def printgeg(): # print wat gegevens over het corp wrds = corpus(5) print "type/token ratio vijf auteurs:" tt_ratio = float(len(wrds))/float(len(set(wrds))) print tt_ratio print "documentlengte/aantal woorden:" print len(wrds)
from classifier import train, p_feat_cat, p_feature
from features import *
from help_functions import *
import time
from nltk import NaiveBayesClassifier
import nltk
import operator
import pickle
import datetime
from math import *
import winsound
from time import time, sleep
import webbrowser
import os
corp = corpus(50)
# corp = lemmatize_corpus(corp0)
# writetofile(corp,"lemmatized_corpus.pkl")
compactcorpus = compactcorpus(corp)
print "corpus build"
authors = compactcorpus.keys()
def document_features(document):
features = {}
for word in word_features:
features[word] = word in document
return features