Put ngrams in ordered dict

Author: Ryan Mitchell

chapter7/2-clean2grams.py

@@ -2,6 +2,7 @@
 from bs4 import BeautifulSoup
 import re
 import string
+from collections import OrderedDict
 
 def cleanInput(input):
     input = re.sub('\n+', " ", input)
@@ -19,14 +20,22 @@ def cleanInput(input):
 
 def getNgrams(input, n):
     input = cleanInput(input)
-    output = []
+    output = dict()
     for i in range(len(input)-n+1):
-        output.append(input[i:i+n])
+        newNGram = " ".join(input[i:i+n])
+        if newNGram in output:
+            output[newNGram] += 1
+        else:
+            output[newNGram] = 1
     return output
 
 html = urlopen("http://en.wikipedia.org/wiki/Python_(programming_language)")
 bsObj = BeautifulSoup(html)
 content = bsObj.find("div", {"id":"mw-content-text"}).get_text()
+#ngrams = getNgrams(content, 2)
+#print(ngrams)
+#print("2-grams count is: "+str(len(ngrams)))
+
 ngrams = getNgrams(content, 2)
-print(ngrams)
-print("2-grams count is: "+str(len(ngrams)))
+ngrams = OrderedDict(sorted(ngrams.items(), key=lambda t: t[1], reverse=True))
+print(ngrams)