statsample-optimization 2.0.3-x86-linux

data/History.txt

@@ -0,0 +1,8 @@
+=== 2.0.3 / 2010-06-14
+* All extensions dependencies of statsample moved to statsample-optimization
+=== 2.0.0 / 2009-08-21
+ * Uses rcov internal configuration
+=== 1.0.0 / 2009-08-02
+
+ * Birthday!
+

data/Manifest.txt

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

data/README.txt

@@ -0,0 +1,30 @@
+= Statsample (optimization package)
+
+http://rubyforge.org/projects/ruby-statsample/
+
+== DESCRIPTION:
+
+Install gsl, statistics2 and provides a C extension to 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 +1,23 @@
+#!/usr/bin/ruby
+# -*- ruby -*-
+
+require 'rubygems'
+require 'rake/extensiontask'
+require 'hoe'
+Hoe.plugin :git
+
+task "test" => ["lib/statsamplert.so"]
+spec=Hoe.spec 'statsample-optimization' do
+  self.version="2.0.3"
+  self.spec_extras[:extensions] = ["ext/statsamplert/extconf.rb"]
+  self.rubyforge_name = 'ruby-statsample'
+  self.developer('Claudio Bustos', 'clbustos_at_gmail.com')
+  self.extra_deps << ["statsample","~>0.12.0"] << ["statistics2", "~>0.54"] << ["gsl", "~>1.12.109"]
+  self.extra_deps  << ["rake-compiler"]
+
+end
+
+Rake::ExtensionTask.new('statsamplert',spec.spec)
+
+
+# vim: syntax=ruby

data/ext/statsamplert/extconf.rb

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

data/ext/statsamplert/statsamplert.c

@@ -0,0 +1,130 @@
+#include <ruby.h>
+/**
+* :stopdoc:
+*/
+void Init_statsamplert();
+VALUE statsample_frequencies(VALUE self, VALUE data);
+VALUE statsample_set_valid_data_intern(VALUE self, VALUE vector);
+VALUE statsample_case_as_hash(VALUE self, VALUE ds, VALUE index);
+VALUE statsample_case_as_array(VALUE self, VALUE ds, VALUE index);
+void Init_statsamplert()
+{
+	VALUE mStatsample;
+    VALUE mSTATSAMPLE__;
+	ID id_statsample;
+	ID id_STATSAMPLE__;
+    id_statsample   = rb_intern("Statsample");
+    id_STATSAMPLE__ = rb_intern("STATSAMPLE__");
+
+    if(rb_const_defined(rb_cObject, id_statsample)) {
+		mStatsample = rb_const_get(rb_cObject, id_statsample);
+	 } else {
+		mStatsample = rb_define_module("Statsample"); 
+	 }
+    if(rb_const_defined(mStatsample, id_STATSAMPLE__)) {
+		mSTATSAMPLE__ = rb_const_get(mStatsample, id_STATSAMPLE__);
+	 } else {
+		mSTATSAMPLE__ = rb_define_module_under(mStatsample, "STATSAMPLE__"); 
+	 }
+     
+     rb_define_const(mStatsample, "OPTIMIZED",Qtrue);
+    rb_define_module_function(mSTATSAMPLE__,"frequencies",statsample_frequencies,1);
+    rb_define_module_function(mSTATSAMPLE__,"set_valid_data_intern", statsample_set_valid_data_intern, 1);
+    rb_define_module_function(mSTATSAMPLE__,"case_as_hash",statsample_case_as_hash,2);
+    rb_define_module_function(mSTATSAMPLE__,"case_as_array",statsample_case_as_array,2);
+
+}
+
+VALUE statsample_set_valid_data_intern(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;
+}
+/**
+* Retuns frequencies for an array as a hash, with 
+* keys as items and values as number of items
+*/
+VALUE statsample_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 statsample_case_as_hash(VALUE self, VALUE ds,VALUE index) {
+    VALUE vector,data,key;
+    VALUE fields=rb_iv_get(ds,"@fields");
+    VALUE vectors=rb_iv_get(ds,"@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 statsample_case_as_array(VALUE self, VALUE ds, VALUE index) {
+    VALUE vector,data,key;
+    VALUE fields=rb_iv_get(ds,"@fields");
+    VALUE vectors=rb_iv_get(ds,"@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 +1,43 @@
+$:.unshift(File.dirname(__FILE__)+"/lib")
+require "test/unit"
+#require "statsample"
+require "statsamplert"
+require "statsample"
+class TestRubyStatsampleOpt < Test::Unit::TestCase
+  def test_base
+    assert(Statsample::OPTIMIZED,true)
+  end
+  def test_frequencies
+    assert(Statsample::STATSAMPLE__.respond_to?(:frequencies))
+    v=[1,1,2].to_vector
+    exp={1=>2,2=>1}
+    assert_equal(exp,Statsample::STATSAMPLE__.frequencies(v.data))
+    assert_equal(v._frequencies, v.frequencies)
+  end
+  def test_set_valid_data
+    assert(Statsample::STATSAMPLE__.respond_to?(:set_valid_data_intern))
+    v=[2,3,4].to_vector
+    v.add(5)
+    assert_equal([2,3,4,5], v.valid_data)
+    v.add(nil,false)
+    assert_equal([2,3,4,5], v.valid_data)
+    assert_equal([2,3,4,5,nil], v.data)
+  end
+  def test_case_as_array
+    assert(Statsample::STATSAMPLE__.respond_to?(:case_as_array))
+    a=[1,2,3].to_vector(:scale)
+    b=[4,5,6].to_vector(:scale)
+    ds={"a"=>a,"b"=>b}.to_dataset
+    assert_equal([1,4],Statsample::STATSAMPLE__.case_as_array(ds,0))
+    assert_equal([2,5],Statsample::STATSAMPLE__.case_as_array(ds,1))
+    assert_equal([3,6],Statsample::STATSAMPLE__.case_as_array(ds,2))
+  end
+  def test_case_as_hash
+    assert(Statsample::STATSAMPLE__.respond_to?(:case_as_hash))
+    a=[1,2,3].to_vector(:scale)
+    b=[4,5,6].to_vector(:scale)
+    ds={"a"=>a,"b"=>b}.to_dataset
+    assert_equal({"a"=>1,"b"=>4},Statsample::STATSAMPLE__.case_as_hash(ds,0))
+  end
+
+end

metadata

@@ -0,0 +1,160 @@
+--- !ruby/object:Gem::Specification 
+name: statsample-optimization
+version: !ruby/object:Gem::Version 
+  hash: 9
+  prerelease: false
+  segments: 
+  - 2
+  - 0
+  - 3
+  version: 2.0.3
+platform: x86-linux
+authors: 
+- Claudio Bustos
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-06-19 00:00:00 -04:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: statsample
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 47
+        segments: 
+        - 0
+        - 12
+        - 0
+        version: 0.12.0
+  type: :runtime
+  version_requirements: *id001
+- !ruby/object:Gem::Dependency 
+  name: statistics2
+  prerelease: false
+  requirement: &id002 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 103
+        segments: 
+        - 0
+        - 54
+        version: "0.54"
+  type: :runtime
+  version_requirements: *id002
+- !ruby/object:Gem::Dependency 
+  name: gsl
+  prerelease: false
+  requirement: &id003 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ~>
+      - !ruby/object:Gem::Version 
+        hash: 253
+        segments: 
+        - 1
+        - 12
+        - 109
+        version: 1.12.109
+  type: :runtime
+  version_requirements: *id003
+- !ruby/object:Gem::Dependency 
+  name: rake-compiler
+  prerelease: false
+  requirement: &id004 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id004
+- !ruby/object:Gem::Dependency 
+  name: hoe
+  prerelease: false
+  requirement: &id005 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 21
+        segments: 
+        - 2
+        - 6
+        - 1
+        version: 2.6.1
+  type: :development
+  version_requirements: *id005
+description: |-
+  Install gsl, statistics2 and provides a C extension to 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: []
+
+extra_rdoc_files: 
+- History.txt
+- Manifest.txt
+- README.txt
+files: 
+- History.txt
+- Manifest.txt
+- README.txt
+- Rakefile
+- ext/statsamplert/extconf.rb
+- ext/statsamplert/statsamplert.c
+- test/test_statsample_optimization.rb
+- lib/statsamplert.so
+has_rdoc: true
+homepage: http://rubyforge.org/projects/ruby-statsample/
+licenses: []
+
+post_install_message: 
+rdoc_options: 
+- --main
+- README.txt
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: ruby-statsample
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Install gsl, statistics2 and provides a C extension to optimize the following methods  * Vector#frecuencies * Vector#set_valid_data * Dataset#case_as_hash * Dataset#case_as_array
+test_files: 
+- test/test_statsample_optimization.rb