apriori 0.2.1

data/config/hoe.rb

@@ -0,0 +1,81 @@
+require 'apriori/version'
+
+AUTHOR = 'Nate Murray'  # can also be an array of Authors
+EMAIL = "nate@natemurray.com"
+DESCRIPTION = "Ruby Apriori is a library to efficiently find item association rules within large sets of transactions."
+GEM_NAME = 'apriori' # what ppl will type to install your gem
+RUBYFORGE_PROJECT = 'apriori' # The unix name for your project
+HOMEPATH = "http://#{RUBYFORGE_PROJECT}.rubyforge.org"
+DOWNLOAD_PATH = "http://rubyforge.org/projects/#{RUBYFORGE_PROJECT}"
+EXTRA_DEPENDENCIES = [
+#  ['activesupport', '>= 1.3.1']
+  ['rake', '>= 0.0.0'],
+  ['hoe', '>= 0.0.0'], 
+  ['newgem', '>= 0.0.0'],
+  ['rubigen', '>= 0.0.0']
+]    # An array of rubygem dependencies [name, version]
+
+@config_file = "~/.rubyforge/user-config.yml"
+@config = nil
+RUBYFORGE_USERNAME = "unknown"
+def rubyforge_username
+  unless @config
+    begin
+      @config = YAML.load(File.read(File.expand_path(@config_file)))
+    rescue
+      puts <<-EOS
+ERROR: No rubyforge config file found: #{@config_file}
+Run 'rubyforge setup' to prepare your env for access to Rubyforge
+ - See http://newgem.rubyforge.org/rubyforge.html for more details
+      EOS
+      exit
+    end
+  end
+  RUBYFORGE_USERNAME.replace @config["username"]
+end
+
+
+REV = nil
+# UNCOMMENT IF REQUIRED:
+# REV = YAML.load(`svn info`)['Revision']
+VERS = Apriori::VERSION::STRING + (REV ? ".#{REV}" : "")
+RDOC_OPTS = ['--quiet', '--title', 'apriori documentation',
+    "--opname", "index.html",
+    "--line-numbers",
+    # "--exclude=ext",
+    "--main", "README",
+    "--inline-source"]
+
+class Hoe
+  def extra_deps
+    @extra_deps.reject! { |x| Array(x).first == 'hoe' }
+    @extra_deps
+  end
+end
+
+# Generate all the Rake tasks
+# Run 'rake -T' to see list of generated tasks (from gem root directory)
+$hoe = Hoe.new(GEM_NAME, VERS) do |p|
+  p.developer(AUTHOR, EMAIL)
+  p.description = DESCRIPTION
+  p.summary = DESCRIPTION
+  p.url = HOMEPATH
+  p.rubyforge_name = RUBYFORGE_PROJECT if RUBYFORGE_PROJECT
+  p.test_globs = ["test/**/test_*.rb"]
+  p.clean_globs |= ['**/.*.sw?', '*.gem', '.config', '**/.DS_Store']  #An array of file patterns to delete on clean.
+  p.rdoc_pattern = /^(lib|bin)|txt$/
+
+  # p.spec_extras = {:extensions, FileList["ext/**/extconf.rb"].to_a} # A hash of extra values to set in the gemspec.
+  p.spec_extras = {:extensions, 'Rakefile'} # A hash of extra values to set in the gemspec.
+
+  # == Optional
+  p.changes = p.paragraphs_of("History.txt", 0..1).join("\n\n")
+  p.extra_deps = EXTRA_DEPENDENCIES
+
+  end
+
+CHANGES = $hoe.paragraphs_of('History.txt', 0..1).join("\\n\\n")
+PATH    = (RUBYFORGE_PROJECT == GEM_NAME) ? RUBYFORGE_PROJECT : "#{RUBYFORGE_PROJECT}/#{GEM_NAME}"
+$hoe.remote_rdoc_dir = File.join(PATH.gsub(/^#{RUBYFORGE_PROJECT}\/?/,''), 'rdoc')
+$hoe.rsync_args = '-av --delete --ignore-errors'
+$hoe.spec.post_install_message = File.open(File.dirname(__FILE__) + "/../PostInstall.txt").read rescue ""

data/config/requirements.rb

@@ -0,0 +1,29 @@
+require 'fileutils'
+include FileUtils
+
+require 'rubygems'
+
+def check_rubygems_version
+  min_version = '1.2.0'
+  local_version = %x[gem --version].chomp
+ 
+  unless local_version >= min_version
+    puts "You need to update the RubyGems utility to #{min_version} using the following"
+    puts ""
+    puts " sudo gem update --system"
+    exit
+  end
+end
+check_rubygems_version
+
+%w[rake hoe newgem rubigen].each do |req_gem|
+  begin
+    require req_gem
+  rescue LoadError
+    puts "This Rakefile requires the '#{req_gem}' RubyGem."
+    puts "Installation: gem install #{req_gem} -y"
+    exit
+  end
+end
+
+$:.unshift(File.join(File.dirname(__FILE__), %w[.. lib]))

data/examples/01_simple_example.rb

@@ -0,0 +1,32 @@
+$:.unshift(File.dirname(__FILE__) + "/../lib")
+require 'apriori'
+
+transactions = [  %w{beer doritos},
+                  %w{apple cheese}, 
+                  %w{beer doritos}, 
+                  %w{apple cheese}, 
+                  %w{apple cheese}, 
+                  %w{apple doritos} ]
+
+rules = Apriori.find_association_rules(transactions,
+                          :min_items => 2,
+                          :max_items => 5,
+                          :min_support => 1, 
+                          :max_support => 100, 
+                          :min_confidence => 20)
+
+puts rules.join("\n")
+
+# RETURNS: 
+# doritos <- beer (33.3/2, 100.0)
+# beer <- doritos (50.0/3, 66.7)
+# apple <- doritos (50.0/3, 33.3)
+# doritos <- apple (66.7/4, 25.0)
+# apple <- cheese (50.0/3, 100.0)
+# cheese <- apple (66.7/4, 75.0)
+
+# NOTE:
+# doritos <- beer (33.3/2, 100.0)
+# means: 
+# * beer appears in 33.3% (2 total) of the transactions (the support)
+# * beer implies doritos 100% of the time (the confidence)

data/examples/02_small_file_example.rb

@@ -0,0 +1,17 @@
+$:.unshift(File.dirname(__FILE__) + "/../lib")
+require 'apriori'
+require 'benchmark'
+
+rules = nil
+results = Benchmark.measure {
+rules = Apriori.find_association_rules(File.dirname(__FILE__) + "/test_data/market_basket_basic_test.dat",
+                           :min_items => 2,
+                           :max_items => 3,
+                           :min_support => 0.01, 
+                           :min_confidence => 30)
+}
+
+puts rules.join("\n")
+puts "#{rules.size} rules generated"
+puts "Benchmarks:"
+puts results

data/examples/03_large_file_example.rb

@@ -0,0 +1,22 @@
+$:.unshift(File.dirname(__FILE__) + "/../lib")
+require 'apriori'
+require 'benchmark'
+
+# NOTE: the 'accidents.dat' file is not supplied with this gem. To download it, 
+# run: rake apriori:get_example_data 
+# or see http://fimi.cs.helsinki.fi/data/
+
+puts "This will take a little while. Hold tight..."
+
+rules = nil
+results = Benchmark.measure {
+rules = Apriori.find_association_rules(File.dirname(__FILE__) + "/test_data/accidents.dat",
+                           :min_items => 2,
+                           :max_items => 10,
+                           :min_support => 50, 
+                           :min_confidence => 80)
+}
+
+puts "#{rules.size} rules generated"
+puts "Benchmarks:"
+puts results

data/examples/test_data/market_basket_basic_test.dat

@@ -0,0 +1,9 @@
+apple 
+beer doritos
+eggs cheese
+apple cheese
+beer doritos
+apple cheese
+eggs cheese apple
+apple cheese
+apple doritos

data/ext/Apriori.c

@@ -0,0 +1,149 @@
+// Include the Ruby headers and goodies
+#include "ruby.h"
+#include "intern.h"
+#include "apriori_wrapper.h"
+
+// Defining a space for information and references about the module to be stored internally
+VALUE Apriori = Qnil;
+
+// Prototype for the initialization method - Ruby calls this, not you
+void Init_mytest();
+
+// Prototype for our method 'test1' - methods are prefixed by 'method_' here
+VALUE method_do_test_apriori(VALUE self);
+//VALUE method_test_hash_ap(VALUE self, VALUE filein, VALUE fileout, VALUE opts);
+//VALUE method_find_association_rules(VALUE self, VALUE filein, VALUE fileout, VALUE opts);
+
+VALUE method_ap_do_apriori(VALUE self, VALUE rargv); 
+
+// The initialization method for this module
+void Init_apriori_ext() {
+	Apriori = rb_define_module("Apriori");
+	rb_define_method(Apriori, "do_test_apriori",   method_do_test_apriori, 0);	
+	rb_define_method(Apriori, "do_apriori", method_ap_do_apriori, 1);
+}
+
+VALUE method_do_test_apriori(VALUE self) {
+    char *arg0 = "apriori";
+    char *arg1 = "test/sample.txt";
+    char *arg2 = "test/results.txt";
+    char *argv[3];
+    argv[0] = arg0;
+    argv[1] = arg1;
+    argv[2] = arg2;
+
+    do_apriori(3, argv);
+	int x = 10;
+	return INT2NUM(x);
+}
+
+// Our 'test1' method.. it simply returns a value of '10' for now.
+/*
+VALUE method_test_hash_ap(VALUE self, VALUE filein, VALUE fileout, VALUE opts) {
+    //VALUE s = rb_str_new2("hello");
+    VALUE s = rb_str_new2("bye");
+    VALUE val = rb_hash_aref(opts, rb_str_intern(s));
+
+    if(val != Qnil) {
+      return val;
+    } else {
+      return rb_str_new2("nope");
+    }
+}
+*/
+
+// Our 'test1' method.. it simply returns a value of '10' for now.
+/*
+VALUE method_find_association_rules(VALUE self, VALUE filein, VALUE fileout, VALUE opts) {
+    VALUE s = rb_str_new2("hello");
+    //VALUE s = rb_str_new2("bye");
+    VALUE val = rb_hash_aref(opts, rb_str_intern(s));
+
+    if(val != Qnil) {
+      return val;
+    } else {
+      return rb_str_new2("nope");
+    }
+}
+*/
+
+VALUE method_ap_do_apriori(VALUE self, VALUE rargv) {
+  char **argv; // todo, learn the best practice here
+  int i = 0;
+  VALUE ary_value;
+  // get the number of arguments
+  int ruby_argv_length = RARRAY(rargv)->len;
+  // allocate enough memory for a pointer to each char *
+  argv = malloc(ruby_argv_length * sizeof(*argv));
+
+  // copy the ruby array of strings to a c "array of strings"
+  // todo, turn this into a function
+  while((ary_value = rb_ary_shift(rargv)) != Qnil) {
+    argv[i] = malloc(strlen(STR2CSTR(ary_value)) + 1);
+    strcpy(argv[i], STR2CSTR(ary_value));
+    i++;
+  }
+  do_apriori(i, argv);
+  return Qnil;
+}
+
+/*
+VALUE better_method_ap_test_ruby_array(VALUE self, VALUE rargv) {
+  char **argv;
+  int i = 3;
+  argv = (char **)convert_rb_ary_strings_to_c_ary_strings(rargv);
+  do_apriori(i, argv);
+}
+
+char **convert_rb_ary_strings_to_c_ary_strings(VALUE rary) {
+  char **argv; // todo, learn the best practice here
+  int i = 0;
+  VALUE ary_value;
+  // get the number of arguments
+  int ruby_argv_length = RARRAY(rary)->len;
+  // allocate enough memory for a pointer to each char *
+  argv = malloc(ruby_argv_length * sizeof(*argv));
+
+  // copy the ruby array of strings to a c "array of strings"
+  // todo, turn this into a function
+  while((ary_value = rb_ary_shift(rary)) != Qnil) {
+    argv[i] = malloc(strlen(STR2CSTR(ary_value)) + 1);
+    strcpy(argv[i], STR2CSTR(ary_value));
+    fprintf(stderr, "%s\n", argv[i]);
+    i++;
+  }
+  printf("%d\n", i);
+  return argv;
+}
+*/
+
+void asdf_junk_box() {
+  /* int j; */
+  /* for(j=0; j<i; j++) { */
+  /*   fprintf(stderr, "%s\n", argv[j]); */
+  /* } */
+
+  // VALUE tmp_argv = rb_ary_new();
+  //do_apriori(i, argv);
+
+  // ok, so you need to figure out how many non-nil values you have,
+  // i guess you could just track it above.
+  // then we're good! we can feed these to the main
+
+//  for(i=0; i < NUM2INT(rb_ary_length(rargv)); i++) {
+//    VALUE argv = rb_ary_new();
+    //fprintf(stderr, STR2CSTR(rb_ary_fetch(1, 1, rargv)));
+//  }
+    // get an array of ruby strings
+    // convert it to a c array of char *'s
+    //
+    //VALUE s = rb_str_new2("bye");
+    //VALUE val = rb_hash_aref(opts, rb_str_intern(s));
+
+    /* if(val != Qnil) { */
+    /*   return val; */
+    /* } else { */
+    /*   return rb_str_new2("nope"); */
+    /* } */
+  return;
+}

data/ext/Makefile

@@ -0,0 +1,149 @@
+
+SHELL = /bin/sh
+
+#### Start of system configuration section. ####
+
+srcdir = /home/nathan/tmp/apriori/ext
+topdir = /usr/local/lib/ruby/1.8/i686-linux
+hdrdir = $(topdir)
+VPATH = $(srcdir):$(topdir):$(hdrdir)
+prefix = $(DESTDIR)/usr/local
+exec_prefix = $(prefix)
+sitedir = $(prefix)/lib/ruby/site_ruby
+rubylibdir = $(libdir)/ruby/$(ruby_version)
+docdir = $(datarootdir)/doc/$(PACKAGE)
+dvidir = $(docdir)
+datarootdir = $(prefix)/share
+archdir = $(rubylibdir)/$(arch)
+sbindir = $(exec_prefix)/sbin
+psdir = $(docdir)
+localedir = $(datarootdir)/locale
+htmldir = $(docdir)
+datadir = $(datarootdir)
+includedir = $(prefix)/include
+infodir = $(datarootdir)/info
+sysconfdir = $(prefix)/etc
+mandir = $(datarootdir)/man
+libdir = $(exec_prefix)/lib
+sharedstatedir = $(prefix)/com
+oldincludedir = $(DESTDIR)/usr/include
+pdfdir = $(docdir)
+sitearchdir = $(sitelibdir)/$(sitearch)
+bindir = $(exec_prefix)/bin
+localstatedir = $(prefix)/var
+sitelibdir = $(sitedir)/$(ruby_version)
+libexecdir = $(exec_prefix)/libexec
+
+CC = gcc
+LIBRUBY = $(LIBRUBY_A)
+LIBRUBY_A = lib$(RUBY_SO_NAME)-static.a
+LIBRUBYARG_SHARED = -Wl,-R -Wl,$(libdir) -L$(libdir) -L. 
+LIBRUBYARG_STATIC = -l$(RUBY_SO_NAME)-static
+
+RUBY_EXTCONF_H = 
+CFLAGS   =  -fPIC -g -O2 
+INCFLAGS = -I. -I$(topdir) -I$(hdrdir) -I$(srcdir)
+CPPFLAGS =   -I/home/nathan/tmp/apriori/ext/util/src -I/home/nathan/tmp/apriori/ext/math/src -I/home/nathan/tmp/apriori/ext/apriori/src 
+CXXFLAGS = $(CFLAGS) 
+DLDFLAGS =   
+LDSHARED = $(CC) -shared
+AR = ar
+EXEEXT = 
+
+RUBY_INSTALL_NAME = ruby
+RUBY_SO_NAME = ruby
+arch = i686-linux
+sitearch = i686-linux
+ruby_version = 1.8
+ruby = /usr/local/bin/ruby
+RUBY = $(ruby)
+RM = rm -f
+MAKEDIRS = mkdir -p
+INSTALL = /usr/bin/ginstall -c
+INSTALL_PROG = $(INSTALL) -m 0755
+INSTALL_DATA = $(INSTALL) -m 644
+COPY = cp
+
+#### End of system configuration section. ####
+
+preload = 
+
+libpath = $(libdir)
+LIBPATH =  -L'$(libdir)' -Wl,-R'$(libdir)'
+DEFFILE = 
+
+CLEANFILES = 
+DISTCLEANFILES = 
+
+extout = 
+extout_prefix = 
+target_prefix = 
+LOCAL_LIBS = 
+LIBS =   -ldl -lcrypt -lm   -lc
+SRCS = vecops.c nimap.c tabscan.c scform.c gamma.c chi2.c tract.c istree.c apriori_wrapper.c Apriori.c
+OBJS = /home/nathan/tmp/apriori/ext/util/src/vecops.o /home/nathan/tmp/apriori/ext/util/src/nimap.o /home/nathan/tmp/apriori/ext/util/src/tabscan.o /home/nathan/tmp/apriori/ext/util/src/scform.o /home/nathan/tmp/apriori/ext/math/src/gamma.o /home/nathan/tmp/apriori/ext/math/src/chi2.o /home/nathan/tmp/apriori/ext/apriori/src/tract.o /home/nathan/tmp/apriori/ext/apriori/src/istree.o apriori_wrapper.o Apriori.o
+TARGET = apriori_ext
+DLLIB = $(TARGET).so
+EXTSTATIC = 
+STATIC_LIB = 
+
+RUBYCOMMONDIR = $(sitedir)$(target_prefix)
+RUBYLIBDIR    = $(sitelibdir)$(target_prefix)
+RUBYARCHDIR   = $(sitearchdir)$(target_prefix)
+
+TARGET_SO     = $(DLLIB)
+CLEANLIBS     = $(TARGET).so $(TARGET).il? $(TARGET).tds $(TARGET).map
+CLEANOBJS     = *.o *.a *.s[ol] *.pdb *.exp *.bak
+
+all:		$(DLLIB)
+static:		$(STATIC_LIB)
+
+clean:
+		@-$(RM) $(CLEANLIBS) $(CLEANOBJS) $(CLEANFILES)
+
+distclean:	clean
+		@-$(RM) Makefile $(RUBY_EXTCONF_H) conftest.* mkmf.log
+		@-$(RM) core ruby$(EXEEXT) *~ $(DISTCLEANFILES)
+
+realclean:	distclean
+install: install-so install-rb
+
+install-so: $(RUBYARCHDIR)
+install-so: $(RUBYARCHDIR)/$(DLLIB)
+$(RUBYARCHDIR)/$(DLLIB): $(DLLIB)
+	$(INSTALL_PROG) $(DLLIB) $(RUBYARCHDIR)
+install-rb: pre-install-rb install-rb-default
+install-rb-default: pre-install-rb-default
+pre-install-rb: Makefile
+pre-install-rb-default: Makefile
+$(RUBYARCHDIR):
+	$(MAKEDIRS) $@
+
+site-install: site-install-so site-install-rb
+site-install-so: install-so
+site-install-rb: install-rb
+
+.SUFFIXES: .c .m .cc .cxx .cpp .C .o
+
+.cc.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.cxx.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.cpp.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.C.o:
+	$(CXX) $(INCFLAGS) $(CPPFLAGS) $(CXXFLAGS) -c $<
+
+.c.o:
+	$(CC) $(INCFLAGS) $(CPPFLAGS) $(CFLAGS) -c $<
+
+$(DLLIB): $(OBJS)
+	@-$(RM) $@
+	$(LDSHARED) $(DLDFLAGS) $(LIBPATH) -o $@ $(OBJS) $(LOCAL_LIBS) $(LIBS)
+
+
+
+$(OBJS): ruby.h defines.h