statsample-optimization 1.0.0

data/History.txt

@@ -0,0 +1,6 @@
+=== 1.0.0 / 2009-08-02
+
+* 1 major enhancement
+
+  * Birthday!
+

data/Manifest.txt

@@ -0,0 +1,7 @@
+History.txt
+Manifest.txt
+README.txt
+Rakefile
+ext/statsample/extconf.rb
+ext/statsample/optimization.c
+test/test_statsample_optimization.rb

data/README.txt

@@ -0,0 +1,31 @@
+= Statsample (optimization package)
+
+http://rubyforge.org/projects/ruby-statsample/
+
+== DESCRIPTION:
+
+Extension for statsample, that speed some methods.
+Optimize the following methods
+
+* Vector#frecuencies
+* Vector#set_valid_data
+* Dataset#case_as_hash
+* Dataset#case_as_array
+
+
+
+== SYNOPSIS:
+Only require statsample. The module detects and use the extensions
+  
+
+== REQUIREMENTS:
+
+* Statsample
+
+== INSTALL:
+
+sudo gem install statsample-optimization
+
+== LICENSE:
+
+GPL-2

data/Rakefile

@@ -0,0 +1,36 @@
+#!/usr/bin/ruby
+# -*- ruby -*-
+
+require 'rubygems'
+require 'hoe'
+
+EXT = "ext/statsample/optimization.#{Config::CONFIG['DLEXT']}"  
+
+task :test => [EXT]
+
+file "ext/statsample/Makefile" => ["ext/statsample/extconf.rb"] do |t|
+    Dir.chdir "ext/statsample" do
+     system %(ruby extconf.rb)
+    end
+
+end
+file EXT => ["ext/statsample/Makefile", "ext/statsample/optimization.c"] do       
+	puts "Compiling"
+  Dir.chdir "ext/statsample" do
+    system %(make)
+    end
+end
+
+
+
+Hoe.spec 'statsample-optimization' do |p|
+  p.version="1.0.0"
+  p.rubyforge_name = 'ruby-statsample'
+  p.developer('Claudio Bustos', 'clbustos_at_gmail.com')
+  p.spec_extras[:extensions] = ["ext/statsample/extconf.rb"]
+  p.extra_deps << "statsample"
+  p.clean_globs << EXT
+  p.clean_globs << EXT << "ext/statsample/*.o" << "ext/statsample/*.so" << "ext/statsample/Makefile"
+end
+
+# vim: syntax=ruby

data/ext/statsample/extconf.rb

@@ -0,0 +1,3 @@
+require "mkmf"
+$CFLAGS+=" -Wall "
+create_makefile("optimization")

data/ext/statsample/optimization.c

@@ -0,0 +1,119 @@
+#include <ruby.h>
+/**
+* :stopdoc:
+*/
+void Init_optimization();
+VALUE nominal_frequencies(VALUE self);
+VALUE rubyss_frequencies(VALUE self, VALUE data);
+VALUE rubyss_set_valid_data(VALUE self, VALUE vector);
+VALUE dataset_case_as_hash(VALUE self, VALUE index);
+VALUE dataset_case_as_array(VALUE self, VALUE index);
+void Init_optimization()
+{
+    VALUE mRubySS = rb_define_module("Statsample"); 
+
+    VALUE cNominal = rb_define_class_under(mRubySS,"Nominal",rb_cObject);
+    VALUE cDataset = rb_define_class_under(mRubySS,"Dataset",rb_cObject);
+    
+    rb_define_const(mRubySS,"OPTIMIZED",Qtrue);
+    rb_define_module_function(mRubySS,"_frequencies",rubyss_frequencies,1);
+    rb_define_module_function(mRubySS,"_set_valid_data",rubyss_set_valid_data,1);
+    rb_define_method(cNominal,"frequencies",nominal_frequencies,0);
+    rb_define_method(cDataset,"case_as_hash",dataset_case_as_hash,1);
+    rb_define_method(cDataset,"case_as_array",dataset_case_as_array,1);
+
+}
+
+VALUE rubyss_set_valid_data(VALUE self, VALUE vector) {
+/** Emulate
+
+@data.each do |n|
+				if is_valid? n
+                    @valid_data.push(n)
+                    @data_with_nils.push(n)
+				else
+                    @data_with_nils.push(nil)
+                    @missing_data.push(n)
+				end
+			end
+            @has_missing_data=@missing_data.size>0
+            */
+    VALUE data=rb_iv_get(vector,"@data");
+    VALUE valid_data=rb_iv_get(vector,"@valid_data");
+    VALUE data_with_nils=rb_iv_get(vector,"@data_with_nils");
+    VALUE missing_data=rb_iv_get(vector,"@missing_data");
+    VALUE missing_values=rb_iv_get(vector,"@missing_values");
+//    VALUE has_missing_data=rb_iv_get(vector,"@has_missing_data");
+    long len=RARRAY_LEN(data);
+    long i;
+    VALUE val;
+    for(i=0;i<len;i++) {
+        val=rb_ary_entry(data,i);
+        if(val==Qnil || rb_ary_includes(missing_values,val)) {
+            rb_ary_push(missing_data,val);
+            rb_ary_push(data_with_nils,Qnil);
+        } else {
+            rb_ary_push(valid_data,val);
+            rb_ary_push(data_with_nils,val);
+        }
+    }
+    rb_iv_set(vector,"@has_missing_data",(RARRAY_LEN(missing_data)>0) ? Qtrue : Qfalse);
+    return Qnil;
+}
+VALUE rubyss_frequencies(VALUE self, VALUE data) {
+    VALUE h;
+    VALUE val;
+     long len;
+    long i;
+
+	Check_Type(data,T_ARRAY);
+     h=rb_hash_new();
+
+	len=RARRAY_LEN(data);
+    for(i=0;i<len;i++) {
+        val=rb_ary_entry(data,i);
+        if(rb_hash_aref(h,val)==Qnil) {
+            rb_hash_aset(h,val,INT2FIX(1));
+        } else {
+            long antiguo=FIX2LONG(rb_hash_aref(h,val));
+            rb_hash_aset(h,val,LONG2FIX(antiguo+1));
+        }
+    }
+    return h;
+}
+
+VALUE nominal_frequencies(VALUE self) {
+    VALUE data=rb_iv_get(self,"@data");
+    return rubyss_frequencies(self,data);
+}
+VALUE dataset_case_as_hash(VALUE self, VALUE index) {
+    VALUE vector,data,key;
+    VALUE fields=rb_iv_get(self,"@fields");
+    VALUE vectors=rb_iv_get(self,"@vectors");
+    VALUE h=rb_hash_new();
+    long len=RARRAY_LEN(fields);
+    long i;
+    for(i=0;i<len;i++) {
+        key=rb_ary_entry(fields,i);
+        vector=rb_hash_aref(vectors,key);
+        data=rb_iv_get(vector,"@data");
+        rb_hash_aset(h,key,rb_ary_entry(data,NUM2LONG(index)));
+    }
+    return h;
+}
+VALUE dataset_case_as_array(VALUE self, VALUE index) {
+    VALUE vector,data,key;
+    VALUE fields=rb_iv_get(self,"@fields");
+    VALUE vectors=rb_iv_get(self,"@vectors");
+    VALUE ar=rb_ary_new();
+    long len=RARRAY_LEN(fields);
+    long i;
+    for(i=0;i<len;i++) {
+        key=rb_ary_entry(fields,i);
+        vector=rb_hash_aref(vectors,key);
+        data=rb_iv_get(vector,"@data");
+        rb_ary_push(ar,rb_ary_entry(data,NUM2LONG(index)));
+    }
+    return ar;
+}
+

data/test/test_statsample_optimization.rb

@@ -0,0 +1,16 @@
+$:.unshift(File.dirname(__FILE__)+"/ext")
+require "test/unit"
+require "statsample"
+require "statsample/optimization"
+
+class TestRubyStatsampleOpt < Test::Unit::TestCase
+    def test_base
+        assert(Statsample::OPTIMIZED,true)
+    end
+    def test_frequencies
+        assert(Statsample.respond_to?(:_frequencies))
+        v=[1,1,2].to_vector
+        exp={1=>2,2=>1}
+        assert_equal(exp,Statsample._frequencies(v.data))
+    end
+end

metadata

@@ -0,0 +1,91 @@
+--- !ruby/object:Gem::Specification 
+name: statsample-optimization
+version: !ruby/object:Gem::Version 
+  version: 1.0.0
+platform: ruby
+authors: 
+- Claudio Bustos
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2009-08-03 00:00:00 -04:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: statsample
+  type: :runtime
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: "0"
+    version: 
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  type: :development
+  version_requirement: 
+  version_requirements: !ruby/object:Gem::Requirement 
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        version: 2.3.2
+    version: 
+description: |-
+  Extension for statsample, that speed some methods.
+  Optimize the following methods
+  
+  * Vector#frecuencies
+  * Vector#set_valid_data
+  * Dataset#case_as_hash
+  * Dataset#case_as_array
+email: 
+- clbustos_at_gmail.com
+executables: []
+
+extensions: 
+- ext/statsample/extconf.rb
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- README.txt
+files: 
+- History.txt
+- Manifest.txt
+- README.txt
+- Rakefile
+- ext/statsample/extconf.rb
+- ext/statsample/optimization.c
+- test/test_statsample_optimization.rb
+has_rdoc: true
+homepage: http://rubyforge.org/projects/ruby-statsample/
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --main
+- README.txt
+require_paths: 
+- ext
+required_ruby_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      version: "0"
+  version: 
+requirements: []
+
+rubyforge_project: ruby-statsample
+rubygems_version: 1.3.5
+signing_key: 
+specification_version: 3
+summary: Extension for statsample, that speed some methods
+test_files: 
+- test/test_statsample_optimization.rb