CODEWITHSUNDEEP
python-3.xtensorflowkerasdeep-learningtensorflow2.0
geek
geek

Reputation: 83

'KerasClassifier' object has no attribute 'loss'

I am doing churn prediction using keras. I have used column transformer from Sklearn. My code is--

import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasClassifier

def keras_classifier_wrapper():
    classifier = Sequential()
    classifier.add(Dense(9, input_dim=13, activation='relu'))
    classifier.add(Dense(8, activation='relu'))
    classifier.add(Dense(1, activation='sigmoid'))
    classifier.compile(optimizer='adam', loss='binary_crossentropy',  metrics=['accuracy'])
    return clf

clf = KerasClassifier(keras_classifier_wrapper, epochs=20, batch_size=50, verbose=0)
categorical_pipe = Pipeline([
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])
numerical_pipe = Pipeline([
   ('imputer', SimpleImputer(strategy='median'))
])
 
preprocessing = ColumnTransformer(
    [('cat', categorical_pipe, cat_var1),
     ('num', numerical_pipe, num_var1)])
 
model3 = Pipeline([
    ('preprocess', preprocessing),
    ('keras_clf', clf)
])

model3.fit(X_train, y_train)

But it showing an error-

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-162-1f0472b386ae> in <module>()
----> 1 model3.fit(X_train, y_train)

2 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/wrappers/scikit_learn.py in fit(self, x, y, **kwargs)
    157       self.model = self.build_fn(**self.filter_sk_params(self.build_fn))
    158 
--> 159     if (losses.is_categorical_crossentropy(self.model.loss) and
    160         len(y.shape) != 2):
    161       y = to_categorical(y)

AttributeError: 'KerasClassifier' object has no attribute 'loss'

Can you plz tell me why this error is showing and how to solve it.

Thanks in advance

Upvotes: 2

Views: 2097

Answers (1)

erentknn
erentknn

Reputation: 113

problem is in your keras_classifier_wrapper function

def keras_classifier_wrapper():
    classifier = Sequential()
    classifier.add(Dense(9, input_dim=13, activation='relu'))
    classifier.add(Dense(8, activation='relu'))
    classifier.add(Dense(1, activation='sigmoid'))
    classifier.compile(optimizer='adam', loss='binary_crossentropy',  metrics=['accuracy'])
    return clf # should be return classifier

you are trying to return clf but there is no clf it is defined afterwards. try to return classifier then it will work

Upvotes: 2

Related Questions