Encountered this error when calculating the accuracy on a test data-CodePudding

I am new to Machine learning, and I have this error to calculate and return the accuracy on a test data

def NBAccuracy(features_train, labels_train, features_test, labels_test):
    """ compute the accuracy of your Naive Bayes classifier """
    ### import the sklearn module for GaussianNB
    from sklearn.naive_bayes import GaussianNB

    ### create classifier
    clf = GaussianNB() #TODO

    ### fit the classifier on the training features and labels
    clf.fit(features_train, labels_train, features_test, labels_test) #TODO

    ### use the trained classifier to predict labels for the test features
    pred = clf.predict(features_test, labels_test) #TODO

    ### calculate and return the accuracy on the test data
    ### this is slightly different than the example, 
    ### where we just print the accuracy
    ### you might need to import an sklearn module
    from sklearn.metrics import accuracy_score
    accuracy = accuracy_score(features_test, labels_test, normalize=False) #TODO
    return accuracy
    return NBAccuracy

I got this error:

TypeError: fit() takes at most 4 arguments (5 given)

CodePudding user response：

You have train data and test data but you cannot use test data also in training and predict output on the same data.

 clf.fit(features_train, labels_train, batch_size=32, epochs=10)

Batch size and epochs can be varied based on your training dataset

And accuracy should be calculated between your prediction output and original output

CodePudding user response：

These areas need to be corrected:

(1) need 2 parameters to fit, and they are training data to train the model, which are features_train and labels_train

(2) prediction is done on test data, ie, features_test

(3) accuracy is done by comparing the truth labels_test and the prediction pred

(4) only 1 return statement is needed, and do return a variable return accuracy (not the function return NBAccuracy)

from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score
    
def NBAccuracy(features_train, labels_train, features_test, labels_test):
    """ compute the accuracy of your Naive Bayes classifier """
    clf = GaussianNB()
    clf.fit(features_train, labels_train)
    pred = clf.predict(features_test)
    accuracy = accuracy_score(labels_test, pred, normalize=False)
    return accuracy