = {best_feat_label: {}}
    del(labels[best_feat])
    feat_values = [example[best_feat] for example in data]
    unique_vals = set(feat_values)
    for value in unique_vals:
        sub_labels = labels[:]
        my_tree[best_feat_label][value] = create_decision_tree(split_data(data, best_feat, value), sub_labels)
    return my_tree

# 可视化决策树
def visualize_tree(tree, feature_names):
    dot_data = export_graphviz(tree, out_file=None, feature_names=feature_names, class_names=['0', '1'], filled=True, rounded=True, special_characters=True)
    graph = graphviz.Source(dot_data)
    graph.render("decision_tree")

# 测试代码
if __name__ == '__main__':
    data = pd.read_csv('data.csv')
    feature_names = list(data.columns[:-1])
    data = np.array(data)
    labels = feature_names[:]
    tree = create_decision_tree(data.tolist(), labels)
    visualize_tree(tree, feature_names)

其中，`calc_entropy` 函数用于计算信息熵，`split_data` 函数用于划分数据集，`choose_best_feature` 函数用于选择最优划分特征，`majority_cnt` 函数用于统计类别数并返回出现次数最多的类别，`create_decision_tree` 函数用于创建决策树，`visualize_tree` 函数用于可视化决策树。在测试代码中，我们读取数据集并创建决策树，最后将决策树可视化。