NLP Analysis

Text mining and NLP for scientific research. Venv: source /Users/zhangmingda/clawd/.venv/bin/activate

Text Preprocessing

import re
import nltk
from collections import Counter

# Download resources (first time)
# nltk.download('punkt')
# nltk.download('stopwords')
# nltk.download('wordnet')

from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize, sent_tokenize
from nltk.stem import WordNetLemmatizer