BUG: TypeError: waterfall() got an unexpected keyword argument 'features'
Opened this issue · 1 comments
iou0515 commented
Issue Description
I'm trying to use shap waterfall to plot a chart of deep learning data model for "regression" task. But it failed by "TypeError: waterfall() got an unexpected keyword argument 'features'"
Minimal Reproducible Example
from tensorflow.keras import models, layers, utils, backend as K
import matplotlib.pyplot as plt
import shap
model = models.Sequential(name="Perceptron", layers=[
layers.Dense( #a fully connected layer
name="dense",
input_dim=3, #with 3 features as the input
units=1, #and 1 node because we want 1 output
activation='linear' #f(x)=x
)
])
model.summary()
# define the function to be called by the model following it. Not used just to manifest how to call tensorflow own functions
import tensorflow as tf
def binary_step_activation(x):
##return 1 if x>0 else 0
return K.switch(x>0, tf.math.divide(x,x), tf.math.multiply(x,0))
# build the model
model = models.Sequential(name="Perceptron", layers=[
layers.Dense(
name="dense",
input_dim=3,
units=1,
activation=binary_step_activation
)
])
n_features = 10
model = models.Sequential(name="DeepNN", layers=[
### hidden layer 1
layers.Dense(name="h1", input_dim=n_features,
units=int(round((n_features+1)/2)),
activation='relu'),
layers.Dropout(name="drop1", rate=0.2),
### hidden layer 2
layers.Dense(name="h2", units=int(round((n_features+1)/4)),
activation='relu'),
layers.Dropout(name="drop2", rate=0.2),
### layer output
layers.Dense(name="output", units=1, activation='sigmoid')
])
model.summary()
########## use the Model class to build our Perceptron and DeepNN
# Perceptron
inputs = layers.Input(name="input", shape=(3,))
outputs = layers.Dense(name="output", units=1,
activation='linear')(inputs)
model = models.Model(inputs=inputs, outputs=outputs,
name="Perceptron")
# DeepNN
### layer input
inputs = layers.Input(name="input", shape=(n_features,))
### hidden layer 1
h1 = layers.Dense(name="h1", units=int(round((n_features+1)/2)), activation='relu')(inputs)
h1 = layers.Dropout(name="drop1", rate=0.2)(h1)
### hidden layer 2
h2 = layers.Dense(name="h2", units=int(round((n_features+1)/4)), activation='relu')(h1)
h2 = layers.Dropout(name="drop2", rate=0.2)(h2)
### layer output
outputs = layers.Dense(name="output", units=1, activation='sigmoid')(h2)
model = models.Model(inputs=inputs, outputs=outputs, name="DeepNN")
########VISULIZATION
#'''
#Extract info for each layer in a keras model.
#'''
def utils_nn_config(model):
lst_layers = []
if "Sequential" in str(model): #-> Sequential doesn't show the input layer
layer = model.layers[0]
lst_layers.append({"name":"input", "in":int(layer.input.shape[-1]), "neurons":0,
"out":int(layer.input.shape[-1]), "activation":None,
"params":0, "bias":0})
for layer in model.layers:
try:
dic_layer = {"name":layer.name, "in":int(layer.input.shape[-1]), "neurons":layer.units,
"out":int(layer.output.shape[-1]), "activation":layer.get_config()["activation"],
"params":layer.get_weights()[0], "bias":layer.get_weights()[1]}
except:
dic_layer = {"name":layer.name, "in":int(layer.input.shape[-1]), "neurons":0,
"out":int(layer.output.shape[-1]), "activation":None,
"params":0, "bias":0}
lst_layers.append(dic_layer)
return lst_layers
#'''
#Plot the structure of a keras neural network.
#'''
def visualize_nn(model, description=False, figsize=(10,8)):
## get layers info
lst_layers = utils_nn_config(model)
layer_sizes = [layer["out"] for layer in lst_layers]
## fig setup
fig = plt.figure(figsize=figsize)
ax = fig.gca()
ax.set(title=model.name)
ax.axis('off')
left, right, bottom, top = 0.1, 0.9, 0.1, 0.9
x_space = (right-left) / float(len(layer_sizes)-1)
y_space = (top-bottom) / float(max(layer_sizes))
p = 0.025
## nodes
for i,n in enumerate(layer_sizes):
top_on_layer = y_space*(n-1)/2.0 + (top+bottom)/2.0
layer = lst_layers[i]
color = "green" if i in [0, len(layer_sizes)-1] else "blue"
color = "red" if (layer['neurons'] == 0) and (i > 0) else color
### add description
if (description is True):
d = i if i == 0 else i-0.5
if layer['activation'] is None:
plt.text(x=left+d*x_space, y=top, fontsize=10, color=color, s=layer["name"].upper())
else:
plt.text(x=left+d*x_space, y=top, fontsize=10, color=color, s=layer["name"].upper())
plt.text(x=left+d*x_space, y=top-p, fontsize=10, color=color, s=layer['activation']+" (")
plt.text(x=left+d*x_space, y=top-2*p, fontsize=10, color=color, s="Σ"+str(layer['in'])+"[X*w]+b")
out = " Y" if i == len(layer_sizes)-1 else " out"
plt.text(x=left+d*x_space, y=top-3*p, fontsize=10, color=color, s=") = "+str(layer['neurons'])+out)
### circles
for m in range(n):
color = "limegreen" if color == "green" else color
circle = plt.Circle(xy=(left+i*x_space, top_on_layer-m*y_space-4*p), radius=y_space/4.0, color=color, ec='k', zorder=4)
ax.add_artist(circle)
### add text
if i == 0:
plt.text(x=left-4*p, y=top_on_layer-m*y_space-4*p, fontsize=10, s=r'$X_{'+str(m+1)+'}$')
elif i == len(layer_sizes)-1:
plt.text(x=right+4*p, y=top_on_layer-m*y_space-4*p, fontsize=10, s=r'$y_{'+str(m+1)+'}$')
else:
plt.text(x=left+i*x_space+p, y=top_on_layer-m*y_space+(y_space/8.+0.01*y_space)-4*p, fontsize=10, s=r'$H_{'+str(m+1)+'}$')
## links
for i, (n_a, n_b) in enumerate(zip(layer_sizes[:-1], layer_sizes[1:])):
layer = lst_layers[i+1]
color = "green" if i == len(layer_sizes)-2 else "blue"
color = "red" if layer['neurons'] == 0 else color
layer_top_a = y_space*(n_a-1)/2. + (top+bottom)/2. -4*p
layer_top_b = y_space*(n_b-1)/2. + (top+bottom)/2. -4*p
for m in range(n_a):
for o in range(n_b):
line = plt.Line2D([i*x_space+left, (i+1)*x_space+left],
[layer_top_a-m*y_space, layer_top_b-o*y_space],
c=color, alpha=0.5)
if layer['activation'] is None:
if o == m:
ax.add_artist(line)
else:
ax.add_artist(line)
plt.show()
#indention is important to make plt.show() work here
visualize_nn(model, description=True, figsize=(10,8))
utils.plot_model(model, to_file='model.png', show_shapes=True, show_layer_names=True)
#import os # Move the png file from laptop
#os.remove('model.png')
# define metrics of accuracy and F1-score which needs to be implemented as below. The optimizer is Adam and loss function is binary_crossentropy
# On the other hand, in regression problems, I usually set the MAE as the loss and the R-squared as the metric
def Recall(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
recall = true_positives / (possible_positives + K.epsilon())
return recall
def Precision(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def F1(y_true, y_pred):
precision = Precision(y_true, y_pred)
recall = Recall(y_true, y_pred)
return 2*((precision*recall)/(precision+recall+K.epsilon()))
# compile the neural network
model.compile(optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy',F1])
# define metrics for MAE
def R2(y, y_hat):
ss_res = K.sum(K.square(y - y_hat))
ss_tot = K.sum(K.square(y - K.mean(y)))
return ( 1 - ss_res/(ss_tot + K.epsilon()) )
# compile the neural network
model.compile(optimizer='adam', loss='mean_absolute_error',
metrics=[R2])
import numpy as np
X = np.random.rand(1000,10)
y = np.random.choice([1,0], size=1000)
print(X)
print(y)
# train/validation
training = model.fit(x=X, y=y, batch_size=32, epochs=100, shuffle=True, verbose=0, validation_split=0.3)
# plot
metrics = [k for k in training.history.keys() if ("loss" not in k) and ("val" not in k)]
fig, ax = plt.subplots(nrows=1, ncols=2, sharey=True, figsize=(15,3))
## training
ax[0].set(title="Training")
ax11 = ax[0].twinx()
ax[0].plot(training.history['loss'], color='black')
ax[0].set_xlabel('Epochs')
ax[0].set_ylabel('Loss', color='black')
for metric in metrics:
ax11.plot(training.history[metric], label=metric)
ax11.set_ylabel("Score", color='steelblue')
ax11.legend()
## validation
ax[1].set(title="Validation")
ax22 = ax[1].twinx()
ax[1].plot(training.history['val_loss'], color='black')
ax[1].set_xlabel('Epochs')
ax[1].set_ylabel('Loss', color='black')
for metric in metrics:
ax22.plot(training.history['val_'+metric], label=metric)
ax22.set_ylabel("Score", color="steelblue")
plt.show()
#######Explainability
#'''
#Use shap to build an a explainer.
#:parameter
# :param model: model instance (after fitting)
# :param X_names: list
# :param X_instance: array of size n x 1 (n,)
# :param X_train: array - if None the model is simple machine learning, if not None then it's a deep learning model
# :param task: string - "classification", "regression"
# :param top: num - top features to display
#:return
# dtf with explanations
#'''
def explainer_shap(model, X_names, X_instance, X_train=None, task="regression", top=10):
## create explainer
### machine learning
if X_train is None:
explainer = shap.TreeExplainer(model)
shap_values = explainer.shap_values(X_instance)
### deep learning
else:
explainer = shap.DeepExplainer(model, data=X_train[:100])
shap_values = explainer.shap_values(X_instance.reshape(1,-1))[0].reshape(-1)
## plot
### classification
if task == "classification":
shap.decision_plot(explainer.expected_value, shap_values, link='logit', feature_order='importance',
features=X_instance, feature_names=X_names, feature_display_range=slice(-1,-top-1,-1))
### regression
else:
shap.waterfall_plot(explainer.expected_value[0], shap_values,
features=X_instance, feature_names=X_names, max_display=top)
list_feature_names=["f1","f2","f3","f4","f5","f6","f7","f8","f9","f10"]
i = 1
explainer_shap(model,
X_names=list_feature_names,
X_instance=X[i],
X_train=X,
task="regression", #task="classification",
top=10)Traceback
Warning (from warnings module):
File "C:\Users\Administrator\AppData\Roaming\Python\Python310\site-packages\shap\explainers\_deep\deep_tf.py", line 99
warnings.warn("Your TensorFlow version is newer than 2.4.0 and so graph support has been removed in eager mode and some static graphs may not be supported. See PR #1483 for discussion.")
UserWarning: Your TensorFlow version is newer than 2.4.0 and so graph support has been removed in eager mode and some static graphs may not be supported. See PR #1483 for discussion.
Warning (from warnings module):
File "C:\Program Files\Python310\lib\site-packages\keras\backend.py", line 452
warnings.warn(
UserWarning: `tf.keras.backend.set_learning_phase` is deprecated and will be removed after 2020-10-11. To update it, simply pass a True/False value to the `training` argument of the `__call__` method of your layer or model.
Traceback (most recent call last):
File "E:/SQL server machine learning inl SQLserver 2022 iso & Acrobat 2023 iso/SQL Server Scripts for machine learning/SQL Server Scripts for machine learning/DL with Python Tensorflow linear.py", line 279, in <module>
explainer_shap(model,
File "E:/SQL server machine learning inl SQLserver 2022 iso & Acrobat 2023 iso/SQL Server Scripts for machine learning/SQL Server Scripts for machine learning/DL with Python Tensorflow linear.py", line 274, in explainer_shap
shap.waterfall_plot(explainer.expected_value[0], shap_values,
TypeError: waterfall() got an unexpected keyword argument 'features'Expected Behavior
Expected to see the similar chart as attached
Py file is attached as text file format
code.py.txt
Bug report checklist
- I have checked that this issue has not already been reported.
- I have confirmed this bug exists on the latest release of shap.
- I have confirmed this bug exists on the master branch of shap.
- I'd be interested in making a PR to fix this bug
Installed Versions
cloudpickle-3.0.0 llvmlite-0.42.0 numba-0.59.1 shap-0.45.0 slicer-0.0.7 tqdm-4.66.2
CloseChoice commented
Thanks for reporting and the example. Unfortunately this is not reproducible, when I run your script I get
Traceback (most recent call last):
File "/home/tobias/programming/github/shap_master/bugs/waterfall_unexpected_argument.py", line 168, in <module>
visualize_nn(model, description=True, figsize=(10,8))
File "/home/tobias/programming/github/shap_master/bugs/waterfall_unexpected_argument.py", line 103, in visualize_nn
lst_layers = utils_nn_config(model)
File "/home/tobias/programming/github/shap_master/bugs/waterfall_unexpected_argument.py", line 90, in utils_nn_config
dic_layer = {"name":layer.name, "in":int(layer.input.shape[-1]), "neurons":0,
AttributeError: 'list' object has no attribute 'shape'Even if I change that line to:
dic_layer = {"name":layer.name, "in":int(linputs.shape[-1]), "neurons":0,this throws an error at another line. Could you please fix this, I feel that this is close? Otherwise I am afraid that we'll put this on low priority since reverse engineering issues is very time consuming.