使用python+sklearn的决策树方法预测是否有信用风险

import numpy as np

import pandas as pd

names=("Balance,Duration,History,Purpose,Credit amount,Savings,Employment,instPercent,sexMarried,Guarantors,Residence duration,Assets,Age,concCredit,Apartment,Credits,Occupation,Dependents,hasPhone,Foreign,lable").split(',')

data=pd.read_csv("Desktop/sunshengyun/data/german/german.data",sep='\s+',names=names)

data.head()

	Balance	Duration	History	Purpose	Credit amount	Savings	Employment	instPercent	sexMarried	Guarantors	…	Assets	Age	concCredit	Apartment	Credits	Occupation	Dependents	hasPhone	Foreign	lable
0	A11	6	A34	A43	1169	A65	A75	4	A93	A101	…	A121	67	A143	A152	2	A173	1	A192	A201	1
1	A12	48	A32	A43	5951	A61	A73	2	A92	A101	…	A121	22	A143	A152	1	A173	1	A191	A201	2
2	A14	12	A34	A46	2096	A61	A74	2	A93	A101	…	A121	49	A143	A152	1	A172	2	A191	A201	1
3	A11	42	A32	A42	7882	A61	A74	2	A93	A103	…	A122	45	A143	A153	1	A173	2	A191	A201	1
4	A11	24	A33	A40	4870	A61	A73	3	A93	A101	…	A124	53	A143	A153	2	A173	2	A191	A201	2

5 rows × 21 columns

data.Balance.unique()

array([‘A11’, ‘A12’, ‘A14’, ‘A13’], dtype=object)

data.count()

Balance 1000 Duration 1000 History 1000 Purpose 1000 Credit amount 1000 Savings 1000 Employment 1000 instPercent 1000 sexMarried 1000 Guarantors 1000 Residence duration 1000 Assets 1000 Age 1000 concCredit 1000 Apartment 1000 Credits 1000 Occupation 1000 Dependents 1000 hasPhone 1000 Foreign 1000 lable 1000 dtype: int64

#部分变量描述性统计分析
data.describe()

	Duration	Credit amount	instPercent	Residence duration	Age	Credits	Dependents	lable
count	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000	1000.000000
mean	20.903000	3271.258000	2.973000	2.845000	35.546000	1.407000	1.155000	1.300000
std	12.058814	2822.736876	1.118715	1.103718	11.375469	0.577654	0.362086	0.458487
min	4.000000	250.000000	1.000000	1.000000	19.000000	1.000000	1.000000	1.000000
25%	12.000000	1365.500000	2.000000	2.000000	27.000000	1.000000	1.000000	1.000000
50%	18.000000	2319.500000	3.000000	3.000000	33.000000	1.000000	1.000000	1.000000
75%	24.000000	3972.250000	4.000000	4.000000	42.000000	2.000000	1.000000	2.000000
max	72.000000	18424.000000	4.000000	4.000000	75.000000	4.000000	2.000000	2.000000

data.Duration.unique()

array([ 6, 48, 12, 42, 24, 36, 30, 15, 9, 10, 7, 60, 18, 45, 11, 27, 8, 54, 20, 14, 33, 21, 16, 4, 47, 13, 22, 39, 28, 5, 26, 72, 40], dtype=int64)

data.History.unique()

array([‘A34’, ‘A32’, ‘A33’, ‘A30’, ‘A31’], dtype=object)

data.groupby('Balance').size().order(ascending=