我在练习神经网络时遇到了一个问题。我的神经网络无法预测正确的结果，尽管训练得分显示为97%。
这是我的代码：
# Import `datasets` from `sklearn`from sklearn import datasetsimport pandas as pdfrom sklearn.model_selection import train_test_split# Import `train_test_split`from sklearn.model_selection import train_test_splitfrom sklearn.preprocessing import StandardScalerfrom sklearn.neural_network import MLPClassifier# Load in the `digits` datafrom sklearn.preprocessing import scaleiris = datasets.load_iris()# split the data up - 3/4 for training, 1/4 for testingdata_train, data_test, name_train, name_test = train_test_split(iris.data, iris.target, test_size=0.25, random_state=0)# Number of training features# n_samples, n_features = data_train.shapescaler = StandardScaler()scaler.fit(data_train)params_train_scaled = scaler.transform(data_train)params_test_scaled = scaler.transform(data_test)# 1 hidden layer, same size as the input layermlp = MLPClassifier( solver='lbfgs', hidden_layer_sizes=(iris.data.shape[1], ), random_state=0)mlp.fit(params_train_scaled, name_train)print(name_train)print('Train score: %.3g' % mlp.score(params_train_scaled, name_train))print('Test Score: %.3g' % mlp.score(params_test_scaled, name_test))printtest_val = [[5.1, 3.5, 1.4, 0.2]]print(mlp.predict(test_val))我认为可能是训练数据和测试数据的缩放方式有问题，但我不确定…
我得到的输出是：
Train score: 1
Test Score: 0.974
然而，预测值应该是0，而不是1。
感谢任何帮助。
回答：
由于你缩放了训练数据，你也应该缩放测试数据：
print(mlp.predict(scaler.transform(test_val)))