One-Hot Encoding Using NLTK

from sklearn.feature_extraction.text import CountVectorizer

# Example documents
documents = [
    "I like NLP",
    "I like machine learning",
    "NLP is fun"
]

# Initialize CountVectorizer with binary=True
vectorizer = CountVectorizer(
    lowercase=True,
    stop_words='english',
    binary=True      # This makes it One-Hot Encoding
)

# Convert documents to one-hot matrix
X = vectorizer.fit_transform(documents)

# Vocabulary
print("Vocabulary:", vectorizer.get_feature_names_out())

# One-hot encoded matrix
print("\nOne-Hot Encoding Matrix:")
print(X.toarray())

Query/Feedback