summaryrefslogtreecommitdiff
path: root/training/dtrain/hstreaming/avg.rb
diff options
context:
space:
mode:
authorPatrick Simianer <p@simianer.de>2013-03-15 10:29:13 +0100
committerPatrick Simianer <p@simianer.de>2013-03-15 10:29:13 +0100
commit2b4b3adc764085bccc6ddbde96b8cc7ba4287a9f (patch)
treebbe72e5e3f425d2389b1f037a83aefd2c40269eb /training/dtrain/hstreaming/avg.rb
parent08d5de939f85075fc1569ddfa545b5d815231c3f (diff)
removed hadoop/hstreaming mode
Diffstat (limited to 'training/dtrain/hstreaming/avg.rb')
-rwxr-xr-xtraining/dtrain/hstreaming/avg.rb32
1 files changed, 0 insertions, 32 deletions
diff --git a/training/dtrain/hstreaming/avg.rb b/training/dtrain/hstreaming/avg.rb
deleted file mode 100755
index 2599c732..00000000
--- a/training/dtrain/hstreaming/avg.rb
+++ /dev/null
@@ -1,32 +0,0 @@
-#!/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
-}
-