def main():
usage = 'python3 classifier.py training_file test_file OR \n \
python3 classifier.py training_file num_folds_for_cross_val'
if len(sys.argv) != 3:
print(usage)
return
trainFileName = sys.argv[1]
trainData = parse_tweets(trainFileName, 'B')
try:
fold = int(sys.argv[2])
'''
linearSVCClassifier = TweetClassifier(trainData, trainData, \
LinearSVC, name = 'Linear SVC Classifier', fold = fold)
linearSVCClassifier.evaluate(TweetClassifier.MODE_CROSS_VALIDATE)
'''
logisticRegClassifier = TweetClassifier(trainData, trainData, \
LogisticRegression, name = 'Logistic Regression Classifier', \
fold = fold)
logisticRegClassifier.evaluate(TweetClassifier.MODE_CROSS_VALIDATE)
except ValueError:
testFileName = sys.argv[2]
testData = parse_tweets(testFileName, 'B')
'''
linearSVCClassifier = TweetClassifier(trainData, testData, \
LinearSVC, name = 'Linear SVC Classifier')
linearSVCClassifier.evaluate(TweetClassifier.MODE_TEST_FILE)
'''
logisticRegClassifier = TweetClassifier(trainData, testData, \
LogisticRegression, name = 'Logistic Regression Classifier')
logisticRegClassifier.evaluate(TweetClassifier.MODE_TEST_FILE)
def handleCommandLineArgs():
# retrieve and check command-line arguments
#print sys.argv
if len(sys.argv) != 3:
print "Error, incorrect number of arguments"
usage()
sys.exit(1)
trainingFile = check_argv(sys.argv[1])
if os.path.exists(sys.argv[2]):
testFile = check_argv(sys.argv[2])
crossVal = False
else:
n = check_n(sys.argv[2])
crossVal = True
# build Tweet dataset
#trainingFile = '/data/cs65/semeval-2015/B/train/twitter-train-full-B.tsv'
tweetData = parse_tweets(trainingFile, 'B')
if crossVal:
# do n-fold cross validation on training set specified
trainFolds, testFolds = crossValidation(tweetData, n, False)
testData = None
else:
testData = parse_tweets(testFile, 'B')
trainFolds = [tweetData["tweets"].keys()]
testFolds = [testData["tweets"].keys()]
return tweetData, testData, trainFolds, testFolds
def main():
filename = '/data/cs65/semeval-2015/B/train/twitter-train-full-B.tsv'
global fold
fold = 5
tweetData = parse_tweets(filename, 'B')
testData(tweetData)
def main():
#Running this file will print the answers to each question to the terminal.
filename = '/data/cs65/semeval-2015/B/train/twitter-train-full-B.tsv'
tweetData = parse_tweets(filename, 'B')
#Q1: How many training examples are there?
print("(1) There are %d training examples" % len(tweetData['tweets'].keys()))
#Q2: How often do each of the sentiment labels show up? What about if you
# conflate neutral/objective/objective-OR-neutral into neutral?
print("(2) With conflation of neutral/objective turned off or on:")
print("OFF:")
maxKeyCOff = MFS_counter(tweetData)
print("---------------")
print("ON:")
maxKeyCOn = MFS_counter(tweetData, True)
print("---------------")
#Q3: What is the random baseline?
print("(3)\n\tWith conflation off: 5 sentiments, so 20% tagged correctly.\n\tWith conflation on: 3 sentiments, so 33.3% tagged correctly." )
#Q4: What is the most frequent sentiment baseline?
print("(4)\n\tWith conflation off: MFS = positive with 37.3% tagged correctly\n\tWith conflation on: MFS = neutral with 48.2% tagged correctly")
def main():
filename = '/data/cs65/semeval-2015/B/train/twitter-train-full-B.tsv'
tweetData = parse_tweets(filename, 'B')
# use 5-fold cross-validation
trainFolds, testFolds = crossValidation(tweetData, 5, False)
standardTweetData = conflateData(tweetData)
lowerTweetData = lowerData(standardTweetData)
negatedTweetData = negateData(standardTweetData, ['not'])
lowerNegatedTweetData = negateData(lowerTweetData, ['not'])
tokenizedTweetData = tokenizeData(standardTweetData)
#extras:
negateWords = ['not', 'no', 'never']
negatedTweetData2 = negateData(standardTweetData, negateWords)
lowerNegatedTweetData2 = negateData(lowerTweetData, negateWords)
print "\nQuestion 5: Most Frequent Sentiments in %d Chunks:\n" % (
len(testFolds))
testMFSList = question5(testFolds, standardTweetData)
print "\nQuestion 6: Accuracy of MFS on Test Data (with cross-validation):"
question6(trainFolds, testFolds, standardTweetData)
print "\nQuestion 7: Accuracy of Decision List Classifier:\n"
print "Standard Conditions:"
question7(trainFolds, testFolds, standardTweetData, 0)
# test stopwords
print "\nWith Stopwords Removed:"
for i in range(25, 151, 25):
print i, "-",
question7(trainFolds, testFolds, standardTweetData, i)
print "\nWith Case-Folding:"
question7(trainFolds, testFolds, lowerTweetData, 0)
print "\nQuestion 8: Accuracy of Decision List with Negations after 'not':"
question7(trainFolds, testFolds, negatedTweetData, 0)
print "\nApply negation after 'not','no','never':"
question7(trainFolds, testFolds, negatedTweetData2, 0)
print "\nQuestion 9: Accuracy of Naive Bayes Classifier:"
question9(trainFolds, testFolds, standardTweetData, 0)
print "\nQuestion 10: Naive Bayes Classifier:"
print "\n1. With StopWords Removed:"
for i in range(25, 151, 25):
print i, '-',
question9(trainFolds, testFolds, standardTweetData, i)
print "\n2. With Case-Folding:"
question9(trainFolds, testFolds, lowerTweetData, 0)
print "\n3. With Negations after 'not':"
question9(trainFolds, testFolds, negatedTweetData, 0)
print "\n4. With Case-Folding and Negations after 'not':"
question9(trainFolds, testFolds, lowerNegatedTweetData, 0)
print "\n5. With StopWords Removed, Case-Folding, and Negations after 'not':"
for i in range(25, 151, 25):
print i, '-',
question9(trainFolds, testFolds, lowerNegatedTweetData, i)
print '\nUsing 2nd Negation Strategy...'
print "\n1. With Negations after 'not', 'never', 'no':"
question9(trainFolds, testFolds, negatedTweetData2, 0)
print "\n2. With Case-Folding and Negations after 'not':"
question9(trainFolds, testFolds, lowerNegatedTweetData2, 0)
print "\n3. With StopWords Removed, Case-Folding, and Negations after 'not', \
'never', 'no':"
for i in range(25, 151, 25):
print i, '-',
question9(trainFolds, testFolds, lowerNegatedTweetData2, i)
print
print "\nQuestion 11: Accuracy of Decision List and Naive Bayes with Tokenization\n"
print 'Decision List:'
question7(trainFolds, testFolds, tokenizedTweetData, 0)
print 'Naive Bayes:'
question9(trainFolds, testFolds, tokenizedTweetData, 0)
print "\nQuestion 11: Extras\n"
tokenedLowerTweetData = lowerData(tokenizedTweetData)
tokenedLowerNegatedTweetData = negateData(tokenedLowerTweetData,
negateWords)
print 'Decision List:'
question7(trainFolds, testFolds, tokenedLowerNegatedTweetData, 0)
print 'Naive Bayes:'
question9(trainFolds, testFolds, tokenedLowerNegatedTweetData, 30)
MFS = sortSents[-1][0]
correctCount = 0
tweets = tweetData["tweets"].keys()
for tweetID in tweets:
sentiments = tweetData["tweets"][tweetID]["answers"]
if conflate:
if 'objective' in sentiments or 'neutral' in sentiments:
sentiments = ['neutral']
if MFS in sentiments:
correctCount += 1
print float(correctCount) / len(tweets) * 100
if __name__ == '__main__':
filename = '/data/cs65/semeval-2015/B/train/twitter-train-full-B.tsv'
tweetData = parse_tweets(filename, 'B')
print "\nQuestion 1:\n"
question1(tweetData)
print "\nQuestion 2:\n"
sentDictionary1 = question2(tweetData, False)
print "\nQuestion 2 (with conflation to neutral):\n"
sentDictionary2 = question2(tweetData, True)
print "\nQuestion 3:\n"
question3(tweetData)
print "\nQuestion 4:\n"
question4(sentDictionary1, tweetData, False)
question4(sentDictionary2, tweetData, True)
def build_decision_list_file(filename):
tweetData = parse_tweets(filename, 'B')
return build_decision_list(tweetData, 'tweets')
for sense2 in counts:
if sense2 != sense and feature in counts[sense2]:
presence_elsewhere += counts[sense2][feature]
if presence_elsewhere == 0:
presence_elsewhere = 0.1
score = log(counts[sense][feature]) / log(presence_elsewhere)
scores.append((sense, feature, score))
return scores
def classify(instance, decision_list, MFS):
# features = get_features(instance, range(2,4), True, [], 3)
features = get_bag_of_words(instance, caseFolding=True)
for entry in decision_list:
if entry[1] in features:
return entry[0]
return MFS
if __name__ == "__main__":
filename = 'twitter-train-full-B.tsv'
tweetData = parse_tweets(filename, 'B')
stopwords = get_stopwords(tweetData['tweets'], 0.2)
stopwords2 = get_stopwords(tweetData['tweets'], 0.1)
print("Stopwords with threshold of 0.2\n", stopwords)
print("Stopwords with threshold of 0.1\n", stopwords2)
print()
example = ["This", "is", "not", "a", "very", "good", "example", ",", "but", "that", "one", "was", "."]
print(example)
negation_processing(example)
print(example)
def main():
usage = 'python3 preprocess.py <INPUT_FILE_NAME> <OUTPUT_FILE_NAME>'
if len(sys.argv) != 3:
print(usage)
return
global abbreviationDict
abbreviationDict = {}
for line in open('abbreviationDict.txt', 'r'):
fields = line.split(': ')
abbreviation = fields[0].lower()
words = fields[1].lower()
abbreviationDict[abbreviation] = words
global emoticonDict
emoticonDict = {}
for line in open('emoticonDict.txt', 'r'):
fields = line.split()
emoticon = fields[0]
replacement = fields[1]
abbreviationDict[emoticon] = replacement
global stopWords
stopWords = []
for line in open('stopWordsDict.txt', 'r'):
stopWords.append(line.split()[0])
global positiveWords
positiveWords = {}
for line in open('positive-words.txt', 'r', encoding='ISO-8859-1'):
positiveWords[line.split()[0]] = 1
global negativeWords
negativeWords = {}
for line in open('negative-words.txt', 'r', encoding='ISO-8859-1'):
negativeWords[line.split()[0]] = 1
'''
#global positiveWords
#global negativeWords
#positiveWords = {}
#negativeWords = {}
for line in open('unigrams-pmilexicon.txt', 'r'):
currLine = line.split()
score = float(currLine[1])
if score >= 4.5:
positiveWords[currLine[0]] = score
elif score <= 4.5:
negativeWords[currLine[0]] = score
global positiveWordsPOS
global negativeWordsPOS
global weakPositiveWordsPOS
global weakNegativeWordsPOS
positiveWordsPOS = {}
negativeWordsPOS = {}
weakPositiveWordsPOS = {}
weakNegativeWordsPOS = {}
for line in open('mpqa.tff', 'r'):
currLine = line.split()
wordType = currLine[0]
POS = currLine[3].split('=')[1]
if POS == 'noun':
POS = 'NN'
elif POS == 'adj':
POS = 'JJ'
elif POS == 'verb':
POS = 'VBD'
elif POS == 'adverb':
POS = 'RB'
if wordType == 'type=strongsubj':
if currLine[5] == 'priorpolarity=positive':
positiveWordsPOS[currLine[2]] = POS
else:
negativeWordsPOS[currLine[2]] = POS
else:
if currLine[5] == 'priorpolarity=negative':
weakPositiveWordsPOS[currLine[2]] = POS
else:
weakNegativeWordsPOS[currLine[2]] = POS
'''
trainFileName = sys.argv[1]
trainData = parse_tweets(trainFileName, 'B')
preprocess(trainData)
outputFileName = sys.argv[2]
write(trainData, outputFileName)
def main():
usage = 'python3 preprocess.py <INPUT_FILE_NAME> <OUTPUT_FILE_NAME>'
if len(sys.argv) != 3:
print(usage)
return
global abbreviationDict
abbreviationDict = {}
for line in open('abbreviationDict.txt', 'r'):
fields = line.split(': ')
abbreviation = fields[0].lower()
words = fields[1].lower()
abbreviationDict[abbreviation] = words
global emoticonDict
emoticonDict = {}
for line in open('emoticonDict.txt', 'r'):
fields = line.split()
emoticon = fields[0]
replacement = fields[1]
abbreviationDict[emoticon] = replacement
global stopWords
stopWords = []
for line in open('stopWordsDict.txt', 'r'):
stopWords.append(line.split()[0])
global positiveWords
positiveWords = {}
for line in open('positive-words.txt', 'r', encoding='ISO-8859-1'):
positiveWords[line.split()[0]] = 1
global negativeWords
negativeWords = {}
for line in open('negative-words.txt', 'r', encoding='ISO-8859-1'):
negativeWords[line.split()[0]] = 1
'''
#global positiveWords
#global negativeWords
#positiveWords = {}
#negativeWords = {}
for line in open('unigrams-pmilexicon.txt', 'r'):
currLine = line.split()
score = float(currLine[1])
if score >= 4.5:
positiveWords[currLine[0]] = score
elif score <= 4.5:
negativeWords[currLine[0]] = score
global positiveWordsPOS
global negativeWordsPOS
global weakPositiveWordsPOS
global weakNegativeWordsPOS
positiveWordsPOS = {}
negativeWordsPOS = {}
weakPositiveWordsPOS = {}
weakNegativeWordsPOS = {}
for line in open('mpqa.tff', 'r'):
currLine = line.split()
wordType = currLine[0]
POS = currLine[3].split('=')[1]
if POS == 'noun':
POS = 'NN'
elif POS == 'adj':
POS = 'JJ'
elif POS == 'verb':
POS = 'VBD'
elif POS == 'adverb':
POS = 'RB'
if wordType == 'type=strongsubj':
if currLine[5] == 'priorpolarity=positive':
positiveWordsPOS[currLine[2]] = POS
else:
negativeWordsPOS[currLine[2]] = POS
else:
if currLine[5] == 'priorpolarity=negative':
weakPositiveWordsPOS[currLine[2]] = POS
else:
weakNegativeWordsPOS[currLine[2]] = POS
'''
trainFileName = sys.argv[1]
trainData = parse_tweets(trainFileName, 'B')
preprocess(trainData)
outputFileName = sys.argv[2]
write(trainData, outputFileName)
