def main():
folders = {}
folders["politik"] = "data/politik"
folders["sport"] = "data/sport"
folders["wirtschaft"] = "data/wirtschaft"
bank = ClassBank()
l = Loader()
# train data
for classname, folder in folders.iteritems():
count = 0
content = ""
for file in os.listdir(folder + "/train/"):
if file.endswith(".txt"):
count = count + 1
content = content + " " + l.load_txt(folder + "/train/" + file)
c = Class(classname, content, count)
bank.addClass(c)
bank.train()
c = Classifier()
# test data
for classname, folder in folders.iteritems():
print "\n=== Testing",classname, "===\n"
for file in os.listdir(folder + "/test/"):
if file.endswith(".txt"):
tokenizer = Tokenizer(l.load_txt(folder + "/test/" + file))
classifiedClass = c.classify(tokenizer.getTokens(), bank)
print file,"=",classifiedClass.getName()
def main(): c = Class( "Politik", "Das ist der Inhalt der Klasse", 10 ) d = Class( "Wirtschaft", "Noch eine Geschichte mit Inhalt", 10 ) b = ClassBank() b.addClass( c ) b.addClass( d ) b.train() classes = b.getClasses() for c in classes: for t in classes[c].condProb: prob = classes[c].condProb print t,"=",prob[t]
