def execute(self): db = Db() l = text_to_list(self.file_contents) d = list_to_dict(l) db.update_word_counts(d, self.doc_type) db.update_doctype_count(self.count, self.doc_type) return self.count
def learn_file(self, name, count): file_contents = None words_count = 0 db = self.db try: f = open(name, 'r') file_contents = f.read() f.close() l = text_to_list(file_contents) d = list_to_dict(l) words_count = db.update_word_counts(d, self.doc_type) db.update_doctype_count(count, self.doc_type) print '>> TRAINING [ %s ]: %5d words learned from "%s"' % (self.doc_type, words_count, name) except Exception as e: raise ValueError(usage + '\nUnable to read specified file "%s", the error message was: %s' % (args[3], e)) return words_count
from db import Db import os, sys, string, re, csv import collections reload(sys) sys.setdefaultencoding('utf8') if sys.argv[1].lower() == 'p': textname = 'positive.csv' text = open(textname, 'rb') elif sys.argv[1].lower() == 'n': textname = 'negative.csv' text = open(textname, 'rb') else: print "Invalid Entry" sys.exit(True) newl = file_to_list(text) newd = list_to_dict(newl) #word_dict = collections.OrderedDict(sorted(newd.items())) #word_dict = sorted(newd,key=newd.__getitem__) for word, count in sorted( newd.items(), key=lambda x: x[1], reverse=True ): ###########################need to sort the list according to count here print word, count #########pos or neg lai db ma rakhnu paryo################# db = Db() counts = db.get_doctype_counts() #poscount = counts['p'] #negcount = counts['n'] if sys.argv[1].lower() == "p": db.update_words_count(newd, 'p') db.update_doctype_count(len(newd), 'p') elif sys.argv[1].lower() == 'n':
def nepunigrams(): unidict = list_to_dict(unilist) #word_dict = collections.OrderedDict(sorted(newd.items())) #word_dict = sorted(newd,key=newd.__getitem__) finaldict = sorted(unidict.items(),key=lambda x : x[1],reverse = True) return finaldict