>>> df_credit = pd.read_csv('c:/creditset.csv', index_col=0)
>>> print(df_credit.shape)
(2000, 5)

# 파티셔닝하기
>>> X = df_credit.loc[:, ['income', 'age', 'loan']]
>>> Y = df_credit['default10yr']
>>> print(X.shape)
(2000, 3)

>>> X_train, X_test, Y_train, Y_test = model_selection.train_test_split(X, Y, test_size=0.3, random_state=42)

>>> model = linear_model.LogisticRegression()
>>> model.fit(X, Y)
>>> model.coef_
array([[-5.76078935e-05, -1.34998242e-01, 8.94164645e-04]])

>>> Y_pred = model.predict(X_test)
>>> Y_pred2 = [0 if x < 0.5 else 1 for x in Y_pred]
>>> Y_pred3 = Y_pred2 == Y_test
>>> np.mean(Y_pred3 == Y_test)
>>> from sklearn.metrics import classification_report, confusion_matrix
>>> confusion_matrix(Y_test, Y_pred3)
array([[ 12, 496],
       [ 43, 49]], dtype=int64)

>>> classification_report(Y_test, Y_pred3)
'             precision       recall  f1-score   support\n\n           0      0.22 
0.02      0.04      508\n              1      0.09       0.53      0.15      92\n\n 
accuracy                             0.10      600\n    macro avg      0.15      0.28 
0.10      600\nweighted avg          0.20     0.10       0.06      600\n'