svm.py 文件源码

def pipeline(iteration,C,gamma,random_seed):
    x_train, _x , y_train, _y = train_test_split(train_x,train_y,test_size=0.4,random_state=random_seed)
    print x_train.shape
    clf = SVC(C=C,kernel='rbf',gamma=gamma,probability=True,cache_size=7000,class_weight='balanced',verbose=True,random_state=random_seed)
    clf.fit(x_train,y_train)
    #predict test set
    pred = clf.predict_proba(test_x)
    test_result = pd.DataFrame(columns=["Idx","score"])
    test_result.Idx = test_Idx
    test_result.score = pred[:,1]
    test_result.to_csv('./test/svm_{0}.csv'.format(iteration),index=None)
    #predict val set
    pred = clf.predict_proba(val_x)
    val_result = pd.DataFrame(columns=["Idx","score"])
    val_result.Idx = val_Idx
    val_result.score = pred[:,1]
    val_result.to_csv('./val/svm_{0}.csv'.format(iteration),index=None)