language-engineering

class Tester(object):
	def __init__(self):
		self.n = 5
	def inc(self,x):
		self.n+=x
	def do_math(self):
		print self.n * 3 + 5 

test = Tester()
test.inc(2)

language-engineering

class Tester(object):
	def __init__(self):
		self.n = 5
	def inc(self,x):
		self.n+=x
	def do_math(self):
		print self.n * 3 + 5 

test = Tester()
test.inc(2)

language-engineering

from corpus_readers import AmazonReviewCorpusReader  #import reader
arcr = AmazonReviewCorpusReader()    		     #create new reader
positive_reviews = arcr.positive()		     #store a reader pointing at positive reviews
negative_reviews = arcr.negative()
dvd_reviews = arcr.category("dvd") 
positive_dvd_reviews = dvd_reviews.positive()
for review in positive_dvd_reviews.reviews():
	print review.raw()

language-engineering

from corpus_readers import AmazonReviewCorpusReader  #import reader
arcr = AmazonReviewCorpusReader()    		     #create new reader
positive_reviews = arcr.positive()		     #store a reader pointing at positive reviews
negative_reviews = arcr.negative()
dvd_reviews = arcr.category("dvd") 
positive_dvd_reviews = dvd_reviews.positive()
for review in positive_dvd_reviews.reviews():
	print review.raw()

language-engineering

import os, sys 
sys.path.append(os.path.join("t:\\", "Departments", "Informatics", "LanguageEngineering"))

language-engineering

from corpus_readers import AmazonReviewCorpusReader

arcr = AmazonReviewCorpusReader( )

positive_reviews = arcr.positive( )

negative_reviews = arcr.negative( )

dvd_reviews = arcr.category( "dvd" ) 

language-engineering

from sussex_nltk.corpus_readers import AmazonReviewCorpusReader 	#import reader class

arcr = AmazonReviewCorpusReader()		 #create new reader

positive_reviews = arcr.positive()		 #store a reader pointing at all positive reviews
negative_reviews = arcr.negative()		 #pointing at all negative
dvd_reviews = arcr.category("dvd") 		 #pointing at all dvd
positive_dvd_reviews = dvd_reviews.positive()	 #pointing at all postive dvd

#get a sample of the tokens in positive dvd reviews using your 5-digit candidate number

language-engineering

from nltk import sent_tokenize	
		
sentences = sent_tokenize(document)	#segment a single string (our document) into a list of sentences and store in "sents"

language-engineering

from sussex_nltk.corpus_readers import WSJCorpusReader   #import the corpus reader

wsjcr = WSJCorpusReader()             #create a new WSJ corpus reader

#get a sample of tokens in the corpus using your 5-digit candidate number
tokens = wsjcr.sample_words(12345) 
for token in tokens:                  #iterate over the tokens       
    print token                       #print each token

language-engineering

from sussex_nltk.corpus_readers import RCV1CorpusReader    #import the corpus reader

rcv1cr = RCV1CorpusReader()        #create a new Reuters corpus reader
tokens = rc1cr.words()             #get a list of all tokens in corpus
for token in tokens:
    print token                    #print each token in corpus