机器学习实战之信用卡诈骗（三）

---

SMOTE样本生成策略

import pandas as pd
from imblearn.over_sampling import SMOTE
from sklearn.ensemble import RandomForestClassifier
from sklearn.matrics import confusion_matrix
from sklearn.model_selection import train_test_split

credit_cards = pd.read_csv('creditcard.csv')

columns = credit_cards.columns
features_columns = columns.delete(len(columns)-1)

features=credit_cards[features_columns]
lables=credit_cards['Class']

features_train, features_test, lables_train, lables_test = train_test_split(features,lables,test_size=02,random_state=0)


oversampler=SMOTE(random_state=0)
os_features,os_labels = oversampler.fit_sample(features_train,lables_train)

print(len(os_labels[os_labels==1]))

os_features = pd.DataFrame(os_features)
os_labels = pd.DataFrame(os_labels)
best_c = printing_Kfold_scores(os_features,os_labels)

lr = LogisticRegression(C = best_c, penalty = '11')
lr.fit(os_features,os_labels.values.ravel())
y_pred = lr.predict(features_test.values)

cnf_matrix = confusion_matrix(lables_test,y_pred)
print(np.set_printoption(precision=2))

print('Recall metric in the testing dataset:',cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))


class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix,classes=class_names,title='Confusion matrix')