Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
NLTK Intro for PUGS
Search
Victor Neo
March 27, 2012
Programming
7
560
NLTK Intro for PUGS
Slides for the NLTK talk given on March 2012 for Python User Group SG Meetup.
Victor Neo
March 27, 2012
Tweet
Share
More Decks by Victor Neo
See All by Victor Neo
Django - The Next Steps
victorneo
5
620
DevOps: Python tools to get started
victorneo
9
13k
Git and Python workshop
victorneo
2
790
Other Decks in Programming
See All in Programming
Composerが「依存解決」のためにどんな工夫をしているか #phpcon
o0h
PRO
1
240
PHPで始める振る舞い駆動開発(Behaviour-Driven Development)
ohmori_yusuke
2
230
エラーって何種類あるの?
kajitack
5
320
5つのアンチパターンから学ぶLT設計
narihara
1
130
LINEヤフー データグループ紹介
lycorp_recruit_jp
0
1.4k
Azure AI Foundryではじめてのマルチエージェントワークフロー
seosoft
0
140
PicoRuby on Rails
makicamel
2
110
設計やレビューに悩んでいるPHPerに贈る、クリーンなオブジェクト設計の指針たち
panda_program
6
1.7k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
48
32k
VS Code Update for GitHub Copilot
74th
1
480
LT 2025-06-30: プロダクトエンジニアの役割
yamamotok
0
600
deno-redisの紹介とJSRパッケージの運用について (toranoana.deno #21)
uki00a
0
150
Featured
See All Featured
個人開発の失敗を避けるイケてる考え方 / tips for indie hackers
panda_program
107
19k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.3k
The Power of CSS Pseudo Elements
geoffreycrofte
77
5.8k
Why Our Code Smells
bkeepers
PRO
337
57k
How to Ace a Technical Interview
jacobian
277
23k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
GitHub's CSS Performance
jonrohan
1031
460k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
181
53k
Faster Mobile Websites
deanohume
307
31k
Side Projects
sachag
455
42k
Transcript
Natural Language Toolkit @victorneo
Natural Language Processing
"the process of a computer extracting meaningful information from natural
language input and/or producing natural language output"
None
Getting started with NLTK
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
None
installatio n # you might need numpy pip install nltk
# enter Python shell import nltk nltk.download()
None
packages # For Part of Speech tagging maxent_treebank_pos_tagger # Get
a list of stopwords stopwords # Brown corpus to play around brown
Preparing data / corpus
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!")
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.
Part-of-speech tagging
pos tagging text = "Run away!" nltk.word_tokenize(text) nltk.pos_tag(tokens) [('Run', 'NNP'),
('away', 'RB'), ('!', '.')]
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
pos tagging "The sailor dogs the barmaid." [('The', 'DT'), ('sailor',
'NN'), ('dogs', 'NNS'), ('the', 'DT'), ('barmaid', 'NN'), ('.', '.')]
Sentiment Analysis Code: http://bit.ly/GLu2Q9
Differentiate between "happy" and "sad" tweets. Teach the classifier the
"features" of happy & sad tweets and test how good it is.
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"
Process data (tweets) Extract Features Train classifier Test classifer accuracy
Tokenize tweets extract_features Naive Bayes Classifier
Process data (tweets) Extract Features Train classifier Test classifer accuracy
Tokenize tweets extract_features Naive Bayes Classifier
happy.txt sad.txt happy_test.txt sad_test.txt } training data } testing data
Tweets obtained from Twitter Search API
Process data (tweets) Extract Features Train classifier Test classifer accuracy
Tokenize tweets extract_features Naive Bayes Classifier
Happy tweets usually contain the following words: "am happy", "great
day" etc. Sad tweets usually contain the following: "not happy", "am sad" etc. features
{'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()
Process data (tweets) Extract Features Train classifier Test classifer accuracy
Tokenize tweets extract_features Naive Bayes Classifier
training_set = \ nltk.classify.util.\ apply_features(extract_features, tweets) classifier = \ NaiveBayesClassifier.train
(training_set) training the classifer training classifer
Process data (tweets) Extract Features Train classifier Test classifer accuracy
Tokenize tweets extract_features Naive Bayes Classifier
def classify_tweet(tweet): return \ classifier.classify(extract_features (tweet)) testing classifer
$ python classification.py Total accuracy: 90.00% (18/20) 18 tweets got
classified correctly.
Where to go from here.
http://www.nltk.org/book
https://class.coursera.org/nlp/auth/welcome
http://www.slideshare.net/shanbady/nltk-boston-text-analytics
[('Thank', 'NNP'), ('you', 'PRP'), ('.', '.')] @victorneo