Arrays 未知标签类型：sklearn中的数组

我在sklearn MLPC分类装置配合方面遇到问题，我收到以下错误：

Unknown label type: (array([ 2.36,  9.88,  6.93,  1.27,  6.64,  4.7 ,  4.72,  4.66, 10.45,
    9.78,  3.97, 10.25,  0.45,  0.07,  7.79,  3.43,  0.71,  2.82,
    7.67,  0.43,  4.48,  8.62,  0.56,  3.57,  6.85,  2.75,  3.37,
    3.24,  2.41,  0.31,  5.51,  6.13,  9.48,  2.02,  0.13,  8.8 ,
    0.37,  5.44,  5.05,  7.96,  4.56,  6.87,  2.93,  8.86, 10.2 ,
    1.61,  4.26,  4.5 ,  6.11, 10.05,  2.1 ,  5.82,  2.69,  7.13,
    1.47,  1.79,  1.86,  7.2 ,  0.5 ,  0.58,  0.16,  5.78,  6.02,
    0.97,  7.05,  6.3 ,  0.97,  5.04,  9.51,  2.88,  3.89,  8.82,
    0.09,  8.37,  1.46,  9.22,  0.09,  4.8 ,  0.  ,  6.16]),)

这是我的数据集：

        x               y           z
0   -35.997271  -16.594561  4.142350
1   -1.587584   -6.526561   0.212667
2   -15.775675  -30.170914  0.370804
3   -22.165420  -0.892974   0.161097
4   -13.913515  -16.396032  9.223847

我已经拆分了X和y系列和测试数据：

x = np.array(df.drop(['z'],1))
y = np.array(df['z'])
x = preprocessing.scale(x)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(x,y, test_size=0.2)

最后运行mlpclassizer和fit函数：

mlp = MLPClassifier(hidden_layer_sizes=(13,13,13), max_iter=500)
mlp.fit(X_train, y_train)

但我收到了这个错误：

Unknown label type: (array([ 2.36,  9.88,  6.93,  1.27,  6.64,  4.7 ,  4.72,  4.66, 10.45,
    9.78,  3.97, 10.25,  0.45,  0.07,  7.79,  3.43,  0.71,  2.82,
    7.67,  0.43,  4.48,  8.62,  0.56,  3.57,  6.85,  2.75,  3.37,
    3.24,  2.41,  0.31,  5.51,  6.13,  9.48,  2.02,  0.13,  8.8 ,
    0.37,  5.44,  5.05,  7.96,  4.56,  6.87,  2.93,  8.86, 10.2 ,
    1.61,  4.26,  4.5 ,  6.11, 10.05,  2.1 ,  5.82,  2.69,  7.13,
    1.47,  1.79,  1.86,  7.2 ,  0.5 ,  0.58,  0.16,  5.78,  6.02,
    0.97,  7.05,  6.3 ,  0.97,  5.04,  9.51,  2.88,  3.89,  8.82,
    0.09,  8.37,  1.46,  9.22,  0.09,  4.8 ,  0.  ,  6.16]),)

---

解决这个问题有什么办法吗？

当输出似乎是连续变量时，运行MLPClassizer。因此，要么使用MLPrePressor，要么用类标签替换输出。

您试图用分类器预测连续的实值。使用回归器代替。