ValueError: Found input variables with inconsistent numbers of samples: [10000, 5711]

I am trying to train neural network with the 'BFGS' as the update function, there appears to be no problem while training and getting the cost function, however wnen I try to test it andmake prediction it gives me an error: ValueError: Found input variables with inconsistent numbers of samples: [10000, 5711] the code I use is:

    X=data.iloc[:,0:].values
    y=data.iloc[:,-1:].values

    X=pd.DataFrame(data,columns=data.columns)
    y=pd.DataFrame(data,columns=['class'])

    X.drop(['class'],axis=1,inplace=True)
    X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0)

    sc=StandardScaler()
    X_train=sc.fit_transform(X_train)
    X_test=sc.transform(X_test)

    qnewton=algorithms.QuasiNewton(
    network=[
        layers.Input(13),
        layers.Tanh(10),
        layers.Sigmoid(1),
    ],
    update_function='bfgs',verbose=True
    )
    qnewton.train(X_train,y_train)
    y_predict=qnewton.predict(X_test)

I don't really understand whatam I doing wrong. Please help.