diff options
author | Patrick Simianer <p@simianer.de> | 2011-11-29 23:35:51 +0100 |
---|---|---|
committer | Patrick Simianer <p@simianer.de> | 2011-11-29 23:35:51 +0100 |
commit | 89cf0569972b2eaf891a5d6d87b530aa52973d11 (patch) | |
tree | d237e58d8205da99013ed9964d34a2e34e3e1ece /dtrain/hstreaming/avg.rb | |
parent | af6c83df01d105a32c7b2ac346a4225e28dd6dfc (diff) |
avg.rb lplp.rb
Diffstat (limited to 'dtrain/hstreaming/avg.rb')
-rwxr-xr-x | dtrain/hstreaming/avg.rb | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/dtrain/hstreaming/avg.rb b/dtrain/hstreaming/avg.rb new file mode 100755 index 00000000..e0899144 --- /dev/null +++ b/dtrain/hstreaming/avg.rb @@ -0,0 +1,31 @@ +# avg.rb + +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 + puts "# shard count: #{shard_count.to_i}" + else + puts "#{k}\t#{w[k]/shard_count}" + puts "# #{c[k]}" + end +} + |