scikit-learn MLPRegressor中如何判断哪一个是训练和测试？

Question

我有两个数据集（训练和测试），它们都有完全相同的特征和标签列，只是内部不同（数字和值）。这是我的代码：

import pandas as pd
import numpy as np 

from sklearn.model_selection import train_test_split
from sklearn.neural_network import MLPRegressor

datatraining = pd.read_csv("datatrain.csv")

datatesting = pd.read_csv("datatest.csv")

columns = ["Full","Id","Id & PPDB","Id & Words Sequence","Id & Synonyms","Id & Hypernyms","Id & Hyponyms"]

labeltrain = datatraining["Gold Standard"].values
featurestrain = datatraining[list(columns)].values


labeltest = datatesting["Gold Standard"].values
featurestest = datatesting[list(columns)].values

X_train = featurestrain
y_train = labeltrain

X_test = featurestest
y_test = labeltest

mlp = MLPRegressor(solver='lbfgs', hidden_layer_sizes=50, max_iter=1000, learning_rate='constant')

mlp.fit(X_train, y_train)

print('Accuracy training : {:.3f}'.format(mlp.score(X_train, y_train)))
print

mlp.fit(X_test, y_test)

print('Accuracy testing : {:.3f}'.format(mlp.score(X_test, y_test)))
print

我仍然怀疑我的代码能否正确找到训练和测试分数，因为我看不到任何区分器来确定哪个正在训练，哪个正在测试。我看到两者都在训练，或者两者都在测试。 任何人都可以解释如何确定它？或者我的代码已经正确了吗？谢谢

Answer 1

一旦你在训练中拟合了你的模型，你就不应该再在测试中拟合它。相反，您应该使用测试集评估模型的性能。因此，您需要删除行

mlp.fit(X_test, y_test)

来自您的代码。然后使用行

print('Accuracy testing : {:.3f}'.format(mlp.score(X_test, y_test)))

您将能够评估模型在未见数据上的性能。