Renumber to make the flow better

06-code-golf/README.md

@@ -0,0 +1,11 @@
+Style #4
+==============================
+
+Constraints:
+
+- As few lines of code as possible
+
+Possible names:
+
+- Code golf
+- Try hard

06-code-golf/tf-06-1.py

@@ -0,0 +1,8 @@
+#!/usr/bin/env python
+import re, string, sys
+
+stops = set(open("../stop_words.txt").read().split(",") + list(string.ascii_lowercase))
+words = [x.lower() for x in re.split("[^a-zA-Z]+", open(sys.argv[1]).read()) if len(x) > 0 and x.lower() not in stops]
+unique_words = list(set(words))
+unique_words.sort(lambda x, y: cmp(words.count(y), words.count(x)))
+print "\n".join(["%s - %s" % (x, words.count(x)) for x in unique_words[:25]])

06-code-golf/tf-06-pn.py

@@ -0,0 +1,11 @@
+#!/usr/bin/env python
+# My golf score is slightly lower!  
+# Best wishes, Peter Norvig
+
+import re, sys, collections
+
+stopwords = set(open('../stop_words.txt').read().split(','))
+words = re.findall('[a-z]{2,}', open(sys.argv[1]).read().lower())
+counts = collections.Counter(w for w in words if w not in stopwords)
+for (w, c) in counts.most_common(25):
+    print w, '-', c

06-code-golf/tf-06.py

@@ -0,0 +1,6 @@
+#!/usr/bin/env python
+import heapq, re, sys
+
+words = re.findall("[a-z]{2,}", open(sys.argv[1]).read().lower())
+for w in heapq.nlargest(25, set(words) - set(open("../stop_words.txt").read().split(",")), words.count):
+    print w, "-", words.count(w)

06-code-golf/tf-06.scala

@@ -0,0 +1,43 @@
+/**
+ Faithful conversion of tf-04.py to scala, avg execution time 5.2 seconds
+ $ time scala tf04a ../pride-and-prejudice.txt
+(Mr,786)
+(Elizabeth,635)
+(very,473)
+(Darcy,417)
+(such,378)
+(Mrs,343)
+(much,325)
+(more,325)
+(Bennet,322)
+(Bingley,305)
+(Jane,295)
+(Miss,281)
+(one,261)
+(know,239)
+(herself,227)
+(before,225)
+(sister,218)
+(soon,214)
+(never,214)
+(though,212)
+(think,210)
+(time,203)
+(now,197)
+(Wickham,194)
+(well,188)
+
+real  0m5.237s
+
+*/
+object tf04 extends App {
+  def l(f:String) = io.Source.fromFile(f).getLines.mkString(",")
+  val s = l("../stop_words.txt").split(",") ++ (1 to 26).map(i=>String.valueOf(Character.toChars(96+i)))
+
+  l(args(0)).split("[^a-zA-Z]+").filter(x => !s.contains(x.toLowerCase))
+  .distinct
+  .map(u=> (u,l(args(0)).split("[^a-zA-Z]+").filter(x => !s.contains(x.toLowerCase)).count(_==u)))
+  .sortBy(-_._2)
+  .take(25)
+  .foreach(println)
+}