将 shap 与 SimpleRNN 顺序模型一起使用时出错
Error using shap with SimpleRNN sequential model
在下面的代码中，我导入了一个已保存的稀疏 numpy 矩阵，该矩阵是使用 python 创建的，对其进行致密化，向多对一 SimpleRNN 添加掩蔽层、batchnorm 和密集输出层。 keras 顺序模型工作正常，但是，我无法使用 shap。这是 运行 在 Windows 10 桌面上来自 Winpython 3830 的 Jupyter 实验室。 X 矩阵的形状为 (4754, 500, 64)：4754 个示例，具有 500 个时间步长和 64 个变量。我创建了一个函数来模拟数据，以便可以测试代码。模拟数据returns同样错误。
from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow.keras.models import Sequential
import tensorflow.keras.backend as Kb
from tensorflow.keras import layers
from tensorflow.keras.layers import BatchNormalization
from tensorflow import keras as K
import numpy as np
import shap
import random
def create_x():
dims = [10,500,64]
data = []
y = []
for i in range(dims[0]):
data.append([])
for j in range(dims[1]):
data[i].append([])
for k in range(dims[2]):
isnp = random.random()
if isnp > .2:
data[i][j].append(np.nan)
else:
data[i][j].append(random.random())
if isnp > .5:
y.append(0)
else:
y.append(1)
return np.asarray(data), np.asarray(y)
def first_valid(arr, axis, invalid_val=0):
#return the 2nd index of 3 for the first non np.nan on the 3rd axis
mask = np.invert(np.isnan(arr))
return np.where(mask.any(axis=axis), mask.argmax(axis=axis), invalid_val)
def densify_np(X):
X_copy = np.empty_like (X)
X_copy[:] = X
#loop over the first index
for i in range(len(X_copy)):
old_row = []
#get the 2nd index of the first valid value for each 3rd index
indices = first_valid(X_copy[i,:,:],axis=0, invalid_val=0)
for j in range(len(indices)):
if np.isnan(X_copy[i,indices[j],j]):
old_row.append(0)
else:
old_row.append(X_copy[i,indices[j],j])
X_copy[i,0,:]= old_row
for k in range(1,len(X_copy[i,:])):
for l in range(len(X_copy[i,k,:])):
if np.isnan(X_copy[i,k,l]):
X_copy[i,k,l] = X_copy[i,k-1,l]
return(X_copy)
#this is what I do in the actual code
#X = np.load('C:/WinPython/WPy64-3830/data/X.npy')
#Y = np.load('C:/WinPython/WPy64-3830/scripts/Y.npy')
#simulated junk data
X, Y = create_x()
#create a dense matrix from the sparse one.
X = densify_np(X)
seed = 7
np.random.seed(seed)
array_size = 64
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=seed)
batch = 64
model = Sequential()
model.add(layers.Input(shape=(500,array_size)))
model.add(layers.Masking(mask_value=0.,input_shape=(500, array_size)))
model.add(BatchNormalization())
model.add(layers.SimpleRNN(1, activation=None, dropout = 0, recurrent_dropout=.2))
model.add(layers.Dense(1, activation = 'sigmoid'))
opt = K.optimizers.Adam(learning_rate=.001)
model.compile(loss='binary_crossentropy', optimizer=opt)
model.fit(X_train, y_train.astype(int), validation_data=(X_test,y_test.astype(int)), epochs=25, batch_size=batch)
explainer = shap.DeepExplainer(model, X_test)
shap_values = explainer.shap_values(X_train)
运行 创建 shap_values 的最后一行产生以下错误。
StagingError Traceback (most recent call last)
<ipython-input-6-f789203da9c8> in <module>
1 import shap
2 explainer = shap.DeepExplainer(model, X_test)
----> 3 shap_values = explainer.shap_values(X_train)
4 print('done')
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\__init__.py in shap_values(self, X, ranked_outputs, output_rank_order, check_additivity)
117 were chosen as "top".
118 """
--> 119 return self.explainer.shap_values(X, ranked_outputs, output_rank_order, check_additivity=check_additivity)
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in shap_values(self, X, ranked_outputs, output_rank_order, check_additivity)
302 # run attribution computation graph
303 feature_ind = model_output_ranks[j,i]
--> 304 sample_phis = self.run(self.phi_symbolic(feature_ind), self.model_inputs, joint_input)
305
306 # assign the attributions to the right part of the output arrays
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in run(self, out, model_inputs, X)
359
360 return final_out
--> 361 return self.execute_with_overridden_gradients(anon)
362
363 def custom_grad(self, op, *grads):
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in execute_with_overridden_gradients(self, f)
395 # define the computation graph for the attribution values using a custom gradient-like computation
396 try:
--> 397 out = f()
398 finally:
399 # reinstate the backpropagatable check
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in anon()
355 v = tf.constant(data, dtype=self.model_inputs[i].dtype)
356 inputs.append(v)
--> 357 final_out = out(inputs)
358 tf_execute.record_gradient = tf_backprop._record_gradient
359
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
821 # This is the first call of __call__, so we have to initialize.
822 initializers = []
--> 823 self._initialize(args, kwds, add_initializers_to=initializers)
824 finally:
825 # At this point we know that the initialization is complete (or less
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
694 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
695 self._concrete_stateful_fn = (
--> 696 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
697 *args, **kwds))
698
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2853 args, kwargs = None, None
2854 with self._lock:
-> 2855 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2856 return graph_function
2857
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
-> 3213 graph_function = self._create_graph_function(args, kwargs)
3214 self._function_cache.primary[cache_key] = graph_function
3215 return graph_function, args, kwargs
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3063 arg_names = base_arg_names + missing_arg_names
3064 graph_function = ConcreteFunction(
-> 3065 func_graph_module.func_graph_from_py_func(
3066 self._name,
3067 self._python_function,
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
984 _, original_func = tf_decorator.unwrap(python_func)
985
--> 986 func_outputs = python_func(*func_args, **func_kwargs)
987
988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
599 # the function a weak reference to itself to avoid a reference cycle.
--> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
601 weak_wrapped_fn = weakref.ref(wrapped_fn)
602
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise
StagingError: in user code:
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py:244 grad_graph *
x_grad = tape.gradient(out, shap_rAnD)
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\backprop.py:1067 gradient **
flat_grad = imperative_grad.imperative_grad(
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\imperative_grad.py:71 imperative_grad
return pywrap_tfe.TFE_Py_TapeGradient(
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\backprop.py:151 _gradient_function
grad_fn = ops._gradient_registry.lookup(op_name) # pylint: disable=protected-access
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\registry.py:96 lookup
raise LookupError(
LookupError: gradient registry has no entry for: shap_TensorListStack
shap 存储库的所有者 said:
The fundamental issue here is that DeepExplainer does not yet support TF 2.0.
那是 2019 年 12 月 11 日。现在仍然如此吗？用 Tensorflow 1.15 试试看是否有效。
shap repo 上关于此的另一个 issue（2020 年 6 月 2 日）说：
Alright, thank you. I did not see the post by Lundberg. I will stick to the workaround of using TF 1.15 until a new version of SHAP is released.
在下面的代码中，我导入了一个已保存的稀疏 numpy 矩阵，该矩阵是使用 python 创建的，对其进行致密化，向多对一 SimpleRNN 添加掩蔽层、batchnorm 和密集输出层。 keras 顺序模型工作正常，但是，我无法使用 shap。这是 运行 在 Windows 10 桌面上来自 Winpython 3830 的 Jupyter 实验室。 X 矩阵的形状为 (4754, 500, 64)：4754 个示例，具有 500 个时间步长和 64 个变量。我创建了一个函数来模拟数据，以便可以测试代码。模拟数据returns同样错误。
from sklearn.model_selection import train_test_split
import tensorflow as tf
from tensorflow.keras.models import Sequential
import tensorflow.keras.backend as Kb
from tensorflow.keras import layers
from tensorflow.keras.layers import BatchNormalization
from tensorflow import keras as K
import numpy as np
import shap
import random
def create_x():
dims = [10,500,64]
data = []
y = []
for i in range(dims[0]):
data.append([])
for j in range(dims[1]):
data[i].append([])
for k in range(dims[2]):
isnp = random.random()
if isnp > .2:
data[i][j].append(np.nan)
else:
data[i][j].append(random.random())
if isnp > .5:
y.append(0)
else:
y.append(1)
return np.asarray(data), np.asarray(y)
def first_valid(arr, axis, invalid_val=0):
#return the 2nd index of 3 for the first non np.nan on the 3rd axis
mask = np.invert(np.isnan(arr))
return np.where(mask.any(axis=axis), mask.argmax(axis=axis), invalid_val)
def densify_np(X):
X_copy = np.empty_like (X)
X_copy[:] = X
#loop over the first index
for i in range(len(X_copy)):
old_row = []
#get the 2nd index of the first valid value for each 3rd index
indices = first_valid(X_copy[i,:,:],axis=0, invalid_val=0)
for j in range(len(indices)):
if np.isnan(X_copy[i,indices[j],j]):
old_row.append(0)
else:
old_row.append(X_copy[i,indices[j],j])
X_copy[i,0,:]= old_row
for k in range(1,len(X_copy[i,:])):
for l in range(len(X_copy[i,k,:])):
if np.isnan(X_copy[i,k,l]):
X_copy[i,k,l] = X_copy[i,k-1,l]
return(X_copy)
#this is what I do in the actual code
#X = np.load('C:/WinPython/WPy64-3830/data/X.npy')
#Y = np.load('C:/WinPython/WPy64-3830/scripts/Y.npy')
#simulated junk data
X, Y = create_x()
#create a dense matrix from the sparse one.
X = densify_np(X)
seed = 7
np.random.seed(seed)
array_size = 64
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.33, random_state=seed)
batch = 64
model = Sequential()
model.add(layers.Input(shape=(500,array_size)))
model.add(layers.Masking(mask_value=0.,input_shape=(500, array_size)))
model.add(BatchNormalization())
model.add(layers.SimpleRNN(1, activation=None, dropout = 0, recurrent_dropout=.2))
model.add(layers.Dense(1, activation = 'sigmoid'))
opt = K.optimizers.Adam(learning_rate=.001)
model.compile(loss='binary_crossentropy', optimizer=opt)
model.fit(X_train, y_train.astype(int), validation_data=(X_test,y_test.astype(int)), epochs=25, batch_size=batch)
explainer = shap.DeepExplainer(model, X_test)
shap_values = explainer.shap_values(X_train)
运行 创建 shap_values 的最后一行产生以下错误。
StagingError Traceback (most recent call last)
<ipython-input-6-f789203da9c8> in <module>
1 import shap
2 explainer = shap.DeepExplainer(model, X_test)
----> 3 shap_values = explainer.shap_values(X_train)
4 print('done')
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\__init__.py in shap_values(self, X, ranked_outputs, output_rank_order, check_additivity)
117 were chosen as "top".
118 """
--> 119 return self.explainer.shap_values(X, ranked_outputs, output_rank_order, check_additivity=check_additivity)
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in shap_values(self, X, ranked_outputs, output_rank_order, check_additivity)
302 # run attribution computation graph
303 feature_ind = model_output_ranks[j,i]
--> 304 sample_phis = self.run(self.phi_symbolic(feature_ind), self.model_inputs, joint_input)
305
306 # assign the attributions to the right part of the output arrays
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in run(self, out, model_inputs, X)
359
360 return final_out
--> 361 return self.execute_with_overridden_gradients(anon)
362
363 def custom_grad(self, op, *grads):
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in execute_with_overridden_gradients(self, f)
395 # define the computation graph for the attribution values using a custom gradient-like computation
396 try:
--> 397 out = f()
398 finally:
399 # reinstate the backpropagatable check
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py in anon()
355 v = tf.constant(data, dtype=self.model_inputs[i].dtype)
356 inputs.append(v)
--> 357 final_out = out(inputs)
358 tf_execute.record_gradient = tf_backprop._record_gradient
359
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
778 else:
779 compiler = "nonXla"
--> 780 result = self._call(*args, **kwds)
781
782 new_tracing_count = self._get_tracing_count()
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
821 # This is the first call of __call__, so we have to initialize.
822 initializers = []
--> 823 self._initialize(args, kwds, add_initializers_to=initializers)
824 finally:
825 # At this point we know that the initialization is complete (or less
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in _initialize(self, args, kwds, add_initializers_to)
694 self._graph_deleter = FunctionDeleter(self._lifted_initializer_graph)
695 self._concrete_stateful_fn = (
--> 696 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
697 *args, **kwds))
698
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
2853 args, kwargs = None, None
2854 with self._lock:
-> 2855 graph_function, _, _ = self._maybe_define_function(args, kwargs)
2856 return graph_function
2857
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _maybe_define_function(self, args, kwargs)
3211
3212 self._function_cache.missed.add(call_context_key)
-> 3213 graph_function = self._create_graph_function(args, kwargs)
3214 self._function_cache.primary[cache_key] = graph_function
3215 return graph_function, args, kwargs
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
3063 arg_names = base_arg_names + missing_arg_names
3064 graph_function = ConcreteFunction(
-> 3065 func_graph_module.func_graph_from_py_func(
3066 self._name,
3067 self._python_function,
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
984 _, original_func = tf_decorator.unwrap(python_func)
985
--> 986 func_outputs = python_func(*func_args, **func_kwargs)
987
988 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\def_function.py in wrapped_fn(*args, **kwds)
598 # __wrapped__ allows AutoGraph to swap in a converted function. We give
599 # the function a weak reference to itself to avoid a reference cycle.
--> 600 return weak_wrapped_fn().__wrapped__(*args, **kwds)
601 weak_wrapped_fn = weakref.ref(wrapped_fn)
602
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\func_graph.py in wrapper(*args, **kwargs)
971 except Exception as e: # pylint:disable=broad-except
972 if hasattr(e, "ag_error_metadata"):
--> 973 raise e.ag_error_metadata.to_exception(e)
974 else:
975 raise
StagingError: in user code:
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\shap\explainers\deep\deep_tf.py:244 grad_graph *
x_grad = tape.gradient(out, shap_rAnD)
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\backprop.py:1067 gradient **
flat_grad = imperative_grad.imperative_grad(
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\imperative_grad.py:71 imperative_grad
return pywrap_tfe.TFE_Py_TapeGradient(
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\eager\backprop.py:151 _gradient_function
grad_fn = ops._gradient_registry.lookup(op_name) # pylint: disable=protected-access
C:\WinPython\WPy64-3830\python-3.8.3.amd64\lib\site-packages\tensorflow\python\framework\registry.py:96 lookup
raise LookupError(
LookupError: gradient registry has no entry for: shap_TensorListStack
shap 存储库的所有者 said:
The fundamental issue here is that DeepExplainer does not yet support TF 2.0.
那是 2019 年 12 月 11 日。现在仍然如此吗？用 Tensorflow 1.15 试试看是否有效。
shap repo 上关于此的另一个 issue（2020 年 6 月 2 日）说：
Alright, thank you. I did not see the post by Lundberg. I will stick to the workaround of using TF 1.15 until a new version of SHAP is released.