summaryrefslogtreecommitdiff
path: root/dtrain/hstreaming/avgweights.rb
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2011-09-23 20:53:15 +0200
committerPatrick Simianer <p@simianer.de>2011-09-23 20:53:15 +0200
commit9bde56ed23b4b97f8193f9f8f582f18086ff17c1 (patch)
tree83bd5687f2069405537f7f8fbdfbe208a634ca54 /dtrain/hstreaming/avgweights.rb
parent4433886ac335e6db7ded081b5ef673490ee27718 (diff)
begin refactoring
Diffstat (limited to 'dtrain/hstreaming/avgweights.rb')
-rwxr-xr-xdtrain/hstreaming/avgweights.rb27
1 files changed, 27 insertions, 0 deletions
diff --git a/dtrain/hstreaming/avgweights.rb b/dtrain/hstreaming/avgweights.rb
new file mode 100755
index 00000000..d5cfaa4d
--- /dev/null
+++ b/dtrain/hstreaming/avgweights.rb
@@ -0,0 +1,27 @@
+#!/usr/bin/env ruby1.9.1
+
+
+STDIN.set_encoding 'utf-8'
+
+#shard_count_key = "__SHARD_COUNT__"
+
+w = {}
+c = {}
+w.default = 0
+c.default = 0
+while line = STDIN.gets
+ key, val = line.split /\t/
+ w[key] += val.to_f
+ c[key] += 1.0
+end
+
+#shard_count = w["__SHARD_COUNT__"]
+
+w.each_key { |k|
+ #if k == shard_count_key then next end
+ #if k == "__bias" then next end
+ puts "#{k}\t#{w[k]/c[k]}" #{w[k]/shard_count}"
+}
+
+#puts "#{shard_count_key}\t#{w[shard_count_key]}"
+