NLTK Intro for PUGS

Slides for the NLTK talk given on March 2012 for Python User Group SG Meetup.

1. Natural Language Toolkit @victorneo
2. Natural Language Processing
3. "the process of a computer extracting meaningful information from natural language input and/or producing natural language output"
5. Getting started with NLTK
6. Open source Python modules, linguistic data and documentation for research and development in natural language processing and text analytics, with distributions for Windows, Mac OSX and Linux. NLTK
8. installatio n # you might need numpy pip install nltk # enter Python shell import nltk nltk.download()
10. packages # For Part of Speech tagging maxent_treebank_pos_tagger # Get a list of stopwords stopwords # Brown corpus to play around brown
11. Preparing data / corpus
12. tokens NLTK works on Tokens, for example, "Hello World!" will be tokenized to: ['Hello', 'World', '!'] The built-in tokenizer for most use cases: nltk.word_tokenize("Hello World!")
13. text processing HTML text: raw = nltk.clean_html(html_text) tokens = nltk.word_tokenize(raw) text = nltk.Text(tokens) Use BeautifulSoup for preprocessing of the HTML text to discard unnecessary data.
14. Part-of-speech tagging
15. pos tagging text = "Run away!" nltk.word_tokenize(text) nltk.pos_tag(tokens) [('Run', 'NNP'), ('away', 'RB'), ('!', '.')]
16. pos tagging [('Run', 'NNP'), ('away', 'RB'), ('!', '.')] NNP: Proper Noun, Singular RB : Adverb http://www.ling.upenn.edu/courses/Fall_2003/ling001/penn_treebank_pos. html
17. pos tagging "The sailor dogs the barmaid." [('The', 'DT'), ('sailor', 'NN'), ('dogs', 'NNS'), ('the', 'DT'), ('barmaid', 'NN'), ('.', '.')]
18. Sentiment Analysis Code: http://bit.ly/GLu2Q9
19. Differentiate between "happy" and "sad" tweets. Teach the classifier the "features" of happy & sad tweets and test how good it is.
20. Happy: "Looking through old pics and realizing everything happens for a reason. So happy with where I am right now" Sad: "So sad I have 8 AM class tomorrow"
21. Process data (tweets) Extract Features Train classifier Test classifer accuracy Tokenize tweets extract_features Naive Bayes Classifier
22. Process data (tweets) Extract Features Train classifier Test classifer accuracy Tokenize tweets extract_features Naive Bayes Classifier
23. happy.txt sad.txt happy_test.txt sad_test.txt } training data } testing data Tweets obtained from Twitter Search API
24. Process data (tweets) Extract Features Train classifier Test classifer accuracy Tokenize tweets extract_features Naive Bayes Classifier
25. Happy tweets usually contain the following words: "am happy", "great day" etc. Sad tweets usually contain the following: "not happy", "am sad" etc. features
26. {'contains(not)': False, 'contains(view)': False, 'contains(best)': False, 'contains(excited)': False, 'contains(morning)': False, 'contains(about)': False, 'contains(horrible)': True, 'contains(like)': False, ... } output of extract_features()
27. Process data (tweets) Extract Features Train classifier Test classifer accuracy Tokenize tweets extract_features Naive Bayes Classifier
28. training_set = \ nltk.classify.util.\ apply_features(extract_features, tweets) classifier = \ NaiveBayesClassifier.train (training_set) training the classifer training classifer
29. Process data (tweets) Extract Features Train classifier Test classifer accuracy Tokenize tweets extract_features Naive Bayes Classifier
30. def classify_tweet(tweet): return \ classifier.classify(extract_features (tweet)) testing classifer
31. $ python classification.py Total accuracy: 90.00% (18/20) 18 tweets got classified correctly.
32. Where to go from here.
33. http://www.nltk.org/book
34. https://class.coursera.org/nlp/auth/welcome
35. http://www.slideshare.net/shanbady/nltk-boston-text-analytics
36. [('Thank', 'NNP'), ('you', 'PRP'), ('.', '.')] @victorneo