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
+}
+