Massive renaming!

07-code-golf/README.md

@@ -0,0 +1,11 @@
+Style #6
+==============================
+
+Constraints:
+
+- As few lines of code as possible
+
+Possible names:
+
+- Code golf
+- Try hard

07-code-golf/tf-07-1.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(key=lambda x: words.count(x), reverse=True)
+print("\n".join(["%s - %s" % (x, words.count(x)) for x in unique_words[:25]]))

07-code-golf/tf-07-bm.py

@@ -0,0 +1,2 @@
+from functools import reduce
+print (reduce(lambda string, tup: string + tup[0] + ' - ' + str(tup[1]) + '\n', sorted( filter(lambda tup: tup[0] not in open(__import__('os').path.join(__import__('os').path.dirname(__file__), '..', 'stop_words.txt')).read().lower().split(','),  reduce(lambda word_dict, word: word_dict if (word_dict.__setitem__(word, word_dict.get(word, 0) + 1) if True else None) else word_dict, filter(lambda word: len(word) > 1, (''.join(map(lambda letter: ' ' if ord(letter) not in set(range(ord('a'), ord('z') + 1)) else letter, open(__import__('sys').argv[1]).read().lower()))).split()), {}).items()), key=lambda tup: tup[1], reverse=True)[0:25], '')) # hole in one?

07-code-golf/tf-07-pn.py

@@ -0,0 +1,10 @@
+#!/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)

07-code-golf/tf-07.clj

@@ -0,0 +1,9 @@
+":";exec java -cp "$HOME/.m2/repository/org/clojure/clojure/1.5.1/clojure-1.5.1.jar" clojure.main $0 $*
+
+(doseq [c (take 25 
+            (sort-by val > 
+              (frequencies
+                (remove 
+                  #(contains? (set (.split (slurp "../stop_words.txt") ",")) %)
+                  (re-seq #"[a-z]{2,}" (.toLowerCase (slurp (first *command-line-args*))))))))]
+  (println (first c) "-" (nth c 1)))

07-code-golf/tf-07.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))

07-code-golf/tf-07.rb

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+require 'set'
+
+stops = ((IO.read '../stop_words.txt').split ',').to_set
+ARGF.read.downcase.scan(/[a-z]{2,}/).each_with_object(Hash.new 0){|w,c|c[w]+=1 if not stops.member? w}.sort_by{|w,c|-c}[0,25].each{|w,c|puts "#{w} - #{c}"}
+

07-code-golf/tf-07.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)
+}