ruby_native_statistics 0.8.2 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 58cae049ef922fead26f20dff3714c2f9c1bcccd95fe38228add9d7f6d57e787
-  data.tar.gz: 3529205f8a822cc3c418d54d36d4651708384cc885f990517e03fc0f1c8edb15
+  metadata.gz: b99d6ace1e36cdd53315356b8c4de080289a46bc307b41bc1979de4cbaff2e42
+  data.tar.gz: 5b8c3498b2a3014313b0b249eb87350e7f07e5a22237de4ea9e95f67096572c7
 SHA512:
-  metadata.gz: fe760b4680dbf1d11685404718589c7d24c659d086c422977ee3e8c1223073331dfb125c83275a9254ce7fa161b33b388cd66008f6de429417c0ba92acedad87
-  data.tar.gz: 768f2745a827ffa45fe34a89ff7eb4cc1f4d444bfa6c99f2c4bcd75058131b25cfc17f93ee58599511f8e6a265335af7480dc7890988c8e10e5aa318f4d4514c
+  metadata.gz: c837f3f6f7e2a8d47291d1e289d09e48de81c5216bca319e1be24aca7a821f0ba8e1acd3548ccfbe83a50b92752af5dc281a9a69dc052e58cee1f5e49b05e06d
+  data.tar.gz: 3c8e3629ffe57bccdbdeaa8b792d593aa89bdce401e034a2a0d08fdf62fb1ad0841229cc60c222aaa37fe0895c2fdee83109176ec553e0c1529c33814868fa4e

data/.github/workflows/main.yml

@@ -27,7 +27,7 @@ jobs:
         uses: actions/checkout@master
 
       - name: Install Bundler
-        run: gem install bundler -v 2.1.2
+        run: gem install bundler --version 2.1.2 --no-document
 
       - name: Install gems
         run: bundle

data/.vscode/c_cpp_properties.json

@@ -0,0 +1,21 @@
+{
+  "configurations": [
+    {
+      "name": "Mac",
+      "includePath": [
+        "${workspaceFolder}/**",
+        "/Users/corybuecker/.asdf/installs/ruby/2.7.0/include/ruby-2.7.0",
+        "/Users/corybuecker/.asdf/installs/ruby/2.7.0/include/ruby-2.7.0/x86_64-darwin19"
+      ],
+      "defines": [],
+      "macFrameworkPath": [
+        "/Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/System/Library/Frameworks"
+      ],
+      "compilerPath": "/usr/bin/clang",
+      "cStandard": "c11",
+      "cppStandard": "c++17",
+      "intelliSenseMode": "clang-x64"
+    }
+  ],
+  "version": 4
+}

data/README.md

@@ -6,11 +6,12 @@ This is a native extension to Ruby that adds native (C) statistical functions to
 - [Population Standard Deviation](https://en.wikipedia.org/wiki/Standard_deviation#Uncorrected_sample_standard_deviation) (stdevp)
 - [Sample Variance](https://en.wikipedia.org/wiki/Variance#Population_variance_and_sample_variance) (var)
 - [Population Variance](https://en.wikipedia.org/wiki/Variance#Population_variance_and_sample_variance) (varp)
+- [Median](https://en.wikipedia.org/wiki/Median) (median)
 - [Mean](https://en.wikipedia.org/wiki/Arithmetic_mean) (mean)
 
-Check the CircleCI build to see the currently supported versions of Ruby. This list will match whatever stable versions are specified at https://www.ruby-lang.org/en/downloads/.
+Check the Github Actions build to see the currently supported versions of Ruby. This list will match whatever stable versions are specified at https://www.ruby-lang.org/en/downloads/.
 
-It is much more performant than calculating the standard deviation with pure Ruby. For a comparison, run the benchmarks with rake.
+It is much more performant than calculating the standard deviation with pure Ruby. For a comparison, run the benchmarks with `rake benchmark`.
 
     bench_native_dispersion	 0.000425	 0.000341	 0.000420	 0.000324	 0.000319
     bench_ruby_dispersion	 0.002168	 0.002156	 0.002148	 0.002149	 0.002151
@@ -29,6 +30,9 @@ It is much more performant than calculating the standard deviation with pure Rub
     # calculate mean
     p r.mean
 
+    # calculate median
+    p r.median
+
 ## Links
 
 This is the third version of this gem, and it is a total rewrite of a SWIG-based design. Lots of thanks to the following resources:

data/Rakefile

@@ -15,7 +15,7 @@ Rake::TestTask.new(:test) do |t|
   t.test_files = FileList["test/**/*_test.rb"]
 end
 
-Rake::TestTask.new(:benchmark) do |t|
+Rake::TestTask.new(benchmark: :compile) do |t|
   t.libs << "test"
   t.libs << "lib"
   t.test_files = FileList["test/**/*_benchmark.rb"]

data/changelog.md

@@ -1,3 +1,7 @@
+# Version 0.9.0
+
+- Add median function
+
 # Version 0.8.2
 
 - Bug fix for build process

data/ext/mathematics/mathematics.c

@@ -1,17 +1,22 @@
+#include "stdbool.h"
 #include "ruby.h"
 #include "mathematics.h"
 
-void Init_mathematics() {
+void Init_mathematics()
+{
   MathematicsModule = rb_define_module("Mathematics");
   rb_define_method(MathematicsModule, "mean", rb_mean, 0);
+  rb_define_method(MathematicsModule, "median", rb_median, 0);
 }
 
-double calculate_mean(VALUE array, unsigned long array_length){
+double calculate_mean(VALUE array, unsigned long array_length)
+{
   unsigned long i;
   double total = 0;
   double mean = 0;
 
-  for(i = 0; i < array_length; i++){
+  for (i = 0; i < array_length; i++)
+  {
     total += rb_num2dbl(rb_ary_entry(array, i));
   }
 
@@ -20,31 +25,103 @@ double calculate_mean(VALUE array, unsigned long array_length){
   return mean;
 }
 
-double calculate_total_distance_from_mean(VALUE array, unsigned long array_length){
+double calculate_total_distance_from_mean(VALUE array, unsigned long array_length)
+{
   unsigned long i;
   double mean = 0;
   double total_distance_from_mean = 0;
 
   mean = calculate_mean(array, array_length);
 
-  for(i = 0; i < array_length; i++){
+  for (i = 0; i < array_length; i++)
+  {
     total_distance_from_mean += pow((rb_num2dbl(rb_ary_entry(array, i)) - mean), 2);
   }
 
   return total_distance_from_mean;
 }
 
-VALUE rb_mean(VALUE self) {
+VALUE rb_mean(VALUE self)
+{
   unsigned int array_length;
 
   Check_Type(self, T_ARRAY);
 
   array_length = rb_long2int(RARRAY_LEN(self));
 
-  if (array_length <= 0) {
+  if (array_length <= 0)
+  {
     rb_raise(rb_eRangeError, "array must have at least one element");
   }
 
   return DBL2NUM(calculate_mean(self, array_length));
 }
 
+int compare_doubles(const void *a, const void *b)
+{
+  double *dbl_a = (double *)a;
+  double *dbl_b = (double *)b;
+
+  double cmp_a = *dbl_a;
+  double cmp_b = *dbl_b;
+
+  return (cmp_a - cmp_b);
+}
+
+VALUE rb_median(VALUE self)
+{
+  unsigned long array_length;
+  unsigned long i;
+  double *working_array;
+  VALUE result;
+
+  Check_Type(self, T_ARRAY);
+
+  array_length = RARRAY_LEN(self);
+
+  if (array_length <= 0)
+  {
+    rb_raise(rb_eRangeError, "array must have at least one element");
+  }
+
+  bool array_even_size = (array_length % 2) == 0;
+  unsigned long middle = (long)floor(array_length / 2.0);
+
+  working_array = malloc(array_length * sizeof(double));
+
+  if (working_array == NULL)
+  {
+    rb_raise(rb_eStandardError, "unknown problem calculating median (possibly array is too large)");
+  }
+
+  for (i = 0; i < array_length; i++)
+  {
+    VALUE item = rb_ary_entry(self, i);
+
+    if (!RB_INTEGER_TYPE_P(item) && !RB_FLOAT_TYPE_P(item))
+    {
+      free(working_array);
+      rb_raise(rb_eTypeError, "element is not a number");
+    }
+
+    working_array[i] = NUM2DBL(item);
+  }
+
+  // Reminder to myself as I'm learning C. Using an array as a function parameter decays that reference
+  // to a pointer to the first element in the array.
+  // https://www.gnu.org/software/gnu-c-manual/gnu-c-manual.html#Function-Parameters
+  qsort(working_array, array_length, sizeof(double), compare_doubles);
+
+  if (!array_even_size)
+  {
+    result = DBL2NUM(working_array[middle]);
+  }
+  else
+  {
+    result = DBL2NUM((working_array[middle - 1] + working_array[middle]) / 2);
+  }
+
+  free(working_array);
+
+  return result;
+}

data/ext/mathematics/mathematics.h

@@ -1,4 +1,5 @@
 VALUE MathematicsModule = Qnil;
 VALUE rb_mean(VALUE self);
+VALUE rb_median(VALUE self);
 double calculate_mean(VALUE array, unsigned long array_length);
 double calculate_total_distance_from_mean(VALUE array, unsigned long array_length);

data/lib/ruby_native_statistics/version.rb

@@ -1,3 +1,3 @@
 module RubyNativeStatistics
-  VERSION = "0.8.2"
+  VERSION = "0.9.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ruby_native_statistics
 version: !ruby/object:Gem::Version
-  version: 0.8.2
+  version: 0.9.0
 platform: ruby
 authors:
 - Cory Buecker
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-01-11 00:00:00.000000000 Z
+date: 2020-01-12 00:00:00.000000000 Z
 dependencies: []
 description: 
 email:
@@ -21,6 +21,7 @@ extra_rdoc_files: []
 files:
 - ".github/workflows/main.yml"
 - ".gitignore"
+- ".vscode/c_cpp_properties.json"
 - ".vscode/settings.json"
 - Gemfile
 - Gemfile.lock