In [1]:

    

# initialize
import numpy as np
import scipy as sp
import pandas as pd
import statsmodels.api as sm
import matplotlib as mpl
import matplotlib.tri as mtri
import matplotlib.pylab as plt
import seaborn as sns
from scipy import stats
from sklearn.datasets import make_regression

# Seaborn setting
sns.set(palette="muted", font_scale=2)

# data loading
data = pd.read_csv('d:/works/project/lc_project/lc_dataframe.csv')
data.tail()


    

    




D:\Anaconda2\lib\site-packages\IPython\core\interactiveshell.py:2717: DtypeWarning: Columns (6) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)






    
Out[1]:






  

    

      

      
loan_amnt
      
term
      
int_rate
      
installment
      
grade
      
sub_grade
      
emp_title
      
emp_length
      
home_ownership
      
annual_inc
      
...
      
delinq_2yrs
      
inq_last_6mths
      
open_acc
      
pub_rec
      
revol_bal
      
revol_util
      
total_acc
      
initial_list_status
      
application_type
      
acc_now_delinq
    
  
  

    

      
268132
      
31050
      
60
      
21.99
      
857.40
      
6
      
61
      
1
      
10
      
2
      
875000.0
      
...
      
1
      
0
      
10
      
0
      
25770
      
79.3
      
13
      
0
      
1
      
0
    
    

      
268133
      
10800
      
36
      
7.89
      
337.89
      
1
      
15
      
1
      
8
      
2
      
92400.0
      
...
      
1
      
0
      
11
      
0
      
9760
      
68.7
      
36
      
1
      
1
      
0
    
    

      
268134
      
9000
      
36
      
9.17
      
286.92
      
2
      
22
      
1
      
1
      
2
      
80000.0
      
...
      
1
      
0
      
8
      
0
      
6320
      
51.8
      
17
      
0
      
1
      
0
    
    

      
268135
      
14400
      
60
      
25.99
      
431.06
      
6
      
65
      
0
      
11
      
6
      
62000.0
      
...
      
0
      
1
      
9
      
1
      
5677
      
45.1
      
30
      
0
      
1
      
0
    
    

      
268136
      
8000
      
36
      
12.59
      
267.98
      
3
      
32
      
1
      
4
      
5
      
45000.0
      
...
      
0
      
0
      
12
      
0
      
9097
      
50.8
      
47
      
1
      
1
      
0
    
  

5 rows × 27 columns

In [ ]:

    

# preprocessing:


    

In [3]:

    

# status/grade group dataframe(series)
data_grade = data.groupby("grade").loan_status.value_counts()

# status / grade ratio plot
n = 7
grade_mat = np.zeros(n)
for i in range(n):
    grade_mat[i] = data_grade[i+1, 1] / float(np.sum(data_grade[i+1]))

# Grade/Paid Ratio Plot
plt.figure(figsize=(15, 10))
x = np.arange(len(grade_mat))
plt.bar(x, grade_mat, align='center')
plt.xticks(x, ('A', 'B', 'C', 'D', 'E', 'F', 'G'))
plt.title("Fully Paid Ratio by LC Credit Rank")
plt.xlabel("LC Credit Rank")
plt.ylabel("Grade/Paid Ratio")
plt.show()