def processSingleSentence(politiciansFile,sentiTokensFile,exceptSentiTokens,sentence,webOutput):
print "<br>Loading resources...<br>Politicians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "<br>SentiTokens: " + sentiTokensFile + "<br>ExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,exceptSentiTokens)
naive = Naive(politicians,sentiTokens)
singleSentence = Opinion(1, sentence=sentence)
targets = naive.inferTarget(singleSentence)
results = []
print "<br>Inferring targets...<br>"
if targets != None:
print "<br>Inferring polarity...<br>"
for target in targets:
rules = Rules(politicians,sentiTokens)
results.append(rules.inferPolarity(target, False))
else:
print "<br>No targets were identified...<br>"
if webOutput:
return printResultsWeb(results,sentence)
else:
return printResultsConsole(results)
def processSingleSentence(politiciansFile, sentiTokensFile, exceptSentiTokens,
sentence, webOutput):
print "<br>Loading resources...<br>Politicians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "<br>SentiTokens: " + sentiTokensFile + "<br>ExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,
exceptSentiTokens)
naive = Naive(politicians, sentiTokens)
singleSentence = Opinion(1, sentence=sentence)
targets = naive.inferTarget(singleSentence)
results = []
print "<br>Inferring targets...<br>"
if targets != None:
print "<br>Inferring polarity...<br>"
for target in targets:
rules = Rules(politicians, sentiTokens)
results.append(rules.inferPolarity(target, False))
else:
print "<br>No targets were identified...<br>"
if webOutput:
return printResultsWeb(results, sentence)
else:
return printResultsConsole(results)
def processSingleSentence(politiciansFile, sentiTokensFile, exceptSentiTokens,
sentence, webOutput):
print "Loading resources..."
print "Politicians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "SentiTokens: " + sentiTokensFile
print "ExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,
exceptSentiTokens)
naive = Naive(politicians, sentiTokens)
singleSentence = Opinion(1, sentence=sentence)
print "Inferring targets..."
targets = naive.inferTarget(singleSentence)
results = []
if targets != None:
print "Inferring polarity..."
for target in targets:
rules = Rules(politicians, sentiTokens)
#if not possible to classify with rules use the naive classifier
classifiedTweet = rules.inferPolarity(target, False)
if classifiedTweet.polarity == 0:
classifiedTweet = naive.inferPolarity(classifiedTweet, True)
results.append(classifiedTweet)
else:
print "No targets were identified..."
if webOutput:
return printResultsWeb(results, sentence)
else:
return printResultsConsole(results)
def processSingleSentence(politiciansFile,sentiTokensFile,exceptSentiTokens,sentence,webOutput):
print "Loading resources..."
print "Politicians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "SentiTokens: " + sentiTokensFile
print "ExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,exceptSentiTokens)
naive = Naive(politicians,sentiTokens)
singleSentence = Opinion(1, sentence=sentence)
print "Inferring targets..."
targets = naive.inferTarget(singleSentence)
results = []
if targets != None:
print "Inferring polarity..."
for target in targets:
rules = Rules(politicians,sentiTokens)
#if not possible to classify with rules use the naive classifier
classifiedTweet = rules.inferPolarity(target, False)
if classifiedTweet.polarity == 0:
classifiedTweet = naive.inferPolarity(classifiedTweet,True)
results.append(classifiedTweet)
else:
print "No targets were identified..."
if webOutput:
return printResultsWeb(results,sentence)
else:
return printResultsConsole(results)
def processTweets(politiciansFile,sentiTokensFile,exceptSentiTokens,multiWordsFile,tweets):
"""
Processes a list of tweets:
1. Identify target
2. If target is one of the politicians infer the comment's polarity
politiciansFile -> path to the politicians list file
sentiTokensFile -> path to the sentiTokens list file
exceptSentiTokens -> path to the list of sentiTokens that cannot lose their accents without
causing ambiguity for ex: más -> mas
tweets -> list of tweets
"""
print "Loading resources...\nPoliticians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "SentiTokens: " + sentiTokensFile + "\nExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,exceptSentiTokens)
print "Multiword Tokenizer " + multiWordsFile
multiWordTokenizer = MultiWordHandler(multiWordsFile)
multiWordTokenizer.addMultiWords(Persons.getMultiWords(politicians))
multiWordTokenizer.addMultiWords(SentiTokens.getMultiWords(sentiTokens))
naive = Naive(politicians,sentiTokens)
targetedTweets = {}
classifiedTweets = {}
#Process tweets...
#First step: infer targets and create a dictionary {target,listOfTweets}
print "Identifying targets..."
for tweet in tweets:
tweetsWithTarget = naive.inferTarget(tweet)
if tweetsWithTarget != None :
#a tweet can have multiple targets (in that case the message is replicated)
for tweet in tweetsWithTarget:
if tweet.target not in targetedTweets:
targetedTweets[tweet.target] = []
tweet.taggedSentence = multiWordTokenizer.tokenizeMultiWords(tweet.sentence)
targetedTweets[tweet.target].append(tweet)
print len(targetedTweets), " targets Identified! Inferring polarity..."
rules = Rules(politicians,sentiTokens)
#Second step infer polarity
for target,tweets in targetedTweets.items():
for tweet in tweets:
if target not in classifiedTweets:
classifiedTweets[target] = []
#try to classify with rules...
classifiedTweet = rules.inferPolarity(tweet,True)
#if not possible use the naive classifier
if classifiedTweet.polarity == 0:
classifiedTweet = naive.inferPolarity(classifiedTweet,True)
classifiedTweets[target].append(classifiedTweet)
return classifiedTweets
def processTweets(politiciansFile, sentiTokensFile, exceptSentiTokens,
multiWordsFile, tweets):
"""
Processes a list of tweets:
1. Identify target
2. If target is one of the politicians infer the comment's polarity
politiciansFile -> path to the politicians list file
sentiTokensFile -> path to the sentiTokens list file
exceptSentiTokens -> path to the list of sentiTokens that cannot lose their accents without
causing ambiguity for ex: más -> mas
tweets -> list of tweets
"""
print "Loading resources...\nPoliticians: " + politiciansFile
politicians = Persons.loadPoliticians(politiciansFile)
print "SentiTokens: " + sentiTokensFile + "\nExceptTokens: " + exceptSentiTokens
sentiTokens = SentiTokens.loadSentiTokens(sentiTokensFile,
exceptSentiTokens)
print "Multiword Tokenizer " + multiWordsFile
multiWordTokenizer = MultiWordHandler(multiWordsFile)
multiWordTokenizer.addMultiWords(Persons.getMultiWords(politicians))
multiWordTokenizer.addMultiWords(SentiTokens.getMultiWords(sentiTokens))
naive = Naive(politicians, sentiTokens)
targetedTweets = {}
classifiedTweets = {}
#Process tweets...
#First step: infer targets and create a dictionary {target,listOfTweets}
print "Identifying targets..."
for tweet in tweets:
tweetsWithTarget = naive.inferTarget(tweet)
if tweetsWithTarget != None:
#a tweet can have multiple targets (in that case the message is replicated)
for tweet in tweetsWithTarget:
if tweet.target not in targetedTweets:
targetedTweets[tweet.target] = []
tweet.taggedSentence = multiWordTokenizer.tokenizeMultiWords(
tweet.sentence)
targetedTweets[tweet.target].append(tweet)
print len(targetedTweets), " targets Identified! Inferring polarity..."
rules = Rules(politicians, sentiTokens)
#Second step infer polarity
for target, tweets in targetedTweets.items():
for tweet in tweets:
if target not in classifiedTweets:
classifiedTweets[target] = []
#try to classify with rules...
classifiedTweet = rules.inferPolarity(tweet, True)
#if not possible use the naive classifier
if classifiedTweet.polarity == 0:
classifiedTweet = naive.inferPolarity(classifiedTweet, True)
classifiedTweets[target].append(classifiedTweet)
return classifiedTweets
