vectorizer = TfidfVectorizer(  
    stop_words='english',       # Remove common English stop words  
    max_features=10000,         # Only keep the 10,000 most frequent words  
    ngram_range=(1, 2),         # Include both single words and two-word phrases  
    min_df=2                    # Ignore words that appear in fewer than 2 documents  
)