Python nltk Module

This page shows the popular functions and classes defined in the nltk module. The items are ordered by their popularity in 40,000 open source Python projects. If you can not find a good example below, you can try the search function to search modules.

• 1. word_tokenize()    
  Used in 254 projects
• 2. download()    
  Used in 148 projects
• 3. corpus()    
  Used in 144 projects
• 4. pos_tag()    
  Used in 112 projects
• 5. tokenize()    
  Used in 100 projects
• 6. sent_tokenize()    
  Used in 81 projects
• 7. FreqDist()    
  Used in 68 projects
• 8. ngrams()    
  Used in 31 projects
• 9. WordNetLemmatizer()    
  Used in 28 projects
• 10. stem()    
  Used in 27 projects
• 11. data()    
  Used in 25 projects
• 12. Tree()    
  Used in 23 projects
• 13. RegexpParser()    
  Used in 21 projects
• 14. ne_chunk()    
  Used in 18 projects
• 15. bigrams()    
  Used in 18 projects
• 16. tag()    
  Used in 14 projects
• 17. PorterStemmer()    
  Used in 14 projects
• 18. util()    
  Used in 13 projects
• 19. RegexpTokenizer()    
  Used in 12 projects
• 20. chunk()    
  Used in 10 projects
• 21. tree()    
  Used in 9 projects
• 22. classify()    
  Used in 9 projects
• 23. probability()    
  Used in 8 projects
• 24. trigrams()    
  Used in 8 projects
• 25. wordpunct_tokenize()    
  Used in 6 projects
• 26. ConditionalFreqDist()    
  Used in 6 projects
• 27. metrics()    
  Used in 6 projects
• 28. TreebankWordTokenizer()    
  Used in 6 projects
• 29. SnowballStemmer()    
  Used in 6 projects
• 30. ChunkParserI()    
  Used in 5 projects
• 31. parse()    
  Used in 5 projects
• 32. ChartParser()    
  Used in 5 projects