Training validation script

@@ -5,6 +5,7 @@ from itertools import chain
 from optparse import OptionParser
 from time import time
 from collections import Counter
+import re
 
 import nltk
 import sklearn
@@ -48,6 +49,12 @@ from nltk.corpus import stopwords
 #################################
 #           FUNCTIONS           #
 #################################
+def endsConLow(word):
+    miregex = re.compile(r'[^aeiouA-Z0-9]$')
+    if miregex.search(word):
+        return True
+    else:
+        return False
 
 def word2features(sent, i):
     listElem = sent[i].split('|')
@@ -69,6 +76,7 @@ def word2features(sent, i):
         'word[:3]': word[:3],
         'word[:2]': word[:2],
         'word[:1]': word[:1],
+        'endsConLow()': endsConLow(word),
     }
     '''    
     if i > 0:
@@ -196,7 +204,8 @@ if __name__ == "__main__":
     print("Exclude stop words: " + str(options.excludeStopWords))
     symbols = ['.', ',', ':', ';', '?', '!', '\'', '"', '<', '>', '(', ')', '-', '_', '/', '\\', '¿', '¡', '+', '{',
                '}', '[', ']', '*', '%', '$', '#', '&', '°', '`', '...']
-    print("Exclude symbols " + str(symbols) + ': ' + str(options.excludeSymbols))
+    #print("Exclude symbols " + str(symbols) + ': ' + str(options.excludeSymbols))
+    print("Exclude symbols: " + str(options.excludeSymbols))
 
     print('-------------------------------- PROCESSING --------------------------------')
     print('Reading corpus...')