python预测多自变量数据（python实现离散型变量分组统计）

1

import numpy as np

2

import pandas as pd

3

4

def Read_data(file):

5

dt = pd.read_csv(file)

6

dt.columns = ['age' 'sex' 'chest_pain_type' 'resting_blood_pressure' 'cholesterol'

7

'fasting_blood_sugar' 'rest_ecg' 'max_heart_rate_achieved' 'exercise_induced_angina'

8

'st_depression' 'st_slope' 'num_major_vessels' 'thalassemia' 'target']

9

data =dt

10

pd.set_option('display.max_rows' None)

11

pd.set_option('display.max_columns' None)

12

pd.set_option('display.width' None)

13

pd.set_option('display.unicode.ambiguous_as_wide' True)

14

pd.set_option('display.unicode.east_asian_width' True)

15

print(data.head().append(dt.tail()))

16

return data

17

18

def Segment_statistics(data):

19

#=======离散型变量分组统计=========================

20

tmp3 = data.groupby(['chest_pain_type' 'sex'])

21

print(tmp3.count())

22

return

23

24

if __name__=="__main__":

25

data1=Read_data("F:\数据杂坛\\0504\heartdisease\Heart-Disease-Data-Set-main\\UCI Heart Disease Dataset.csv")

26

Segment_statistics(data1)