Merge branch '2.5' into 3.0

Author: andrewdalpino

.github/workflows/ci.yml

@@ -20,7 +20,7 @@ jobs:
         with:
           php-version: ${{ matrix.php-versions }}
           tools: composer, pecl
-          extensions: svm, mbstring, gd, fileinfo
+          extensions: svm, mbstring, gd, fileinfo, swoole
           ini-values: memory_limit=-1
 
       - name: Validate composer.json

.gitignore

@@ -8,6 +8,7 @@ Thumbs.db
 .DS_Store
 debug.log
 /test.png
+pyvenv.cfg
 .venv
 .idea
 .vscode

CHANGELOG.md

@@ -12,6 +12,9 @@
 - 2.5.0
     - Added Vantage Point Spatial tree
     - Blob Generator can now `simulate()` a Dataset object
+    - Added Wrapper interface
+    - Added Swoole Backend
+    - Plus Plus added check for min number of sample seeds
 
 - 2.4.1
     - Sentence Tokenizer fix Arabic and Farsi language support

benchmarks/Classifiers/OneVsRestBench.php

@@ -2,18 +2,22 @@
 
 namespace Rubix\ML\Benchmarks\Classifiers;
 
+use Rubix\ML\Backends\Backend;
 use Rubix\ML\Classifiers\OneVsRest;
 use Rubix\ML\Datasets\Generators\Blob;
 use Rubix\ML\Classifiers\LogisticRegression;
 use Rubix\ML\NeuralNet\Optimizers\Stochastic;
 use Rubix\ML\Datasets\Generators\Agglomerate;
+use Rubix\ML\Tests\DataProvider\BackendProviderTrait;
 
 /**
  * @Groups({"Classifiers"})
  * @BeforeMethods({"setUp"})
  */
 class OneVsRestBench
 {
+    use BackendProviderTrait;
+
     protected const TRAINING_SIZE = 10000;
 
     protected const TESTING_SIZE = 10000;
@@ -52,9 +56,13 @@ public function setUp() : void
      * @Subject
      * @Iterations(5)
      * @OutputTimeUnit("seconds", precision=3)
+     * @ParamProviders("provideBackends")
+     * @param array{ backend: Backend } $params
      */
-    public function trainPredict() : void
+    public function trainPredict(array $params) : void
     {
+        $this->estimator->setBackend($params['backend']);
+
         $this->estimator->train($this->training);
 
         $this->estimator->predict($this->testing);

benchmarks/Classifiers/RandomForestBench.php

@@ -2,17 +2,21 @@
 
 namespace Rubix\ML\Benchmarks\Classifiers;
 
+use Rubix\ML\Backends\Backend;
 use Rubix\ML\Classifiers\RandomForest;
 use Rubix\ML\Datasets\Generators\Blob;
 use Rubix\ML\Classifiers\ClassificationTree;
 use Rubix\ML\Datasets\Generators\Agglomerate;
+use Rubix\ML\Tests\DataProvider\BackendProviderTrait;
 use Rubix\ML\Transformers\IntervalDiscretizer;
 
 /**
  * @Groups({"Classifiers"})
  */
 class RandomForestBench
 {
+    use BackendProviderTrait;
+
     protected const TRAINING_SIZE = 10000;
 
     protected const TESTING_SIZE = 10000;
@@ -70,9 +74,13 @@ public function setUpCategorical() : void
      * @Iterations(5)
      * @BeforeMethods({"setUpContinuous"})
      * @OutputTimeUnit("seconds", precision=3)
+     * @ParamProviders("provideBackends")
+     * @param array{ backend: Backend } $params
      */
-    public function continuous() : void
+    public function continuous(array $params) : void
     {
+        $this->estimator->setBackend($params['backend']);
+
         $this->estimator->train($this->training);
 
         $this->estimator->predict($this->testing);
@@ -83,9 +91,13 @@ public function continuous() : void
      * @Iterations(5)
      * @BeforeMethods({"setUpCategorical"})
      * @OutputTimeUnit("seconds", precision=3)
+     * @ParamProviders("provideBackends")
+     * @param array{ backend: Backend } $params
      */
-    public function categorical() : void
+    public function categorical(array $params) : void
     {
+        $this->estimator->setBackend($params['backend']);
+
         $this->estimator->train($this->training);
 
         $this->estimator->predict($this->testing);

composer.json

@@ -49,7 +49,8 @@
         "phpstan/extension-installer": "^1.0",
         "phpstan/phpstan": "^1.0",
         "phpstan/phpstan-phpunit": "^1.0",
-        "phpunit/phpunit": "^9.0"
+        "phpunit/phpunit": "^9.0",
+        "swoole/ide-helper": "^5.1"
     },
     "suggest": {
         "ext-tensor": "For fast Matrix/Vector computing",

docs/cross-validation/metrics/rand-index.md

@@ -7,7 +7,7 @@ $$
 {\displaystyle ARI = {\frac {\left.\sum _{ij}{\binom {n_{ij}}{2}}-\left[\sum _{i}{\binom {a_{i}}{2}}\sum _{j}{\binom {b_{j}}{2}}\right]\right/{\binom {n}{2}}}{\left.{\frac {1}{2}}\left[\sum _{i}{\binom {a_{i}}{2}}+\sum _{j}{\binom {b_{j}}{2}}\right]-\left[\sum _{i}{\binom {a_{i}}{2}}\sum _{j}{\binom {b_{j}}{2}}\right]\right/{\binom {n}{2}}}}}
 $$
 
-**Estimator Compatibility:** Regressor
+**Estimator Compatibility:** Clusterer
 
 **Score Range:** -1 to 1
 

phpstan.neon

@@ -6,3 +6,4 @@ parameters:
         - 'benchmarks'
     excludePaths:
         - src/Backends/Amp.php
+        - src/Backends/Swoole.php

phpunit.xml

@@ -1,5 +1,18 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<phpunit xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" backupGlobals="false" backupStaticAttributes="false" bootstrap="vendor/autoload.php" colors="true" convertErrorsToExceptions="true" convertNoticesToExceptions="true" convertWarningsToExceptions="true" forceCoversAnnotation="true" processIsolation="false" stopOnFailure="false" xsi:noNamespaceSchemaLocation="https://schema.phpunit.de/9.3/phpunit.xsd">
+<phpunit
+  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  backupGlobals="false"
+  backupStaticAttributes="false"
+  bootstrap="vendor/autoload.php"
+  colors="true"
+  convertErrorsToExceptions="true"
+  convertNoticesToExceptions="true"
+  convertWarningsToExceptions="true"
+  forceCoversAnnotation="true"
+  processIsolation="true"
+  stopOnFailure="false"
+  xsi:noNamespaceSchemaLocation="https://schema.phpunit.de/9.3/phpunit.xsd"
+>
   <coverage processUncoveredFiles="true">
     <include>
       <directory suffix=".php">src</directory>

src/AnomalyDetectors/LocalOutlierFactor.php

@@ -67,7 +67,7 @@ class LocalOutlierFactor implements Estimator, Learner, Scoring, Persistable
      *
      * @var Spatial
      */
-    protected \Rubix\ML\Graph\Trees\Spatial $tree;
+    protected Spatial $tree;
 
     /**
      * The precomputed k distances between each training sample and its k'th nearest neighbor.