notebook.community

Edit and run



In [2]:

    
import pandas as pd



In [6]:

    
train_data = pd.read_csv('../Dataset/Train_nyOWmfK.csv', encoding = "ISO-8859-1")
test_data = pd.read_csv('../Dataset/Test_bCtAN1w.csv', encoding = "ISO-8859-1")



In [10]:

    
train_data.head()









    Out[10]:






  
    
      
      ID
      Gender
      City
      Monthly_Income
      DOB
      Lead_Creation_Date
      Loan_Amount_Applied
      Loan_Tenure_Applied
      Existing_EMI
      Employer_Name
      ...
      Interest_Rate
      Processing_Fee
      EMI_Loan_Submitted
      Filled_Form
      Device_Type
      Var2
      Source
      Var4
      LoggedIn
      Disbursed
    
  
  
    
      0
      ID000002C20
      Female
      Delhi
      20000
      23-May-78
      15-May-15
      300000.0
      5.0
      0.0
      CYBOSOL
      ...
      NaN
      NaN
      NaN
      N
      Web-browser
      G
      S122
      1
      0
      0
    
    
      1
      ID000004E40
      Male
      Mumbai
      35000
      07-Oct-85
      04-May-15
      200000.0
      2.0
      0.0
      TATA CONSULTANCY SERVICES LTD (TCS)
      ...
      13.25
      NaN
      6762.9
      N
      Web-browser
      G
      S122
      3
      0
      0
    
    
      2
      ID000007H20
      Male
      Panchkula
      22500
      10-Oct-81
      19-May-15
      600000.0
      4.0
      0.0
      ALCHEMIST HOSPITALS LTD
      ...
      NaN
      NaN
      NaN
      N
      Web-browser
      B
      S143
      1
      0
      0
    
    
      3
      ID000008I30
      Male
      Saharsa
      35000
      30-Nov-87
      09-May-15
      1000000.0
      5.0
      0.0
      BIHAR GOVERNMENT
      ...
      NaN
      NaN
      NaN
      N
      Web-browser
      B
      S143
      3
      0
      0
    
    
      4
      ID000009J40
      Male
      Bengaluru
      100000
      17-Feb-84
      20-May-15
      500000.0
      2.0
      25000.0
      GLOBAL EDGE SOFTWARE
      ...
      NaN
      NaN
      NaN
      N
      Web-browser
      B
      S134
      3
      1
      0
    
  

5 rows × 26 columns



In [12]:

    
train_data.isnull().sum()









    Out[12]:





ID                           0
Gender                       0
City                      1003
Monthly_Income               0
DOB                          0
Lead_Creation_Date           0
Loan_Amount_Applied         71
Loan_Tenure_Applied         71
Existing_EMI                71
Employer_Name               71
Salary_Account           11764
Mobile_Verified              0
Var5                         0
Var1                         0
Loan_Amount_Submitted    34613
Loan_Tenure_Submitted    34613
Interest_Rate            59294
Processing_Fee           59600
EMI_Loan_Submitted       59294
Filled_Form                  0
Device_Type                  0
Var2                         0
Source                       0
Var4                         0
LoggedIn                     0
Disbursed                    0
dtype: int64



In [ ]:

	ID	Gender	City	Monthly_Income	DOB	Lead_Creation_Date	Loan_Amount_Applied	Loan_Tenure_Applied	Existing_EMI	Employer_Name	...	Interest_Rate	Processing_Fee	EMI_Loan_Submitted	Filled_Form	Device_Type	Var2	Source	Var4	LoggedIn
0	ID000002C20	Female	Delhi	20000	23-May-78	15-May-15	300000.0	5.0	0.0	CYBOSOL	...	NaN	NaN	NaN	N	Web-browser	G	S122	1	0
1	ID000004E40	Male	Mumbai	35000	07-Oct-85	04-May-15	200000.0	2.0	0.0	TATA CONSULTANCY SERVICES LTD (TCS)	...	13.25	NaN	6762.9	N	Web-browser	G	S122	3	0
2	ID000007H20	Male	Panchkula	22500	10-Oct-81	19-May-15	600000.0	4.0	0.0	ALCHEMIST HOSPITALS LTD	...	NaN	NaN	NaN	N	Web-browser	B	S143	1	0
3	ID000008I30	Male	Saharsa	35000	30-Nov-87	09-May-15	1000000.0	5.0	0.0	BIHAR GOVERNMENT	...	NaN	NaN	NaN	N	Web-browser	B	S143	3	0
4	ID000009J40	Male	Bengaluru	100000	17-Feb-84	20-May-15	500000.0	2.0	25000.0	GLOBAL EDGE SOFTWARE	...	NaN	NaN	NaN	N	Web-browser	B	S134	3	1