python实现非正态分布转正态分布(BoxCox转换)

1

import pandas as pd

2

import matplotlib.pyplot as plt

3

import seaborn as sns

4

import matplotlib

5

from scipy import stats

6

import warnings

7

warnings.filterwarnings("ignore")

8

9

def Box_Cox(file,sheet_name):

10

df1 = pd.read_excel(file,sheet_name)

11

print(df1["患者密度（人/10万人）"])

12

sns.distplot(df1["患者密度（人/10万人）"],color = "#D86457")

13

matplotlib.rcParams['font.sans-serif'] = ['SimHei']

14

matplotlib.rcParams['axes.unicode_minus'] = False

15

plt.show()

16

17

fig = plt.figure()

18

ax = fig.add_subplot(111)

19

stats.boxcox_normplot(df1["患者密度（人/10万人）"], -20, 20,plot = ax)

20

plt.axvline(x = stats.boxcox_normmax(df1["患者密度（人/10万人）"]),color = "#D86457")

21

plt.show()

22

23

print(stats.boxcox_normmax(df1["患者密度（人/10万人）"]))

24

x = stats.boxcox(df1["患者密度（人/10万人）"],stats.boxcox_normmax(df1["患者密度（人/10万人）"]))

25

sns.distplot(x,color = "#D86457")

26

plt.show()

27

28

df=pd.DataFrame(x,columns=['转换'])

29

print(df)

30

31

if __name__=='__main__':

32

Box_Cox("F:\医学大数据课题\论文终稿修改\实验\差异性分析.xlsx",sheet_name='人口密度分组')