用于分类的最小方差的Python - bin大小

import numpy as np

def find_optimal_bin_size(data):
    min_variance = float('inf')
    optimal_bin_size = None

    for bin_size in range(1, len(data)):
        hist, bin_edges = np.histogram(data, bins=bin_size)
        bin_variances = []

        for i in range(bin_size):
            bin_data = data[(data >= bin_edges[i]) & (data < bin_edges[i+1])]
            bin_variances.append(np.var(bin_data))

        variance = np.mean(bin_variances)
        if variance < min_variance:
            min_variance = variance
            optimal_bin_size = bin_size

    return optimal_bin_size

# 示例数据
data = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]

# 计算最小方差的bin大小
optimal_bin_size = find_optimal_bin_size(data)
print("最小方差的bin大小为:", optimal_bin_size)