One-Hot Encoding Using NLTK

from sklearn.feature_extraction.text import CountVectorizer# Example documentsdocuments = [    "I like NLP",    "I like machine learning",    "NLP is fun"]# Initialize CountVectorizer with binary=Truevectorizer = CountVectorizer(    lowercase=True,    stop_words='english',    binary=True      # This makes it One-Hot Encoding)# Convert documents to one-hot matrixX = vectorizer.fit_transform(documents)# Vocabularyprint("Vocabulary:", vectorizer.get_feature_names_out())# One-hot encoded matrixprint("\nOne-Hot Encoding Matrix:")print(X.toarray())

Query/Feedback