From 06a270c8d3f061bc7fed062cb28605dd8c6e3a8f Mon Sep 17 00:00:00 2001 From: Patrick Simianer
Date: Tue, 29 Nov 2011 23:35:51 +0100
Subject: avg.rb lplp.rb
---
dtrain/hstreaming/avg.rb | 31 ++++++++++++
dtrain/hstreaming/lplp.rb | 112 ++++++++++++++++++++++++++-----------------
dtrain/hstreaming/red-all.rb | 26 ----------
dtrain/hstreaming/red-avg.rb | 27 -----------
4 files changed, 100 insertions(+), 96 deletions(-)
create mode 100755 dtrain/hstreaming/avg.rb
delete mode 100755 dtrain/hstreaming/red-all.rb
delete mode 100755 dtrain/hstreaming/red-avg.rb
(limited to 'dtrain')
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
+}
+
diff --git a/dtrain/hstreaming/lplp.rb b/dtrain/hstreaming/lplp.rb
index edb93e77..0ec21a46 100755
--- a/dtrain/hstreaming/lplp.rb
+++ b/dtrain/hstreaming/lplp.rb
@@ -2,15 +2,15 @@
# norms
def l0(feature_column, n)
- if feature_column.size == n then return 1 else return 0 end
+ if feature_column.size >= n then return 1 else return 0 end
end
def l1(feature_column, n=-1)
- return feature_column.reduce { |sum, i| i.abs }
+ return feature_column.map { |i| i.abs }.reduce { |sum,i| sum+i }
end
def l2(feature_column, n=-1)
- return Math.sqrt feature_column.reduce { |sum, i| i**2 }
+ return Math.sqrt feature_column.map { |i| i.abs2 }.reduce { |sum,i| sum+i }
end
def linfty(feature_column, n=-1)
@@ -18,7 +18,7 @@ def linfty(feature_column, n=-1)
end
# stats
-def M(feature_column, n)
+def median(feature_column, n)
return feature_column.concat(0.step(n-feature_column.size-1).map{|i|0}).sort[feature_column.size/2]
end
@@ -27,22 +27,73 @@ def mean(feature_column, n)
end
# selection
-def select_k(weights, normfn, n, k=10000)
- weights.sort{|a,b| normfn.call(b[1], n) <=> normfn.call(a[1], n)}.each { |p|
+def select_k(weights, norm_fun, n, k=10000)
+ weights.sort{|a,b| norm_fun.call(b[1], n) <=> norm_fun.call(a[1], n)}.each { |p|
puts "#{p[0]}\t#{mean(p[1], n)}"
k -= 1
if k == 0 then break end
}
end
-def cut(weights, normfn, n, epsilon=0.0001)
+def cut(weights, norm_fun, n, epsilon=0.0001)
weights.each { |k,v|
- if normfn.call(v).abs > epsilon
+ if norm_fun.call(v, n).abs > epsilon
puts "#{k}\t#{mean(v, n)}"
end
}
end
+# test
+def _test()
+ puts
+ w = {}
+ w["a"] = [1, 2, 3]
+ w["b"] = [1, 2]
+ w["c"] = [66]
+ w["d"] = [10, 20, 30]
+ n = 3
+ puts w.to_s
+ puts
+ puts "select_k"
+ puts "l0 expect ad"
+ select_k(w, method(:l0), n, 2)
+ puts "l1 expect cd"
+ select_k(w, method(:l1), n, 2)
+ puts "l2 expect c"
+ select_k(w, method(:l2), n, 1)
+ puts
+ puts "cut"
+ puts "l1 expect cd"
+ cut(w, method(:l1), n, 7)
+ puts
+ puts "median"
+ a = [1,2,3,4,5]
+ puts a.to_s
+ puts median(a, 5)
+ puts
+ puts "#{median(a, 7)} <- that's because we add missing 0s:"
+ puts a.concat(0.step(7-a.size-1).map{|i|0}).to_s
+ puts
+ puts "mean expect bc"
+ w.clear
+ w["a"] = [2]
+ w["b"] = [2.1]
+ w["c"] = [2.2]
+ cut(w, method(:mean), 1, 2.05)
+ exit
+end
+_test()
+
+# actually do something
+def usage()
+ puts "lplp.rb