In [2]:
import pandas as pd
# training_data[training_data.apply(lambda x: x['Credit_History'] == 0 and x['Loan_Status'] == 'Y',axis = 1)]
In [9]:
training_data = pd.read_csv('Data/train_u6lujuX_CVtuZ9i.csv')
testing_data = pd.read_csv('Data/test_Y3wMUE5_7gLdaTN.csv')
In [17]:
training_data
Out[17]:
Loan_ID
Gender
Married
Dependents
Education
Self_Employed
ApplicantIncome
CoapplicantIncome
LoanAmount
Loan_Amount_Term
Credit_History
Property_Area
Loan_Status
0
LP001002
Male
No
0
Graduate
No
5849
0.0
NaN
360.0
1.0
Urban
Y
1
LP001003
Male
Yes
1
Graduate
No
4583
1508.0
128.0
360.0
1.0
Rural
N
2
LP001005
Male
Yes
0
Graduate
Yes
3000
0.0
66.0
360.0
1.0
Urban
Y
3
LP001006
Male
Yes
0
Not Graduate
No
2583
2358.0
120.0
360.0
1.0
Urban
Y
4
LP001008
Male
No
0
Graduate
No
6000
0.0
141.0
360.0
1.0
Urban
Y
5
LP001011
Male
Yes
2
Graduate
Yes
5417
4196.0
267.0
360.0
1.0
Urban
Y
6
LP001013
Male
Yes
0
Not Graduate
No
2333
1516.0
95.0
360.0
1.0
Urban
Y
7
LP001014
Male
Yes
3+
Graduate
No
3036
2504.0
158.0
360.0
0.0
Semiurban
N
8
LP001018
Male
Yes
2
Graduate
No
4006
1526.0
168.0
360.0
1.0
Urban
Y
9
LP001020
Male
Yes
1
Graduate
No
12841
10968.0
349.0
360.0
1.0
Semiurban
N
10
LP001024
Male
Yes
2
Graduate
No
3200
700.0
70.0
360.0
1.0
Urban
Y
11
LP001027
Male
Yes
2
Graduate
NaN
2500
1840.0
109.0
360.0
1.0
Urban
Y
12
LP001028
Male
Yes
2
Graduate
No
3073
8106.0
200.0
360.0
1.0
Urban
Y
13
LP001029
Male
No
0
Graduate
No
1853
2840.0
114.0
360.0
1.0
Rural
N
14
LP001030
Male
Yes
2
Graduate
No
1299
1086.0
17.0
120.0
1.0
Urban
Y
15
LP001032
Male
No
0
Graduate
No
4950
0.0
125.0
360.0
1.0
Urban
Y
16
LP001034
Male
No
1
Not Graduate
No
3596
0.0
100.0
240.0
NaN
Urban
Y
17
LP001036
Female
No
0
Graduate
No
3510
0.0
76.0
360.0
0.0
Urban
N
18
LP001038
Male
Yes
0
Not Graduate
No
4887
0.0
133.0
360.0
1.0
Rural
N
19
LP001041
Male
Yes
0
Graduate
NaN
2600
3500.0
115.0
NaN
1.0
Urban
Y
20
LP001043
Male
Yes
0
Not Graduate
No
7660
0.0
104.0
360.0
0.0
Urban
N
21
LP001046
Male
Yes
1
Graduate
No
5955
5625.0
315.0
360.0
1.0
Urban
Y
22
LP001047
Male
Yes
0
Not Graduate
No
2600
1911.0
116.0
360.0
0.0
Semiurban
N
23
LP001050
NaN
Yes
2
Not Graduate
No
3365
1917.0
112.0
360.0
0.0
Rural
N
24
LP001052
Male
Yes
1
Graduate
NaN
3717
2925.0
151.0
360.0
NaN
Semiurban
N
25
LP001066
Male
Yes
0
Graduate
Yes
9560
0.0
191.0
360.0
1.0
Semiurban
Y
26
LP001068
Male
Yes
0
Graduate
No
2799
2253.0
122.0
360.0
1.0
Semiurban
Y
27
LP001073
Male
Yes
2
Not Graduate
No
4226
1040.0
110.0
360.0
1.0
Urban
Y
28
LP001086
Male
No
0
Not Graduate
No
1442
0.0
35.0
360.0
1.0
Urban
N
29
LP001087
Female
No
2
Graduate
NaN
3750
2083.0
120.0
360.0
1.0
Semiurban
Y
...
...
...
...
...
...
...
...
...
...
...
...
...
...
584
LP002911
Male
Yes
1
Graduate
No
2787
1917.0
146.0
360.0
0.0
Rural
N
585
LP002912
Male
Yes
1
Graduate
No
4283
3000.0
172.0
84.0
1.0
Rural
N
586
LP002916
Male
Yes
0
Graduate
No
2297
1522.0
104.0
360.0
1.0
Urban
Y
587
LP002917
Female
No
0
Not Graduate
No
2165
0.0
70.0
360.0
1.0
Semiurban
Y
588
LP002925
NaN
No
0
Graduate
No
4750
0.0
94.0
360.0
1.0
Semiurban
Y
589
LP002926
Male
Yes
2
Graduate
Yes
2726
0.0
106.0
360.0
0.0
Semiurban
N
590
LP002928
Male
Yes
0
Graduate
No
3000
3416.0
56.0
180.0
1.0
Semiurban
Y
591
LP002931
Male
Yes
2
Graduate
Yes
6000
0.0
205.0
240.0
1.0
Semiurban
N
592
LP002933
NaN
No
3+
Graduate
Yes
9357
0.0
292.0
360.0
1.0
Semiurban
Y
593
LP002936
Male
Yes
0
Graduate
No
3859
3300.0
142.0
180.0
1.0
Rural
Y
594
LP002938
Male
Yes
0
Graduate
Yes
16120
0.0
260.0
360.0
1.0
Urban
Y
595
LP002940
Male
No
0
Not Graduate
No
3833
0.0
110.0
360.0
1.0
Rural
Y
596
LP002941
Male
Yes
2
Not Graduate
Yes
6383
1000.0
187.0
360.0
1.0
Rural
N
597
LP002943
Male
No
NaN
Graduate
No
2987
0.0
88.0
360.0
0.0
Semiurban
N
598
LP002945
Male
Yes
0
Graduate
Yes
9963
0.0
180.0
360.0
1.0
Rural
Y
599
LP002948
Male
Yes
2
Graduate
No
5780
0.0
192.0
360.0
1.0
Urban
Y
600
LP002949
Female
No
3+
Graduate
NaN
416
41667.0
350.0
180.0
NaN
Urban
N
601
LP002950
Male
Yes
0
Not Graduate
NaN
2894
2792.0
155.0
360.0
1.0
Rural
Y
602
LP002953
Male
Yes
3+
Graduate
No
5703
0.0
128.0
360.0
1.0
Urban
Y
603
LP002958
Male
No
0
Graduate
No
3676
4301.0
172.0
360.0
1.0
Rural
Y
604
LP002959
Female
Yes
1
Graduate
No
12000
0.0
496.0
360.0
1.0
Semiurban
Y
605
LP002960
Male
Yes
0
Not Graduate
No
2400
3800.0
NaN
180.0
1.0
Urban
N
606
LP002961
Male
Yes
1
Graduate
No
3400
2500.0
173.0
360.0
1.0
Semiurban
Y
607
LP002964
Male
Yes
2
Not Graduate
No
3987
1411.0
157.0
360.0
1.0
Rural
Y
608
LP002974
Male
Yes
0
Graduate
No
3232
1950.0
108.0
360.0
1.0
Rural
Y
609
LP002978
Female
No
0
Graduate
No
2900
0.0
71.0
360.0
1.0
Rural
Y
610
LP002979
Male
Yes
3+
Graduate
No
4106
0.0
40.0
180.0
1.0
Rural
Y
611
LP002983
Male
Yes
1
Graduate
No
8072
240.0
253.0
360.0
1.0
Urban
Y
612
LP002984
Male
Yes
2
Graduate
No
7583
0.0
187.0
360.0
1.0
Urban
Y
613
LP002990
Female
No
0
Graduate
Yes
4583
0.0
133.0
360.0
0.0
Semiurban
N
614 rows × 13 columns
In [18]:
training_data.isnull().sum()
Out[18]:
Loan_ID 0
Gender 13
Married 3
Dependents 15
Education 0
Self_Employed 32
ApplicantIncome 0
CoapplicantIncome 0
LoanAmount 22
Loan_Amount_Term 14
Credit_History 50
Property_Area 0
Loan_Status 0
dtype: int64
Content source: Zhenxingzhang/AnalyticsVidhya
Similar notebooks: