import os, os.path
import sys, json
import cStringIO
sys.path.append(
'/Users/rickardbergeling/GitHub/CS4242-Social-Media-Computing/Assignment03/python/libsvm-master/python'
)
import svm
import pickle
import dictionary
from svmutil import *
import helper as helperClass
helper = helperClass.Helper("python/data/stopwords.txt")
helper.setFeatureList(pickle.load(open("python/featureList.pkl", "rb")))
featureVectors = []
for i in range(1, len(sys.argv)):
tweet = json.loads(sys.argv[i])
featureVectors.append(helper.getFeatureVector(helper.clean(tweet)))
model = svm_load_model('python/tweetClassifier.model')
save_stdout = sys.stdout
sys.stdout = cStringIO.StringIO()
predictedLabels, predictionAccuracy, predictionValues = svm_predict(
[0] * len(featureVectors), featureVectors, model)
sys.stdout = save_stdout
for label in predictedLabels:
print dictionary.translateLabel(int(label))
print "Translating labels..." # Convert labels to numbers labels = [] for l in rawLabels: labels.append(dictionary.translateSentiment(l)) print "Cleaning tweets..." # Clean all the tweets, including stopword removal, stemming and custom feature removal tweets = [] words = set() for t in rawTweets: cleanedTweet = helper.clean(t) tweets.append(cleanedTweet) words = words.union(helper.extractWords(cleanedTweet)) print "Generating feature vectors..." # Generate feature vectors for each one of the tweets featureVectors = [] for t in tweets: featureVectors.append(helper.getFeatureVector(t)) p_labs, p_acc, p_vals = svm_predict(labels, featureVectors, model) translatedLabels = [] for i in p_labs: translatedLabels.append(dictionary.translateLabel(int(i))) result_output_file = "data/output/result.csv" reader.saveSVMOutput(result_output_file, rawTweets, translatedLabels, rawLabels) reader.getStats(result_output_file)
