def printResults(accuracy, precision, recall, f_measure, name="Unknown"):
print '\n'
print "Result of " + name + ":"
print "Accuracy: ", sum(accuracy) / float(len(accuracy))
print "Precision: ", sum(precision) / float(len(precision))
print "Recall: ", sum(recall) / float(len(recall))
print "F1-measure: ", sum(f_measure) / float(len(f_measure))
print '\n'
if __name__ == "__main__":
xmlTrainFile = '../DATA/general-tweets-train-tagged.xml'
tweets = xml.readXML(xmlTrainFile)
results_folder = 'results_5/'
if not os.path.exists(results_folder):
os.makedirs(results_folder)
tokenized_tweets = []
for tweet in tweets:
tokenized_tweets.append(ut.tokenize(tweet.content, tweet.polarity))
tweets = []
labels = []
for tweet in tokenized_tweets:
tweets.append(tweet['clean'])
labels.append(tweet['class'])
import classify_diagnosis as diagnose
import itertools
def printResults(accuracy, precision, recall, f_measure, name="Unknown"):
print "Result of " + name + ":"
print "Accuracy: ", sum(accuracy) / float(len(accuracy))
print "Precision: ", sum(precision) / float(len(precision))
print "Recall: ", sum(recall) / float(len(recall))
print "F1-measure: ", sum(f_measure) / float(len(f_measure))
if __name__ == "__main__":
xmlTrainFile = '../DATA/general-tweets-train-tagged.xml'
tweets = xml.readXML(xmlTrainFile)
tokenized_tweets = []
for tweet in tweets:
tokenized_tweets.append(ut.tokenize(tweet.content, tweet.polarity))
tweets = []
labels = []
for tweet in tokenized_tweets:
tweets.append(tweet['clean'])
labels.append(tweet['class'])
tweets = np.array(tweets)
labels = np.array(labels)
train_tweets, test_tweets, train_labels, test_labels = ut.crossValidation2(
def readMD(path):
u"""Read the markdown from path and answer the compiled etree."""
xmlPath = markDown2XMLFile(path)
return readXML(xmlPath)