决策树C4.5算法复现（根据ID3算法改进）

			决策树C4.5算法复现（基于数据集win分类）

---

C4.5 对比 ID3
优势：①ID3仅能处理离散值，C4.5可以处理连续值（采用二分法选择最佳分类标准）
劣势：①:C4.5可以处理缺失值，ID3无法处理缺失值

本文主要生成整棵决策树，关于剪枝处理和对缺失值的处理以后我会慢慢补充`

from scipy import *
from math import log
import operator
from sklearn.model_selection import train_test_split
import numpy as np
import pandas as pd

def load_dataSet(train_size):
    """
    主要划分了训练集和测试集
    主要使用的是pandas来读取exel表并且用sklearn库来划分测试集和训练集
    """
    fpath = r'd:win.xls'
    object = pd.read_excel(fpath)
    dataSet = object.iloc[0:179, 1:14]
    trans_dataSet = dataSet.values.tolist()
    #X = np.array(m1)
    #k1 = object.iloc[0:150, 1:5]
    #k2 = k1.values.tolist()
    list1 = []
    for i in trans_dataSet:
        list1.append(i)
    data_size = len(list1)
    test_data_size = data_size - train_size
    train_data, test_data = train_test_split(list1, test_size=test_data_size / data_size)
    return train_data, test_data


def Ent(data_set):
    """
    本处计算信息熵
    """
    num_entries = len(data_set)
    label_number = {
   }
    for entry in data_set:
        label = entry[-1]
        if label in label_number.keys():
            label_number[label] += 1
        else:
            label_number[label] = 1
    info_D = 0.0
    for label in label_number.keys():
        prob = float(label_number[label]) / num_entries
        info_D -= prob * log(prob, 2)
    return info_D


def split_data_set(data_set, index, value, continuo, part=0):
    """
    本处主要是对连续值和离散值的处理
    """
    rest_data_set = []
    if continuo ==False:
        for entry in data_set:
            if entry[index] == value:
                reduced_entry = entry[:index]
                reduced_entry.extend(entry[index + 1:])  # 划分后去除数据中第index列的值
                rest_data_set.append(reduced_entry)
    else:
        for entry in data_set:
            if part == 0 and float(entry[index]) <= value:  # 求划分点左侧的数据集
                reduced_entry = entry[:index]
                reduced_entry.extend(entry[index + 1:])  # 划分后去除数据中第index列的值
                rest_data_set