Python批量统计数据分布的偏度并画图

代码

import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import os
import re
path = r'F:/偏度统计'
FileNames = os.listdir(path)

for fn in FileNames:
    if re.search(r'\.txt$', fn):
        fullfilename = os.path.join(path, fn)
        df = pd.read_csv(fullfilename, header=0, sep="\t")
        print(df['0'].skew()) #%偏度计算
        print(df['0'].kurt()) #%峰度计算
        plt.hist(df['0'], 100, density=True, facecolor='b', stacked=True, alpha=0.9)
        plt.xlabel("{}".format(fn)[:-4])
        plt.ylabel("Beta")
        # 解决中文显示问题
        plt.rcParams['font.sans-serif'] = ['SimHei']
        plt.rcParams['axes.unicode_minus'] = False
        plt.title("偏度：{}".format(df['0'].skew()))
        plt.savefig("密度图{}.jpg".format(fn))
# data = pd.read_csv('./chr1.txt', header=0, sep="\t")
# plt.hist(data["0"], 100, density=True, facecolor='g', stacked=True, alpha=0.9)
# plt.show()
# print(data.shape)
# # print(data["0"].skew())
# print(data["0"].skew()) #%偏度计算
# print(data["0"].kurt()) #%峰度计算

作图结果

上述代码不仅可以计算偏度，还可以计算峰度。偏度的判定标准如下：