SVM Feature Vector extraction and Training the classifier

tw-17.py

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:
            map[w] = 0
        
        tweet_words = t[0]
        tweet_opinion = t[1]
        #Fill the map
        for word in tweet_words:
            #process the word (remove repetitions and punctuations)
            word = replaceTwoOrMore(word) 
            word = word.strip('\'"?,.')
            #set map[word] to 1 if word exists
            if word in map:
                map[word] = 1
        #end for loop
        values = map.values()
        feature_vector.append(values)
        if(tweet_opinion == 'positive'):
            label = 0
        elif(tweet_opinion == 'negative'):
            label = 1
        elif(tweet_opinion == 'neutral'):
            label = 2
        labels.append(label)            
    #return the list of feature_vector and labels
    return {'feature_vector' : feature_vector, 'labels': labels}
#end

#Train the classifier
result = getSVMFeatureVectorandLabels(tweets, featureList)
problem = svm_problem(result['labels'], result['feature_vector'])
#'-q' option suppress console output
param = svm_parameter('-q')
param.kernel_type = LINEAR
classifier = svm_train(problem, param)
svm_save_model(classifierDumpFile, classifier)

#Test the classifier
test_feature_vector = getSVMFeatureVector(test_tweets, featureList)
#p_labels contains the final labeling result
p_labels, p_accs, p_vals = svm_predict([0] * len(test_feature_vector),test_feature_vector, classifier)