带有 TensorFlow 2.4+ 错误的 SHAP DeepExplainer

如何解决带有 TensorFlow 2.4+ 错误的 SHAP DeepExplainer

我正在尝试使用 DeepExplainer 计算 shap 值，但出现以下错误：

不再支持keras，请改用tf.keras

即使我使用的是 tf.keras？

KeyError       Traceback (most recent call last)
 in 
6 # ...or pass tensors directly
7 explainer = shap.DeepExplainer((model.layers[0].input,model.layers[-1].output),background)
8 shap_values = explainer.shap_values(X_test[1:5])

C:\ProgramData\Anaconda3\lib\site-packages\shap\explainers\_deep\__init__.py in shap_values(self,X,ranked_outputs,output_rank_order,check_additivity)
122   were chosen as "top".
124   return self.explainer.shap_values(X,check_additivity=check_additivity)
C:\ProgramData\Anaconda3\lib\site-packages\shap\explainers\_deep\deep_tf.py in shap_values(self,check_additivity)
310                 # assign the attributions to the right part of the output arrays
311                 for l in range(len(X)):
312                     phis[l][j] = (sample_phis[l][bg_data[l].shape[0]:] * (X[l][j] - bg_data[l])).mean(0)
313 
314             output_phis.append(phis[0] if not self.multi_input else phis)

C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in __getitem__(self,key)

    2798 if self.columns.nlevels > 1:
    2799    return self._getitem_multilevel(key)
    2800    indexer = self.columns.get_loc(key)
    2801 if is_integer(indexer):
    2802    indexer = [indexer]
C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_loc(self,key,method,tolerance)
2646                 return self._engine.get_loc(key)
2647             except KeyError:
2648                 return self._engine.get_loc(self._maybe_cast_indexer(key))
2649         indexer = self.get_indexer([key],method=method,tolerance=tolerance)
2650         if indexer.ndim > 1 or indexer.size > 1:

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 0

import shap
import numpy as np
import pandas as pd
import tensorflow as tf
import tensorflow.keras.backend as K

from keras.utils import to_categorical 
from sklearn.model_selection import train_test_split
from tensorflow.python.keras.layers import Dense
from tensorflow.python.keras import Sequential
from tensorflow.keras import optimizers

# print the JS visualization code to the notebook
shap.initjs()

X_train,X_test,Y_train,Y_test = train_test_split(*shap.datasets.iris(),test_size=0.2,random_state=0)

Y_train = to_categorical(Y_train,num_classes=3) 
Y_test = to_categorical(Y_test,num_classes=3) 

# Define baseline model
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(8,input_dim=len(X_train.columns),activation="relu"))
model.add(tf.keras.layers.Dense(3,activation="softmax"))
model.summary()


# compile the model
model.compile(optimizer='adam',loss="categorical_crossentropy",metrics=['accuracy'])

hist = model.fit(X_train,batch_size=5,epochs=200,verbose=0)

# select a set of background examples to take an expectation over
background = X_train.iloc[np.random.choice(X_train.shape[0],100,replace=False)]

# Explain predictions of the model
#explainer = shap.DeepExplainer(model,background)
# ...or pass tensors directly
explainer = shap.DeepExplainer((model.layers[0].input,background)
shap_values = explainer.shap_values(X_test[1:5])

解决方法

TL;DR

• 在 TF 2.4+ 的顶部添加 tf.compat.v1.disable_v2_behavior()
• 在 numpy 数组上计算 shap 值，而不是在 df 上

完全可重现的示例：

import shap
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split

import tensorflow as tf    
tf.compat.v1.disable_v2_behavior() # <-- HERE !

import tensorflow.keras.backend as K
from tensorflow.keras.utils import to_categorical
from tensorflow.python.keras.layers import Dense
from tensorflow.python.keras import Sequential
from tensorflow.keras import optimizers

print("SHAP version is:",shap.__version__)
print("Tensorflow version is:",tf.__version__)

X_train,X_test,Y_train,Y_test = train_test_split(
    *shap.datasets.iris(),test_size=0.2,random_state=0
)

Y_train = to_categorical(Y_train,num_classes=3)
Y_test = to_categorical(Y_test,num_classes=3)

# Define baseline model
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Dense(8,input_dim=len(X_train.columns),activation="relu"))
model.add(tf.keras.layers.Dense(3,activation="softmax"))
# model.summary()

# compile the model
model.compile(optimizer="adam",loss="categorical_crossentropy",metrics=["accuracy"])

hist = model.fit(X_train,batch_size=5,epochs=200,verbose=0)

# select a set of background examples to take an expectation over
background = X_train.iloc[np.random.choice(X_train.shape[0],100,replace=False)]

explainer = shap.DeepExplainer(
    (model.layers[0].input,model.layers[-1].output),background
)
shap_values = explainer.shap_values(X_test[:3].values) # <-- HERE !

# print the JS visualization code to the notebook
shap.initjs()
shap.force_plot(
    explainer.expected_value[0],shap_values[0][0],feature_names=X_train.columns
)

---

SHAP version is: 0.39.0
Tensorflow version is: 2.5.0