python 正态分布

 

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from scipy.stats import norm
from scipy.stats import shapiro
import statistics
data= pd.read_csv('ethercat3.csv',usecols=['Time'])
clo_t = data['Time'].tolist()
stat, p = shapiro(clo_t)
print('stat=%.3f, p=%.3f \n' % (stat, p))
if p > 0.05:
    print("Data follows Normal Distribution")
else:
    print("Data does not follow Normal Distribution")

[root@centos7 ~]# python3  norm_test.py 
/usr/local/lib64/python3.6/site-packages/scipy/stats/morestats.py:1681: UserWarning: p-value may not be accurate for N > 5000.
  warnings.warn("p-value may not be accurate for N > 5000.")
stat=0.636, p=0.000 

Data does not follow Normal Distribution

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from scipy.stats import norm
from scipy.stats import shapiro
import statistics
data= pd.read_csv('ethercat3.csv',usecols=['Time'])
clo_t = data['Time'].tolist()
stat, p = shapiro(clo_t[0:4000])
print('stat=%.3f, p=%.3f \n' % (stat, p))
if p > 0.05:
    print("Data follows Normal Distribution")
else:
    print("Data does not follow Normal Distribution")

import matplotlib.pyplot as plt
import numpy as np
import matplotlib

# 设置matplotlib正常显示中文和负号
matplotlib.rcParams['font.sans-serif']=['SimHei'] # 用黑体显示中文
matplotlib.rcParams['axes.unicode_minus']=False # 正常显示负号
# 随机生成（10000,）服从正态分布的数据
data = np.random.randn(10000)
"""
绘制直方图
data:必选参数，绘图数据
bins:直方图的长条形数目，可选项，默认为10
normed:是否将得到的直方图向量归一化，可选项，默认为0，代表不归一化，显示频数。normed=1，表示归一化，显示频率。
facecolor:长条形的颜色
edgecolor:长条形边框的颜色
alpha:透明度
"""
plt.hist(data, bins=40, normed=0, facecolor="blue", edgecolor="black", alpha=0.7)
# 显示横轴标签
plt.xlabel("区间")
# 显示纵轴标签
plt.ylabel("频数/频率")
# 显示图标题
plt.title("频数/频率分布直方图")
plt.show()

Normality Test with Python in Data Science

Is my data normal?