Deep learningをSHAPで説明したい

前提・実現したいこと

アヤメの分類をDeep learinigで行い、SHAPを使って
特徴変数の影響度の説明をしようと思っています。

Explainerを実装中に以下のエラーメッセージが発生しました。

プログラミングをはじめて半年ほどで、
初の質問ですので記入不足等あったらすみません。

発生している問題・エラーメッセージ

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in assert_input_compatibility(self, inputs)
    309             try:
--> 310                 K.is_keras_tensor(x)
    311             except ValueError:

6 frames
ValueError: Unexpectedly found an instance of type `<class 'numpy.ndarray'>`. Expected a symbolic tensor instance.

During handling of the above exception, another exception occurred:

ValueError                                Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py in assert_input_compatibility(self, inputs)
    314                                  'Received type: ' +
    315                                  str(type(x)) + '. Full input: ' +
--> 316                                  str(inputs) + '. All inputs to the layer '
    317                                  'should be tensors.')
    318 

ValueError: Layer sequential_6 was called with an input that isn't a symbolic tensor. Received type: <class 'numpy.ndarray'>. Full input: [array([[-0.90068117,  0.55861082,…

該当のソースコード

python,keras
1#データセット読み込み
2from sklearn import datasets
3iris = datasets.load_iris()
4
5from sklearn.model_selection import train_test_split as split
6x_train, x_test, y_train, y_test = split(iris.data,iris.target,train_size=0.8,test_size=0.2)
7
8import numpy as np
9import pandas as pd
10
11
12iris_data=pd.DataFrame(iris.data)
13iris_label=pd.DataFrame(iris.target)
14
15from sklearn import preprocessing
16
17#mini-maxスケール変換
18minimax_scale=preprocessing.MinMaxScaler(feature_range=(0,1))
19iris_data=minimax_scale.fit_transform(iris_data)
20
21#データの標準化
22scaler=preprocessing.StandardScaler()
23iris_data=scaler.fit_transform(iris_data)
24iris_data=pd.DataFrame(iris_data)
25
26import keras
27
28onehot_label=keras.utils.np_utils.to_categorical(iris_label.astype('int32'),3)
29
30X=iris_data
31Y=onehot_label
32
33X=np.asarray(X)
34Y=np.asarray(Y)
35
36print(X.shape)
37print(Y.shape)
38
39from sklearn.model_selection import train_test_split
40
41x_train,x_test,y_train,y_test=train_test_split(X,Y,test_size=0.2,train_size=0.8,shuffle=True)
42
43from keras.models import Sequential
44from keras.layers.core import Dense, Activation
45
46model=Sequential()
47
48model.add(Dense(16, input_shape=(4,)))
49model.add(Activation('relu'))
50
51model.add(Dense(3))
52model.add(Activation('softmax'))
53
54model.compile(optimizer='adam', loss='categorical_crossentropy',
55             metrics=['accuracy'])
56 
57hist=model.fit(x_train,y_train,
58               epochs=50, 
59               batch_size=1, 
60               verbose=1,
61               validation_data=(x_test,y_test))
62
63#SHAPを用いた説明
64import shap
65
66explainer = shap.DeepExplainer(model,x_test)