给一个csv文件数据,python实现c4.5决策树算法

好的，下面是一个简单的示例，使用Python实现C4.5决策树算法：

import pandas as pd
import numpy as np
from math import log2

# 计算数据集的信息熵
def calc_entropy(data):
    target_col = data.iloc[:, -1]
    _, counts = np.unique(target_col, return_counts=True)
    freqs = counts / counts.sum()
    entropy = -freqs.dot(np.log2(freqs))
    return entropy

# 计算数据集的信息增益
def calc_info_gain(data, feature):
    entropy_before = calc_entropy(data)
    vals, counts = np.unique(data[feature], return_counts=True)
    freqs = counts / counts.sum()
    entropy_after = np.sum(freqs * np.array([calc_entropy(data[data[feature]==v]) for v in vals]))
    info_gain = entropy_before - entropy_after
    return info_gain

# 计算数据集的基尼指数
def calc_gini(data):
    target_col = data.iloc[:, -1]
    _, counts = np.unique(target_col, return_counts=True)
    freqs = counts / counts.sum()
    gini = 1 - np.sum(freqs ** 2)
    return gini

# 计算数据集的基尼增益
def calc_gini_gain(data, feature):
    gini_before = calc_gini(data)
    vals, counts = np.unique(data[feature], return_counts=True)
    freqs = counts / counts.sum()
    gini_after = np.sum(freqs * np.array([calc_gini(data[data[feature]==v]) for v in vals]))
    gini_gain = gini_before - gini_after
    return gini_gain

# 选择最佳分裂特征
def choose_best_feature(data, criterion):
    if criterion == 'entropy':
        func = calc_info_gain
    elif criterion == 'gini':
        func = calc_gini_gain
    else:
        raise ValueError('Invalid criterion')
    info_gains = [func(data, feature) for feature in data.columns[:-1]]
    best_feature_idx = np.argmax(info_gains)
    return data.columns[best_feature_idx]

# 构造决策树
def build_tree(data, criterion):
    target_col = data.iloc[:, -1]
    if len(set(target_col)) == 1:
        return target_col.values[0]
    if data.shape[1] == 1:
        return target_col.value_counts().idxmax()
    best_feature = choose_best_feature(data, criterion)
    tree = {best_feature: {}}
    for val in np.unique(data[best_feature]):
        subset = data[data[best_feature] == val].drop(best_feature, axis=1)
        subtree = build_tree(subset, criterion)
        tree[best_feature][val] = subtree
    return tree

# 预测新样本的类别
def predict(tree, sample):
    for feature in tree.keys():
        val = sample[feature]
        if val in tree[feature]:
            subtree = tree[feature][val]
            if isinstance(subtree, dict):
                return predict(subtree, sample)
            else:
                return subtree

# 加载数据集
data = pd.read_csv('dataset.csv')

# 构建决策树
tree = build_tree(data, 'entropy')

# 预测新样本的类别
sample = {'age': 'young', 'income': 'high', 'student': 'no', 'credit_rating': 'fair'}
prediction = predict(tree, sample)
print('Prediction:', prediction)

以上代码中，`calc_entropy()`、`calc_gini()`、`calc_info_gain()`、`calc_gini_gain()`函数分别用于计算数据集的信息熵、基尼指数、信息增益和基尼增益，`choose_best_feature()`函数用于选择最佳分裂特征，`build_tree()`函数用于构建决策树，`predict()`函数用于预测新样本的类别。最后使用示例数据集进行测试，预测结果为`Prediction: no`。