# Download the Brown Corpus if not already downloaded nltk.download('brown')
# Tokenize the text and remove stopwords stopwords = nltk.corpus.stopwords.words('english') tokens = [word.lower() for word in brown.words() if word.isalpha() and word.lower() not in stopwords]
# Save the list to a file with open('top_5000_words.txt', 'w') as f: for word, freq in top_5000: f.write(f'{word}\t{freq}\n') Keep in mind that the resulting list might not be perfect, as it depends on the corpus used and the preprocessing steps.
# Download the Brown Corpus if not already downloaded nltk.download('brown')
# Tokenize the text and remove stopwords stopwords = nltk.corpus.stopwords.words('english') tokens = [word.lower() for word in brown.words() if word.isalpha() and word.lower() not in stopwords]
# Save the list to a file with open('top_5000_words.txt', 'w') as f: for word, freq in top_5000: f.write(f'{word}\t{freq}\n') Keep in mind that the resulting list might not be perfect, as it depends on the corpus used and the preprocessing steps.
