From 5339c8fdb1df47a2dab688bf1469e02a28eb0c89 Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Fri, 4 Nov 2016 17:04:12 +0100
Subject: rename, remove non nlp stuff

---
 convert-to-svm-light-format             | 22 ----------------------
 dense-features.txt                      | 12 ------------
 fake-svm-light                          | 14 --------------
 mem-usage                               | 11 -----------
 ruby-eval                               |  6 ------
 svm-light-fmt-conv                      | 22 ++++++++++++++++++++++
 svm-light-fmt-fake                      | 14 ++++++++++++++
 take-mem                                | 18 ------------------
 test/filter-features/dense-features.txt | 12 ++++++++++++
 9 files changed, 48 insertions(+), 83 deletions(-)
 delete mode 100755 convert-to-svm-light-format
 delete mode 100644 dense-features.txt
 delete mode 100755 fake-svm-light
 delete mode 100755 mem-usage
 delete mode 100755 ruby-eval
 create mode 100755 svm-light-fmt-conv
 create mode 100755 svm-light-fmt-fake
 delete mode 100755 take-mem
 create mode 100644 test/filter-features/dense-features.txt

diff --git a/convert-to-svm-light-format b/convert-to-svm-light-format
deleted file mode 100755
index a9ce98f..0000000
--- a/convert-to-svm-light-format
+++ /dev/null
@@ -1,22 +0,0 @@
-#!/usr/bin/env ruby
-
-require 'zipf'
-
-fd = Marshal.load ReadFile.read ARGV[0]
-d = fd.size
-
-not_quiet = ARGV[1]
-train = []
-l_i = 1
-while line = STDIN.gets
-  STDERR.write "#{l_i}\n" if l_i%1000==0&&not_quiet
-  s = []
-  line.split.each { |i|
-    k,w = i.split '=', 2
-    s << [fd[k]+1, w.to_f]
-  }
-  s.sort_by! { |i| i.first }
-  puts "+1 #{s.map{|i| "#{i.first}:#{i[1]}" }.join(' ')}"
-  l_i+= 1
-end
-
diff --git a/dense-features.txt b/dense-features.txt
deleted file mode 100644
index daae8d1..0000000
--- a/dense-features.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-CountEF
-EgivenFCoherent
-Glue
-IsSingletonF
-IsSingletonFE
-LanguageModel
-LanguageModel_OOV
-MaxLexFgivenE
-MaxLexEgivenF
-PassThrough
-SampleCountF
-WordPenalty
diff --git a/fake-svm-light b/fake-svm-light
deleted file mode 100755
index eb074c1..0000000
--- a/fake-svm-light
+++ /dev/null
@@ -1,14 +0,0 @@
-#!/usr/bin/env ruby
-
-while line = STDIN.gets
-  a = line.split
-  label = a.shift.to_f
-  label *= -1
-  a.map! { |i|
-    k,v = i.split ":"
-    v = v.to_f*-1
-    "#{k}:#{v}"
-  }
-  puts "#{label} #{a.join ' '}"
-end
-
diff --git a/mem-usage b/mem-usage
deleted file mode 100755
index 5c2104f..0000000
--- a/mem-usage
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/bin/bash
-
-"$@" &
-pid=$! peak=0
-while true; do
-  sleep 1
-  sample="$(ps -o rss= $pid 2> /dev/null)" || break
-  let peak='sample > peak ? sample : peak'
-done
-echo "$(( ${peak%% *} / 1024)) m"
-
diff --git a/ruby-eval b/ruby-eval
deleted file mode 100755
index fe0d181..0000000
--- a/ruby-eval
+++ /dev/null
@@ -1,6 +0,0 @@
-#!/usr/bin/env ruby
-
-while line = STDIN.gets
-  puts "#{eval line}"
-end
-
diff --git a/svm-light-fmt-conv b/svm-light-fmt-conv
new file mode 100755
index 0000000..a9ce98f
--- /dev/null
+++ b/svm-light-fmt-conv
@@ -0,0 +1,22 @@
+#!/usr/bin/env ruby
+
+require 'zipf'
+
+fd = Marshal.load ReadFile.read ARGV[0]
+d = fd.size
+
+not_quiet = ARGV[1]
+train = []
+l_i = 1
+while line = STDIN.gets
+  STDERR.write "#{l_i}\n" if l_i%1000==0&&not_quiet
+  s = []
+  line.split.each { |i|
+    k,w = i.split '=', 2
+    s << [fd[k]+1, w.to_f]
+  }
+  s.sort_by! { |i| i.first }
+  puts "+1 #{s.map{|i| "#{i.first}:#{i[1]}" }.join(' ')}"
+  l_i+= 1
+end
+
diff --git a/svm-light-fmt-fake b/svm-light-fmt-fake
new file mode 100755
index 0000000..eb074c1
--- /dev/null
+++ b/svm-light-fmt-fake
@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+while line = STDIN.gets
+  a = line.split
+  label = a.shift.to_f
+  label *= -1
+  a.map! { |i|
+    k,v = i.split ":"
+    v = v.to_f*-1
+    "#{k}:#{v}"
+  }
+  puts "#{label} #{a.join ' '}"
+end
+
diff --git a/take-mem b/take-mem
deleted file mode 100755
index 57289a5..0000000
--- a/take-mem
+++ /dev/null
@@ -1,18 +0,0 @@
-#!/usr/bin/env python
-
-import sys
-import time
-
-if len(sys.argv) != 2:
-    print "usage: fillmem <number-of-megabytes>"
-    sys.exit()
-
-count = int(sys.argv[1])
-
-megabyte = (0,) * (1024 * 1024 / 8)
-
-data = megabyte * count
-
-while True:
-    time.sleep(1)
-
diff --git a/test/filter-features/dense-features.txt b/test/filter-features/dense-features.txt
new file mode 100644
index 0000000..daae8d1
--- /dev/null
+++ b/test/filter-features/dense-features.txt
@@ -0,0 +1,12 @@
+CountEF
+EgivenFCoherent
+Glue
+IsSingletonF
+IsSingletonFE
+LanguageModel
+LanguageModel_OOV
+MaxLexFgivenE
+MaxLexEgivenF
+PassThrough
+SampleCountF
+WordPenalty
-- 
cgit v1.2.3