2.2正态分布检测

# -*- encoding: utf-8 -*-

import sys
import numpy as np
import pandas as pd
from scipy import stats as sts
import matplotlib.pyplot as plt
import matplotlib as mpl

if __name__ == "__main__":
    # 文件读取
    rf = pd.read_csv('http://jse.amstat.org/datasets/normtemp.dat.txt',header = None,sep = '\s+',names=['体温','性别','心率']);
    print("结果数据概览：")
    print(rf.head())
    print("体温数据概览：")
    print(rf['体温'].describe())

    # 偏态系数
    print("偏态系数："+str(sts.skew(rf['体温'])))
    # 峰态系数
    print("峰度系数："+str(sts.kurtosis(rf['体温'])))


    u = rf['体温'].mean() #计算均值
    std = rf['体温'].std() #计算标准差
    # 正态检测
    # 适用于小样本资料（3≤n≤50）
    print(sts.shapiro(rf['体温']))
    # 适用于大样本
    print(sts.kstest(rf['体温'],'norm',(u,std)))
    # pvalue值大于0.05即认为符合正态分布
```![任乌拉](https://img.haomeiwen.com/i8940211/db23dafd9958f6b7.png?imageMogr2/auto-orient/strip%7CimageView2/2/w/1240)