def loadFeedInformationToDatabase(settings,allCats):
# Put feed information in database
database = FeedDatabase(settings['database'])
counter = 0
size = len(allCats)
for elem in allCats.keys():
sys.stderr.write('...Uploading... ({0}/{1})\n'.format(counter,size))
title = allCats[elem]['title']
guid = elem
description = allCats[elem]['description']
categry = allCats[elem]['category']
database.add_feed_element(title,guid,description,categry)
counter +=1
sys.stderr.write('...Finished Uploading Information to Database\n')
database.close_database()
def train_classifier(settings,trainingData):
counter = 0
size = len(trainingData)
database = FeedDatabase(settings['database'])
for key in trainingData.keys():
database.change_classified(key,classified=True)
database.close_database()
classifier = fisherclassifier(getwords)
classifier.setdb(settings['database'])
for key in trainingData.keys():
sys.stderr.write('...Training ({0}/{1})...\n'.format(counter,size))
classifier.train(trainingData[key]['description'],trainingData[key]['category'])
counter +=1
sys.stderr.write('...Finished Training Classifier\n')
def classifyEntries(settings):
database = FeedDatabase(settings['database'])
unclassifiedEntries = database.get_unpredicted_entries()
#for i in unclassifiedEntries:
# print(i)
#print(len(unclassifiedEntries))
database.close_database()
classifier = fisherclassifier(getwords)
classifier.setdb(settings['database'])
counter = 0
size = len(unclassifiedEntries)
results = []
for entr in unclassifiedEntries:
a = open('script50.txt','w+')
for i in results:
a.write('{0}|{1}\n'.format(i['guid'],i['category']))
a.close()
category = classifier.classify(entr['description'])
#print('{0}|{1}'.format(entr['guid'],category))
results.append({'guid':entr['guid'],'category':category})
counter += 1
sys.stderr.write('...Classified {0} of {1} entries\n'.format(counter,size))
