ravikiranj

Sentence = AT_USER i heard about that contest! congrats girl!!

Feature Vector
==============
hey',.....'heard','congrats', .... 'bombs', 'strange', 'australian', 'women', 'drink', 'head', 'hurts', 'bloodwork'
 0           1        1               0        0            0           0        0       0       0          0

ravikiranj

def getSVMFeatureVectorAndLabels(tweets, featureList):
    sortedFeatures = sorted(featureList)
    map = {}
    feature_vector = []
    labels = []
    for t in tweets:
        label = 0
        map = {}
        #Initialize empty map
        for w in sortedFeatures:

ravikiranj

.*
optimization finished, #iter = 5
nu = 0.176245
obj = -2.643822, rho = 0.164343
nSV = 3, nBSV = 0
*
optimization finished, #iter = 1
nu = 0.254149
obj = -2.541494, rho = 0.000000
nSV = 2, nBSV = 0

ravikiranj

import svm
from svmutil import *

#training data
labels = [0, 1, 1, 2]
samples = [[0, 1, 0], [1, 1, 1], [1, 1, 0], [0, 0, 0]]

#SVM params
param = svm_parameter()
param.C = 10

ravikiranj

#Max Entropy Classifier
MaxEntClassifier = nltk.classify.maxent.MaxentClassifier.train(training_set, 'GIS', trace=3, \
                       encoding=None, labels=None, sparse=True, gaussian_prior_sigma=0, max_iter = 10)
testTweet = 'Congrats @ravikiranj, i heard you wrote a new tech post on sentiment analysis'
processedTestTweet = processTweet(testTweet)
print MaxEntClassifier.classify(extract_features(getFeatureVector(processedTestTweet)))

Output
=======
positive

ravikiranj

testTweet = 'I am so badly hurt'
processedTestTweet = processTweet(testTweet)
print NBClassifier.classify(extract_features(getFeatureVector(processedTestTweet)))

Output
======
positive

ravikiranj

# print informative features about the classifier
print NBClassifier.show_most_informative_features(10)

Output
======
Most Informative Features
       contains(twitter) = False          positi : neutra =      2.3 : 1.0
           contains(car) = False          positi : negati =      2.3 : 1.0
         contains(hurts) = False          positi : negati =      2.3 : 1.0
      contains(articles) = False          positi : neutra =      1.4 : 1.0

ravikiranj

# Train the classifier
NBClassifier = nltk.NaiveBayesClassifier.train(training_set)

# Test the classifier
testTweet = 'Congrats @ravikiranj, i heard you wrote a new tech post on sentiment analysis'
processedTestTweet = processTweet(testTweet)
print NBClassifier.classify(extract_features(getFeatureVector(processedTestTweet)))

Output
======

ravikiranj

#Read the tweets one by one and process it
inpTweets = csv.reader(open('data/sampleTweets.csv', 'rb'), delimiter=',', quotechar='|')
stopWords = getStopWordList('data/feature_list/stopwords.txt')
featureList = []

# Get tweet words
tweets = []
for row in inpTweets:
    sentiment = row[0]
    tweet = row[1]

ravikiranj

#get feature list stored in a file (for reuse)
featureList = getFeatureList('data/sampleTweetFeatureList.txt')

#start extract_features
def extract_features(tweet):
    tweet_words = set(tweet)
    features = {}
    for word in featureList:
        features['contains(%s)' % word] = (word in tweet_words)
    return features