From 1b8181bf0d6e9137e6b9ccdbe414aec37377a1a9 Mon Sep 17 00:00:00 2001
From: Chris Dyer <cdyer@allegro.clab.cs.cmu.edu>
Date: Sun, 18 Nov 2012 13:35:42 -0500
Subject: major restructure of the training code

---
 training/dtrain/hstreaming/avg.rb | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100755 training/dtrain/hstreaming/avg.rb

(limited to 'training/dtrain/hstreaming/avg.rb')

diff --git a/training/dtrain/hstreaming/avg.rb b/training/dtrain/hstreaming/avg.rb
new file mode 100755
index 00000000..2599c732
--- /dev/null
+++ b/training/dtrain/hstreaming/avg.rb
@@ -0,0 +1,32 @@
+#!/usr/bin/env ruby
+# first arg may be an int of custom shard count
+
+shard_count_key = "__SHARD_COUNT__"
+
+STDIN.set_encoding 'utf-8'
+STDOUT.set_encoding 'utf-8'
+
+w = {}
+c = {}
+w.default = 0
+c.default = 0
+while line = STDIN.gets
+  key, val = line.split /\s/
+  w[key] += val.to_f
+  c[key] += 1
+end
+
+if ARGV.size == 0
+  shard_count = w["__SHARD_COUNT__"]
+else
+  shard_count = ARGV[0].to_f
+end
+w.each_key { |k|
+  if k == shard_count_key
+    next
+  else
+    puts "#{k}\t#{w[k]/shard_count}"
+    #puts "# #{c[k]}"
+  end
+}
+
-- 
cgit v1.2.3