From 1b62cfff2a910765b700bbea15786a1d62d800ef Mon Sep 17 00:00:00 2001 From: Jinesh K J Date: Tue, 7 Apr 2009 03:10:02 +0530 Subject: Updated the ngram module with option parser --- silpa/modules/ngram/visualizer.py | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) (limited to 'silpa/modules/ngram/visualizer.py') diff --git a/silpa/modules/ngram/visualizer.py b/silpa/modules/ngram/visualizer.py index e2c1136..585c11f 100644 --- a/silpa/modules/ngram/visualizer.py +++ b/silpa/modules/ngram/visualizer.py @@ -26,7 +26,7 @@ import pickle class NGramVisualizer: depth=0 - def loadCorpus(self,new_file_name,corpus_file_name): + def loadCorpus(self,corpus,corpus_file_name): limiters = [".","!","?",",",";"] try: corpusfile = open(corpus_file_name) @@ -35,23 +35,6 @@ class NGramVisualizer: else: graph_dict = pickle.load(corpusfile) # graph_dict = dict() - line = [] - line_number = 0 - rule_number = 0 - corpus="" - data_file = codecs. open(new_file_name,encoding='utf-8', errors='ignore') - while 1: - line_number = line_number +1 - text = unicode( data_file.readline()) - if text == "": - break - if text[0] == '#': - continue - line_number = line_number +1 - line = text.strip() - if(line == ""): - continue - corpus=corpus+" "+line sentences=[] sentence = "" start = 0 -- cgit