信息增益pycharm代码

好的，这里是计算信息增益的 Python 代码：

import math

def entropy(data):
    """
    计算数据集的熵
    :param data: 数据集，格式为列表，每个元素为一个样本，最后一个元素为标签
    :return: 熵
    """
    label_count = {}
    for sample in data:
        label = sample[-1]
        if label not in label_count:
            label_count[label] = 0
        label_count[label] += 1
    entropy = 0.0
    for label in label_count:
        prob = float(label_count[label]) / len(data)
        entropy -= prob * math.log(prob, 2)
    return entropy

def split_data(data, axis, value):
    """
    根据特征划分数据集
    :param data: 数据集，格式为列表，每个元素为一个样本，最后一个元素为标签
    :param axis: 特征所在的列
    :param value: 特征的取值
    :return: 划分后的子集
    """
    sub_data = []
    for sample in data:
        if sample[axis] == value:
            sub_sample = sample[:axis]
            sub_sample.extend(sample[axis+1:])
            sub_data.append(sub_sample)
    return sub_data

def choose_best_feature(data):
    """
    选择最好的特征
    :param data: 数据集，格式为列表，每个元素为一个样本，最后一个元素为标签
    :return: 最好的特征所在的列
    """
    num_features = len(data[0]) - 1
    base_entropy = entropy(data)
    best_info_gain = 0.0
    best_feature = -1
    for i in range(num_features):
        feature_list = [sample[i] for sample in data]
        unique_values = set(feature_list)
        new_entropy = 0.0
        for value in unique_values:
            sub_data = split_data(data, i, value)
            prob = len(sub_data) / float(len(data))
            new_entropy += prob * 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

# 示例数据
data = [[1, 1, 'yes'],
        [1, 1, 'yes'],
        [1, 0, 'no'],
        [0, 1, 'no'],
        [0, 1, 'no']]
# 计算信息增益
print(choose_best_feature(data))

输出结果为 `0`，表示第一个特征（即第一列）是最好的特征。