Naive Bayes Text Classification Function

This function trains a Naive Bayes classifier using text data to classify comments.

Technology Stack : scikit-learn

Code Type : Machine learning classification

Code Difficulty : Intermediate

                
                    
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline

def classify_reviews(texts, labels):
    """
    This function takes in a list of texts and their corresponding labels and
    trains a Multinomial Naive Bayes classifier to classify the texts.
    """
    # Create a pipeline that vectorizes the text and then trains a Naive Bayes classifier
    model = make_pipeline(CountVectorizer(), MultinomialNB())
    
    # Split the data into training and testing sets
    texts_train, texts_test, labels_train, labels_test = train_test_split(texts, labels, test_size=0.2, random_state=42)
    
    # Train the model
    model.fit(texts_train, labels_train)
    
    # Predict the labels for the test set
    predictions = model.predict(texts_test)
    
    # Return the accuracy of the classifier
    return model.score(texts_test, labels_test)