For pulling conjunctions

getAdjectives.py

@@ -2,49 +2,57 @@ import math
 import nltk
 from nltk.corpus import brown as sc
 from collections import Counter
+from nltk.corpus import movie_reviews
 
 
 
-def genConj(training):
-    conj = open('conj.txt', 'r+')
+def genConj():
+    conj = open('movieconj.txt', 'r+')
     ands = open('ands.txt', 'r+')
     ors =  open('ors.txt', 'r+')
     buts =  open('buts.txt', 'r+')
     nor =  open('nor.txt', 'r+')
     eor = open('eor.txt', 'r+')
-    j = 0;
-    for review in training:     #For every review
+    j = 0
+    for review in sorted(movie_reviews.fileids()):     #For every review
         tokens = nltk.pos_tag(nltk.word_tokenize(movie_reviews.raw(fileids=[review])))
         print j
         j = j+1
         for i in range(0,len(tokens)-3):
             if ((tokens[i][1]== "JJ" or tokens[i][1] == "JJR" or tokens[i][1] == "JJS") and (tokens[i+2][1]== "JJ" or tokens[i+2][1] == "JJR" or tokens[i+2][1] == "JJS")):
                 if (tokens[i+1][0] == "and"):
+                    print tokens[i][0]
                     conj.write(tokens[i][0]+ " " + tokens[i+2][0] + " " + tokens[i+1][0] + "\n")
-                    ands.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
+                    #ands.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
                 elif (tokens[i+1][0] == "or"):
                     conj.write(tokens[i][0]+ " " + tokens[i+2][0] + " " + tokens[i+1][0] + "\n")
-                    ors.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
+                    #ors.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
                 elif (tokens[i+1][0] == "but"+ "\n"):
                     conj.write(tokens[i][0]+ " " + tokens[i+2][0] + " " + tokens[i+1][0] + "\n")
-                    buts.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
+                    #buts.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
                 elif (tokens[i+1][0] == "either-or"):
                     conj.write(tokens[i][0]+ " " + tokens[i+2][0] + " " + tokens[i+1][0] + "\n")
-                    eor.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
+                    #eor.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
                 elif (tokens[i+1][0] == "neither-nor"):
                     conj.write(tokens[i][0]+ " " + tokens[i+2][0] + " " + tokens[i+1][0] + "\n")
-                    nor.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
-
-f = open('words2.txt', 'w')
-list1 = []
-for word in sc.tagged_sents():
-    for w in word:
-        if(w[1] == "JJ" or w[1] == "JJR" or w[1] == "JJS" or w[1] == "JJT"):
-            list1.append(w[0])
-counts = Counter(list1)
-d = dict(counts)
-
-for n in d:
-    if( d[n] >= 15):
-        f.write(n+" \n")
-f.close()
+                    #nor.write(tokens[i][0]+ " " + tokens[i+2][0]+ "\n")
+
+
+
+
+def doBrown():
+    f = open('movieconj.txt', 'w')
+    list1 = []
+    for word in sc.tagged_sents():
+        for w in word:
+            if(w[1] == "JJ" or w[1] == "JJR" or w[1] == "JJS" or w[1] == "JJT"):
+                list1.append(w[0])
+    counts = Counter(list1)
+    d = dict(counts)
+
+    for n in d:
+        if( d[n] >= 15):
+            f.write(n+" \n")
+    f.close()
+
+genConj()