C4.5算法的python实现

C4.5算法是一种决策树算法，用于从数据集中生成分类树。以下是C4.5算法的Python实现。

首先，需要导入必要的库：

import pandas as pd
import numpy as np
import math

接下来，定义一个函数来计算数据集的香农熵：

def entropy(target_col):
    elements,counts = np.unique(target_col,return_counts = True)
    entropy = np.sum([(-counts[i]/np.sum(counts))*np.log2(counts[i]/np.sum(counts)) for i in range(len(elements))])
    return entropy

然后，定义一个函数来计算数据集的信息增益：

def InfoGain(data,split_attribute_name,target_name="class"):
    total_entropy = entropy(data[target_name])
    vals,counts= np.unique(data[split_attribute_name],return_counts=True)
    Weighted_Entropy = np.sum([(counts[i]/np.sum(counts))*entropy(data.where(data[split_attribute_name]==vals[i]).dropna()[target_name]) for i in range(len(vals))])
    Information_Gain = total_entropy - Weighted_Entropy
    return Information_Gain

接着，定义一个函数来选择最佳分裂属性：

def ID3(data,originaldata,features,target_attribute_name="class",parent_node_class = None):
    if len(np.unique(data[target_attribute_name])) <= 1:
        return np.unique(data[target_attribute_name])[0]
    elif len(data)==0:
        return np.unique(originaldata[target_attribute_name])[np.argmax(np.unique(originaldata[target_attribute_name],return_counts=True)[1])]
    elif len(features) ==0:
        return parent_node_class
    else:
        parent_node_class = np.unique(data[target_attribute_name])[np.argmax(np.unique(data[target_attribute_name],return_counts=True)[1])]
        item_values = [InfoGain(data,feature,target_attribute_name) for feature in features]
        best_feature_index = np.argmax(item_values)
        best_feature = features[best_feature_index]
        tree = {best_feature:{}}
        features = [i for i in features if i != best_feature]
        for value in np.unique(data[best_feature]):
            value = value
            sub_data = data.where(data[best_feature] == value).dropna()
            subtree = ID3(sub_data,dataset,features,target_attribute_name,parent_node_class)
            tree[best_feature][value] = subtree
        return(tree)

最后，调用上述函数来生成分类树：

dataset = pd.read_csv('your_data.csv')
features = list(dataset.columns[:-1])
tree = ID3(dataset,dataset,features)
print(tree)

这就是C4.5算法的Python实现。