使用 joblib.dump 保存和加载经过训练的 GradientBoostingClassifier

我正在尝试使用 joblib.dump 使用以下代码保存经过训练的 GradientBoostingClassifier：

# use 90% of training data
NI=int(len(X_tr)*0.9) 
I1=np.random.choice(len(X_tr),NI)
Xi=X_tr[I1,:]
Yi=Y_tr[I1]

#train a GradientBoostingCalssifier using that data

a=GradientBoostingClassifier(learning_rate=0.02, n_estimators=500, min_samples_leaf=50,presort=True,warm_start=True)

 a.fit(Xi,Yi) 

# calculate class probabilities for the remaining data

I2=np.array(list(set(range(len(X_tr)))-set(I1)))
Pi=np.zeros(len(X_tr))
Pi[I2]=a.predict_proba(X_tr[I2,:])[:,1].reshape(-1)

#save indexes of training data and the predicted probabilites
np.savetxt('models\\balanced\\GBT1\\oob_index'+str(j)+'.txt',I2)
np.savetxt('models\\balanced\\GBT1\\oob_m'+str(j)+'.txt',Pi)

# save the trained classifier
joblib.dump(a, 'models\\balanced\\GBT1\\m'+str(j)+'.pkl') 

训练并保存分类器后，我关闭终端，打开一个新终端并运行以下代码来加载分类器并在保存的测试数据集上对其进行测试

    # load the saved class probabilities 
    Pi=np.loadtxt('models\\balanced\\GBT1\\oob_m'+str(j)+'.txt') 

    #load the training data index 
    Ii=np.loadtxt('models\\balanced\\GBT1\\oob_index'+str(j)+'.txt')

    #load the trained model
    a=joblib.load('models\\balanced\\GBT1\\m'+str(j)+'.pkl')

    #predict class probabilities using the trained model
    Pi1=a.predict_proba(X_tr[Ii,:])[:,1] 

    # Calculate aupr for the retrained model 
    _prec,_rec,_=metrics.precision_recall_curve(Y[Ii],Pi1,pos_label=1)
    auc=metrics.auc(_rec,_prec);

    # calculate aupr for the saved probabilities
    _prec1,_rec1,_=metrics.precision_recall_curve(Y[Ii],Pi[Ii],pos_label=1)
    auc1=metrics.auc(_rec1,_prec1);

     print('in iteration ', j, ' aucs: ', auc, auc1)

该代码打印以下内容： 在迭代 0 aucs 中：0.0331879 0.0657821 ...................................... 在所有情况下，重新加载的分类器的 aupr 与原始训练的分类器显着不同。我使用相同版本的 sklearn 和 python 来加载和保存。我究竟做错了什么？

错误出在您的代码中。我建议你使用分割数据train_test_split。它通过以下方式对数据进行混洗default http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html

下面的代码产生相同的结果auc指标：

from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import precision_recall_curve
from sklearn.metrics import auc
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
import pickle
from sklearn.externals import joblib

def main():
    X, y = load_iris(return_X_y=True)
    X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=.3)

    clf = GradientBoostingClassifier()
    clf.fit(X_train, y_train)

    preds = clf.predict(X_test)
    prec, rec, _ = precision_recall_curve(y_test, preds, pos_label=1)

    with open('dump.pkl', 'wb') as f:
        pickle.dump(clf, f)

    print('AUC SCORE: ', auc(rec, prec))

    clf2 = joblib.load('dump.pkl')
    preds2 = clf2.predict(X_test)

    prec2, rec2, _ = precision_recall_curve(y_test, preds2, pos_label=1)

    print('AUC SCORE AFTER DUMP: ', auc(rec2, prec2))

if __name__ == '__main__':
    main()

>>> AUC SCORE: 0.273271889401
>>> AUC SCORE AFTER DUMP: 0.273271889401