零基础入门金融风控-贷款违约预测作业1

import numpy as np
import pandas as pd
import os
os.chdir("G:\\datawhale\\finance")

train = pd.read_csv('train.csv')
testA = pd.read_csv('testA.csv')

train.head()

	id	loanAmnt	term	interestRate	installment	grade	subGrade	employmentTitle	employmentLength	homeOwnership	...	n5	n6	n7	n8	n9	n10	n11	n12	n13	n14
0	0	35000.0	5	19.52	917.97	E	E2	320.0	2 years	2	...	9.0	8.0	4.0	12.0	2.0	7.0	0.0	0.0	0.0	2.0
1	1	18000.0	5	18.49	461.90	D	D2	219843.0	5 years	0	...	NaN	NaN	NaN	NaN	NaN	13.0	NaN	NaN	NaN	NaN
2	2	12000.0	5	16.99	298.17	D	D3	31698.0	8 years	0	...	0.0	21.0	4.0	5.0	3.0	11.0	0.0	0.0	0.0	4.0
3	3	11000.0	3	7.26	340.96	A	A4	46854.0	10+ years	1	...	16.0	4.0	7.0	21.0	6.0	9.0	0.0	0.0	0.0	1.0
4	4	3000.0	3	12.99	101.07	C	C2	54.0	NaN	1	...	4.0	9.0	10.0	15.0	7.0	12.0	0.0	0.0	0.0	4.0

5 rows × 47 columns

testA.head()

	id	loanAmnt	term	interestRate	installment	grade	subGrade	employmentTitle	employmentLength	homeOwnership	...	n5	n6	n7	n8	n9	n10	n11	n12	n13	n14
0	800000	14000.0	3	10.99	458.28	B	B3	7027.0	10+ years	0	...	8.0	4.0	15.0	19.0	6.0	17.0	0.0	0.0	1.0	3.0
1	800001	20000.0	5	14.65	472.14	C	C5	60426.0	10+ years	0	...	1.0	3.0	3.0	9.0	3.0	5.0	0.0	0.0	2.0	2.0
2	800002	12000.0	3	19.99	445.91	D	D4	23547.0	2 years	1	...	1.0	36.0	5.0	6.0	4.0	12.0	0.0	0.0	0.0	7.0
3	800003	17500.0	5	14.31	410.02	C	C4	636.0	4 years	0	...	7.0	2.0	8.0	14.0	2.0	10.0	0.0	0.0	0.0	3.0
4	800004	35000.0	3	17.09	1249.42	D	D1	368446.0	< 1 year	1	...	11.0	3.0	16.0	18.0	11.0	19.0	0.0	0.0	0.0	1.0

5 rows × 48 columns

print('Train data shape:',train.shape)
print('TestA data shape:',testA.shape)

Train data shape: (800000, 47)
TestA data shape: (200000, 48)

from sklearn.metrics import confusion_matrix
y_pred = [0, 1, 0, 1]
y_true = [0, 1, 1, 0]
print('混淆矩阵:\n',confusion_matrix(y_true, y_pred))

混淆矩阵:
 [[1 1]
 [1 1]]

from sklearn.metrics import accuracy_score
y_pred = [0, 1, 0, 1]
y_true = [0, 1, 1, 0]
print('ACC:',accuracy_score(y_true, y_pred))

ACC: 0.5

from sklearn import metrics
y_pred = [0, 1, 0, 1]
y_true = [0, 1, 1, 0]
print('Precision',metrics.precision_score(y_true, y_pred))
print('Recall',metrics.recall_score(y_true, y_pred))
print('F1-score:',metrics.f1_score(y_true, y_pred))

Precision 0.5
Recall 0.5
F1-score: 0.5

import matplotlib.pyplot as plt
from sklearn.metrics import precision_recall_curve
y_pred = [0, 1, 1, 0, 1, 1, 0, 1, 1, 1]
y_true = [0, 1, 1, 0, 1, 0, 1, 1, 0, 1]
precision, recall, thresholds = precision_recall_curve(y_true, y_pred)
plt.plot(precision, recall)

[<matplotlib.lines.Line2D at 0x288a1151648>]

## ROC曲线
from sklearn.metrics import roc_curve
y_pred = [0, 1, 1, 0, 1, 1, 0, 1, 1, 1]
y_true = [0, 1, 1, 0, 1, 0, 1, 1, 0, 1]
FPR,TPR,thresholds=roc_curve(y_true, y_pred)
plt.title('ROC')
plt.plot(FPR, TPR,'b')
plt.plot([0,1],[0,1],'r--')
plt.ylabel('TPR')
plt.xlabel('FPR')

Text(0.5, 0, 'FPR')

## AUC
import numpy as np
from sklearn.metrics import roc_auc_score
y_true = np.array([0, 0, 1, 1])
y_scores = np.array([0.1, 0.4, 0.35, 0.8])
print('AUC socre:',roc_auc_score(y_true, y_scores))

AUC socre: 0.75

## KS值 在实际操作时往往使用ROC曲线配合求出KS值
from sklearn.metrics import roc_curve
y_pred = [0, 1, 1, 0, 1, 1, 0, 1, 1, 1]
y_true = [0, 1, 1, 0, 1, 0, 1, 1, 1, 1]
FPR,TPR,thresholds=roc_curve(y_true, y_pred)
KS=abs(FPR-TPR).max()
print('KS值：',KS)

KS值： 0.5238095238095237