SHAP DeepExplainer 在 TensorFlow 2.4+ 中出现错误

Question

我试图使用DeepExplainer计算shap值，但是出现以下错误：

keras不再被支持，请改用tf.keras

即使我正在使用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, ranked_outputs, output_rank_order, check_additivity=check_additivity)
C:\ProgramData\Anaconda3\lib\site-packages\shap\explainers\_deep\deep_tf.py in shap_values(self, X, ranked_outputs, output_rank_order, 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, Y_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, model.layers[-1].output), background)
shap_values = explainer.shap_values(X_test[1:5])

- Fred

---

你能添加完整的错误信息（完整的回溯）吗？另外，在你的导入中：from keras.utils import to_categorical，你正在使用 keras。 - Lescurel

@Lescurel to_categorical只是一个实用函数，用于转换标签，它极少发挥任何作用；模型显然是使用tf.keras构建的。完整的错误跟踪确实是必需的。 - desertnaut

完整的错误跟踪显示了一个完全不同的错误(KeyError)。 - xdurch0

Answer 1

TL;DR

• 在 TF 2.4+ 中，在开头添加 tf.compat.v1.disable_v2_behavior()
• 在 numpy 数组上计算 shap 值，而不是在数据框上计算

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, Y_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

- Sergey Bushmanov