Pandas DataFrame



In [2]:

    
lc_data = pd.DataFrame.from_csv('./lc_dataframe(cleaning).csv')
lc_data = lc_data.reset_index()
lc_data.tail()









    Out[2]:






  
    
      
      loan_amnt
      term
      int_rate
      installment
      grade
      sub_grade
      emp_title
      emp_length
      home_ownership
      annual_inc
      ...
      dti
      delinq_2yrs
      inq_last_6mths
      open_acc
      pub_rec
      revol_bal
      revol_util
      total_acc
      initial_list_status
      acc_now_delinq
    
  
  
    
      268131
      31050
      60
      21.99
      857.40
      6
      61
      1
      10
      1
      875000.0
      ...
      9.66
      1
      0
      10
      0
      25770
      79.3
      13
      0
      0
    
    
      268132
      10800
      36
      7.89
      337.89
      1
      15
      1
      8
      1
      92400.0
      ...
      19.62
      1
      0
      11
      0
      9760
      68.7
      36
      1
      0
    
    
      268133
      9000
      36
      9.17
      286.92
      2
      22
      1
      1
      1
      80000.0
      ...
      3.97
      1
      0
      8
      0
      6320
      51.8
      17
      0
      0
    
    
      268134
      14400
      60
      25.99
      431.06
      6
      65
      0
      11
      5
      62000.0
      ...
      16.88
      0
      1
      9
      1
      5677
      45.1
      30
      0
      0
    
    
      268135
      8000
      36
      12.59
      267.98
      3
      32
      1
      4
      4
      45000.0
      ...
      26.21
      0
      0
      12
      0
      9097
      50.8
      47
      1
      0
    
  

5 rows × 25 columns

V4 grade (범주형 데이터형)

LC assigned loan grade A,B,C,D,E,F,G = {1, 2, 3, 4, 5, 6, 7}



In [28]:

    
x = lc_data['grade']
sns.distplot(x, color = 'r')
plt.show()

V5 sub_grade (범주형 데이터형)

LC assigned loan subgrade 1, 2, 3, 4, 5



In [30]:

    
x = lc_data['sub_grade']
sns.distplot(x, color = 'g')
plt.show()

V6 emp_title (범주형 데이터형)

The job title supplied by the Borrower when applying for the loan.* True = 1, False = 0



In [32]:

    
x = lc_data['emp_title']
plt.hist(x)
plt.show()

V7 emp_length (범주형 데이터형)

Employment length in years. Possible values are between 0 and 10 where 0 means less than one year and 10 means ten or more years. < 1' = 0, 10+ = 10, 'n/a' = 11



In [33]:

    
x = lc_data['emp_length']

sns.distplot(x, color = 'r')
plt.show()

V8 home_ownership (범주형 데이터형)

The home ownership status provided by the borrower during registration or obtained from the credit report. Our values are: RENT, OWN, MORTGAGE, OTHER

Mortgage, None, Other, Own, Rent = {1, 2, 3, 4, 5}



In [34]:

    
x = lc_data['home_ownership']

sns.distplot(x, color = 'g')
plt.show()

V10 verification_status (범주형 데이터형)

Indicates if income was verified by LC, not verified, or if the income source was verified

Source Verified, Verified = 1, Not Verified = 0



In [35]:

    
x = lc_data['verification_status']

sns.distplot(x)
plt.show()

V11 issue_d (범주형 데이터형)

The month which the loan was funded

mm 으로 변환



In [36]:

    
x = lc_data['issue_d']
sns.distplot(x, color = 'r')
plt.show()

V14 purpose (범주형 데이터형)

A category provided by the borrower for the loan request.

15개 범주 = {1:15} (1부터 15까지)



In [37]:

    
x = lc_data['purpose']

sns.distplot(x, color = 'g')
plt.show()

V23 initial_list_status (범주형 데이터형)

The initial listing status of the loan. Possible values are – W, F

W = 1, F = 0



In [39]:

    
x = lc_data['initial_list_status']
plt.hist(x)
plt.show()

	loan_amnt	term	int_rate	installment	grade	sub_grade	emp_title	emp_length	home_ownership	annual_inc	...	dti	delinq_2yrs	inq_last_6mths	open_acc	pub_rec	revol_bal	revol_util	total_acc	initial_list_status
268131	31050	60	21.99	857.40	6	61	1	10	1	875000.0	...	9.66	1	0	10	0	25770	79.3	13	0
268132	10800	36	7.89	337.89	1	15	1	8	1	92400.0	...	19.62	1	0	11	0	9760	68.7	36	1
268133	9000	36	9.17	286.92	2	22	1	1	1	80000.0	...	3.97	1	0	8	0	6320	51.8	17	0
268134	14400	60	25.99	431.06	6	65	0	11	5	62000.0	...	16.88	0	1	9	1	5677	45.1	30	0
268135	8000	36	12.59	267.98	3	32	1	4	4	45000.0	...	26.21	0	0	12	0	9097	50.8	47	1