From f6a561158654ea8689fd3155f586ccb76106ab27 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 21:50:30 +0200
Subject: [PATCH 01/27] move functions definitions

---
 src/Phpml/Classifier/NaiveBayes.php            | 16 ----------------
 .../NaiveBayes/GaussianNaiveBayes.php          | 18 ++++++++++++++++++
 2 files changed, 18 insertions(+), 16 deletions(-)

diff --git a/src/Phpml/Classifier/NaiveBayes.php b/src/Phpml/Classifier/NaiveBayes.php
index e852645..7207409 100644
--- a/src/Phpml/Classifier/NaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes.php
@@ -5,22 +5,6 @@ namespace Phpml\Classifier;
 abstract class NaiveBayes implements Classifier
 {
 
-    /**
-     * @param array $features
-     * @param array $labels
-     */
-    public function train($features, $labels)
-    {
 
-    }
-
-    /**
-     * @param mixed $feature
-     * @return mixed
-     */
-    public function predict($feature)
-    {
-
-    }
 
 }
diff --git a/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php b/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
index df9772f..33117fa 100644
--- a/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
@@ -5,4 +5,22 @@ use Phpml\Classifier\NaiveBayes;
 class GaussianNaiveBayes extends NaiveBayes
 {
 
+    /**
+     * @param array $features
+     * @param array $labels
+     */
+    public function train($features, $labels)
+    {
+
+    }
+
+    /**
+     * @param mixed $feature
+     * @return mixed
+     */
+    public function predict($feature)
+    {
+
+    }
+
 }

From ce1653a5a768bd96d7f0c265d63419e299db05db Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 22:25:27 +0200
Subject: [PATCH 02/27] create euclidean distance function

---
 src/Phpml/Classifier/Classifier.php           |  3 +-
 src/Phpml/Classifier/KNearestNeighbors.php    | 54 +++++++++++++++++++
 src/Phpml/Classifier/NaiveBayes.php           | 19 ++++++-
 .../NaiveBayes/GaussianNaiveBayes.php         | 26 ---------
 .../Exception/InvalidArgumentException.php    | 17 ++++++
 src/Phpml/Metric/Distance.php                 | 36 +++++++++++++
 6 files changed, 127 insertions(+), 28 deletions(-)
 create mode 100644 src/Phpml/Classifier/KNearestNeighbors.php
 delete mode 100644 src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
 create mode 100644 src/Phpml/Exception/InvalidArgumentException.php
 create mode 100644 src/Phpml/Metric/Distance.php

diff --git a/src/Phpml/Classifier/Classifier.php b/src/Phpml/Classifier/Classifier.php
index ea2bbf1..1d2362e 100644
--- a/src/Phpml/Classifier/Classifier.php
+++ b/src/Phpml/Classifier/Classifier.php
@@ -1,4 +1,5 @@
 <?php
+declare(strict_types=1);
 
 namespace Phpml\Classifier;
 
@@ -9,7 +10,7 @@ interface Classifier
      * @param array $features
      * @param array $labels
      */
-    public function train($features, $labels);
+    public function train(array $features, array $labels);
 
     /**
      * @param mixed $feature
diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
new file mode 100644
index 0000000..ac4bf31
--- /dev/null
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -0,0 +1,54 @@
+<?php
+declare(strict_types=1);
+
+namespace Phpml\Classifier;
+
+class KNearestNeighbors implements Classifier
+{
+    /**
+     *
+     * @var int
+     */
+    private $k;
+
+    /**
+     * @var array
+     */
+    private $features;
+
+    /**
+     * @var array
+     */
+    private $labels;
+
+    /**
+     * @param int $k
+     */
+    public function __construct(int $k = 3)
+    {
+        $this->k = $k;
+        $this->features = [];
+        $this->labels = [];
+    }
+
+
+    /**
+     * @param array $features
+     * @param array $labels
+     */
+    public function train(array $features, array $labels)
+    {
+        $this->features = $features;
+        $this->labels = $labels;
+    }
+
+    /**
+     * @param mixed $feature
+     * @return mixed
+     */
+    public function predict($feature)
+    {
+
+    }
+
+}
diff --git a/src/Phpml/Classifier/NaiveBayes.php b/src/Phpml/Classifier/NaiveBayes.php
index 7207409..8e31eff 100644
--- a/src/Phpml/Classifier/NaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes.php
@@ -1,10 +1,27 @@
 <?php
+declare(strict_types=1);
 
 namespace Phpml\Classifier;
 
-abstract class NaiveBayes implements Classifier
+class NaiveBayes implements Classifier
 {
 
+    /**
+     * @param array $features
+     * @param array $labels
+     */
+    public function train(array $features, array $labels)
+    {
 
+    }
+
+    /**
+     * @param mixed $feature
+     * @return mixed
+     */
+    public function predict($feature)
+    {
+
+    }
 
 }
diff --git a/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php b/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
deleted file mode 100644
index 33117fa..0000000
--- a/src/Phpml/Classifier/NaiveBayes/GaussianNaiveBayes.php
+++ /dev/null
@@ -1,26 +0,0 @@
-<?php
-
-use Phpml\Classifier\NaiveBayes;
-
-class GaussianNaiveBayes extends NaiveBayes
-{
-
-    /**
-     * @param array $features
-     * @param array $labels
-     */
-    public function train($features, $labels)
-    {
-
-    }
-
-    /**
-     * @param mixed $feature
-     * @return mixed
-     */
-    public function predict($feature)
-    {
-
-    }
-
-}
diff --git a/src/Phpml/Exception/InvalidArgumentException.php b/src/Phpml/Exception/InvalidArgumentException.php
new file mode 100644
index 0000000..c88ab50
--- /dev/null
+++ b/src/Phpml/Exception/InvalidArgumentException.php
@@ -0,0 +1,17 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Exception;
+
+class InvalidArgumentException extends \Exception
+{
+
+    /**
+     * @return InvalidArgumentException
+     */
+    public static function parametersSizeNotMatch()
+    {
+        return new self('Size of parameters not match');
+    }
+
+}
diff --git a/src/Phpml/Metric/Distance.php b/src/Phpml/Metric/Distance.php
new file mode 100644
index 0000000..e1e64c6
--- /dev/null
+++ b/src/Phpml/Metric/Distance.php
@@ -0,0 +1,36 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Metric;
+
+use Phpml\Exception\InvalidArgumentException;
+
+class Distance
+{
+
+    /**
+     * @param array $a
+     * @param array $b
+     *
+     * @return float
+     *
+     * @throws InvalidArgumentException
+     */
+    public static function euclidean(array $a, array $b): float 
+    {
+        if(count($a) != count($b))
+        {
+            throw InvalidArgumentException::parametersSizeNotMatch();
+        }
+
+        $distance = 0;
+
+        for($i=0; $i<count($a); $i++)
+        {
+            $distance += pow($a[$i] - $b[$i], 2);
+        }
+
+        return sqrt($distance);
+    }
+
+}

From dd927ef9815a7ff9fd13dd2fb8373effc6df86c6 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 22:38:51 +0200
Subject: [PATCH 03/27] create phpunit configuration and first tests

---
 composer.json                                  |  5 +++++
 phpunit.xml                                    | 14 ++++++++++++++
 .../Exception/InvalidArgumentException.php     |  4 ++--
 src/Phpml/Metric/Distance.php                  |  4 ++--
 tests/Phpml/Metric/DistanceTest.php            | 18 ++++++++++++++++++
 5 files changed, 41 insertions(+), 4 deletions(-)
 create mode 100644 phpunit.xml
 create mode 100644 tests/Phpml/Metric/DistanceTest.php

diff --git a/composer.json b/composer.json
index 7f6a744..d8d5026 100644
--- a/composer.json
+++ b/composer.json
@@ -11,6 +11,11 @@
             "email": "arkadiusz.kondas@gmail.com"
         }
     ],
+    "autoload": {
+        "psr-4": {
+            "": "src/"
+        }
+    },
     "config": {
         "bin-dir": "bin"
     },
diff --git a/phpunit.xml b/phpunit.xml
new file mode 100644
index 0000000..d31e033
--- /dev/null
+++ b/phpunit.xml
@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<phpunit
+        colors="true"
+        beStrictAboutTestsThatDoNotTestAnything="true"
+        beStrictAboutOutputDuringTests="true"
+        beStrictAboutTestSize="true"
+        beStrictAboutChangesToGlobalState="true"
+>
+    <testsuites>
+        <testsuite name="PHP-ML Test Suite">
+            <directory>tests/*</directory>
+        </testsuite>
+    </testsuites>​
+</phpunit>
diff --git a/src/Phpml/Exception/InvalidArgumentException.php b/src/Phpml/Exception/InvalidArgumentException.php
index c88ab50..4ee194b 100644
--- a/src/Phpml/Exception/InvalidArgumentException.php
+++ b/src/Phpml/Exception/InvalidArgumentException.php
@@ -9,9 +9,9 @@ class InvalidArgumentException extends \Exception
     /**
      * @return InvalidArgumentException
      */
-    public static function parametersSizeNotMatch()
+    public static function sizeNotMatch()
     {
-        return new self('Size of parameters not match');
+        return new self('Size of given arguments not match');
     }
 
 }
diff --git a/src/Phpml/Metric/Distance.php b/src/Phpml/Metric/Distance.php
index e1e64c6..581b73c 100644
--- a/src/Phpml/Metric/Distance.php
+++ b/src/Phpml/Metric/Distance.php
@@ -16,11 +16,11 @@ class Distance
      *
      * @throws InvalidArgumentException
      */
-    public static function euclidean(array $a, array $b): float 
+    public static function euclidean(array $a, array $b): float
     {
         if(count($a) != count($b))
         {
-            throw InvalidArgumentException::parametersSizeNotMatch();
+            throw InvalidArgumentException::sizeNotMatch();
         }
 
         $distance = 0;
diff --git a/tests/Phpml/Metric/DistanceTest.php b/tests/Phpml/Metric/DistanceTest.php
new file mode 100644
index 0000000..947bb81
--- /dev/null
+++ b/tests/Phpml/Metric/DistanceTest.php
@@ -0,0 +1,18 @@
+<?php
+declare(strict_types = 1);
+
+namespace tests\Phpml\Metric;
+
+use Phpml\Metric\Distance;
+
+class DistanceTest extends \PHPUnit_Framework_TestCase
+{
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnInvalidArguments()
+    {
+        Distance::euclidean([0, 1, 2], [0, 2]);
+    }
+
+}

From 5c348e845285a27dc143dc71c22afa80bc02feb2 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 22:48:07 +0200
Subject: [PATCH 04/27] add more Euclidean distance tests

---
 tests/Phpml/Metric/DistanceTest.php | 37 +++++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/tests/Phpml/Metric/DistanceTest.php b/tests/Phpml/Metric/DistanceTest.php
index 947bb81..aad4c05 100644
--- a/tests/Phpml/Metric/DistanceTest.php
+++ b/tests/Phpml/Metric/DistanceTest.php
@@ -10,9 +10,42 @@ class DistanceTest extends \PHPUnit_Framework_TestCase
     /**
      * @expectedException \Phpml\Exception\InvalidArgumentException
      */
-    public function testThrowExceptionOnInvalidArguments()
+    public function testThrowExceptionOnInvalidArgumentsInEuclidean()
     {
-        Distance::euclidean([0, 1, 2], [0, 2]);
+        $a = [0, 1, 2];
+        $b = [0, 2];
+
+        Distance::euclidean($a, $b);
+    }
+
+    public function testCalculateEuclideanDistanceForOneDimension()
+    {
+        $a = [4];
+        $b = [2];
+
+        $expectedDistance = 2;
+        $actualDistance = Distance::euclidean($a, $b);
+
+        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
+    }
+
+    public function testCalculateEuclideanDistanceForTwoAndMoreDimension()
+    {
+        $a = [4, 6];
+        $b = [2, 5];
+
+        $expectedDistance = 2.2360679774998;
+        $actualDistance = Distance::euclidean($a, $b);
+
+        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
+
+        $a = [6, 10, 3];
+        $b = [2, 5, 5];
+
+        $expectedDistance = 6.7082039324993694;
+        $actualDistance = Distance::euclidean($a, $b);
+
+        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
     }
 
 }

From bd31f9a025932b1f53864f425c96c6ab99a06465 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 22:49:54 +0200
Subject: [PATCH 05/27] php-cs-fixer

---
 src/Phpml/Classifier/Classifier.php              |  6 +++---
 src/Phpml/Classifier/KNearestNeighbors.php       |  8 +++-----
 src/Phpml/Classifier/NaiveBayes.php              |  8 +++-----
 src/Phpml/Dataset/Dataset.php                    |  1 -
 src/Phpml/Dataset/Iris.php                       |  1 -
 src/Phpml/Exception/InvalidArgumentException.php |  5 ++---
 src/Phpml/Metric/Distance.php                    | 11 ++++-------
 tests/Phpml/Metric/DistanceTest.php              |  4 ++--
 8 files changed, 17 insertions(+), 27 deletions(-)

diff --git a/src/Phpml/Classifier/Classifier.php b/src/Phpml/Classifier/Classifier.php
index 1d2362e..face7b2 100644
--- a/src/Phpml/Classifier/Classifier.php
+++ b/src/Phpml/Classifier/Classifier.php
@@ -1,11 +1,11 @@
 <?php
-declare(strict_types=1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Classifier;
 
 interface Classifier
 {
-
     /**
      * @param array $features
      * @param array $labels
@@ -14,8 +14,8 @@ interface Classifier
 
     /**
      * @param mixed $feature
+     *
      * @return mixed
      */
     public function predict($feature);
-
 }
diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
index ac4bf31..e028d61 100644
--- a/src/Phpml/Classifier/KNearestNeighbors.php
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -1,12 +1,12 @@
 <?php
-declare(strict_types=1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Classifier;
 
 class KNearestNeighbors implements Classifier
 {
     /**
-     *
      * @var int
      */
     private $k;
@@ -31,7 +31,6 @@ class KNearestNeighbors implements Classifier
         $this->labels = [];
     }
 
-
     /**
      * @param array $features
      * @param array $labels
@@ -44,11 +43,10 @@ class KNearestNeighbors implements Classifier
 
     /**
      * @param mixed $feature
+     *
      * @return mixed
      */
     public function predict($feature)
     {
-
     }
-
 }
diff --git a/src/Phpml/Classifier/NaiveBayes.php b/src/Phpml/Classifier/NaiveBayes.php
index 8e31eff..ed6bb8c 100644
--- a/src/Phpml/Classifier/NaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes.php
@@ -1,27 +1,25 @@
 <?php
-declare(strict_types=1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Classifier;
 
 class NaiveBayes implements Classifier
 {
-
     /**
      * @param array $features
      * @param array $labels
      */
     public function train(array $features, array $labels)
     {
-
     }
 
     /**
      * @param mixed $feature
+     *
      * @return mixed
      */
     public function predict($feature)
     {
-
     }
-
 }
diff --git a/src/Phpml/Dataset/Dataset.php b/src/Phpml/Dataset/Dataset.php
index 4c2378a..316ee1d 100644
--- a/src/Phpml/Dataset/Dataset.php
+++ b/src/Phpml/Dataset/Dataset.php
@@ -6,5 +6,4 @@ abstract class Dataset
      * @var string
      */
     protected $filepath;
-
 }
diff --git a/src/Phpml/Dataset/Iris.php b/src/Phpml/Dataset/Iris.php
index 6669061..0565558 100644
--- a/src/Phpml/Dataset/Iris.php
+++ b/src/Phpml/Dataset/Iris.php
@@ -6,5 +6,4 @@ class Iris extends Dataset
      * @var string
      */
     protected $filepath = 'iris.csv';
-
 }
diff --git a/src/Phpml/Exception/InvalidArgumentException.php b/src/Phpml/Exception/InvalidArgumentException.php
index 4ee194b..70bf918 100644
--- a/src/Phpml/Exception/InvalidArgumentException.php
+++ b/src/Phpml/Exception/InvalidArgumentException.php
@@ -1,11 +1,11 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Exception;
 
 class InvalidArgumentException extends \Exception
 {
-
     /**
      * @return InvalidArgumentException
      */
@@ -13,5 +13,4 @@ class InvalidArgumentException extends \Exception
     {
         return new self('Size of given arguments not match');
     }
-
 }
diff --git a/src/Phpml/Metric/Distance.php b/src/Phpml/Metric/Distance.php
index 581b73c..e0dce2d 100644
--- a/src/Phpml/Metric/Distance.php
+++ b/src/Phpml/Metric/Distance.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Metric;
 
@@ -7,7 +8,6 @@ use Phpml\Exception\InvalidArgumentException;
 
 class Distance
 {
-
     /**
      * @param array $a
      * @param array $b
@@ -18,19 +18,16 @@ class Distance
      */
     public static function euclidean(array $a, array $b): float
     {
-        if(count($a) != count($b))
-        {
+        if (count($a) != count($b)) {
             throw InvalidArgumentException::sizeNotMatch();
         }
 
         $distance = 0;
 
-        for($i=0; $i<count($a); $i++)
-        {
+        for ($i = 0; $i < count($a); ++$i) {
             $distance += pow($a[$i] - $b[$i], 2);
         }
 
         return sqrt($distance);
     }
-
 }
diff --git a/tests/Phpml/Metric/DistanceTest.php b/tests/Phpml/Metric/DistanceTest.php
index aad4c05..249a9f8 100644
--- a/tests/Phpml/Metric/DistanceTest.php
+++ b/tests/Phpml/Metric/DistanceTest.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace tests\Phpml\Metric;
 
@@ -47,5 +48,4 @@ class DistanceTest extends \PHPUnit_Framework_TestCase
 
         \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
     }
-
 }

From 8d910410c88b760c0a27d07ab9873d3054cc1e64 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Mon, 4 Apr 2016 22:50:14 +0200
Subject: [PATCH 06/27] create php-cs-fixer start script

---
 tools/php-cs-fixer.sh | 6 ++++++
 1 file changed, 6 insertions(+)
 create mode 100755 tools/php-cs-fixer.sh

diff --git a/tools/php-cs-fixer.sh b/tools/php-cs-fixer.sh
new file mode 100755
index 0000000..dbf66e4
--- /dev/null
+++ b/tools/php-cs-fixer.sh
@@ -0,0 +1,6 @@
+#!/bin/bash
+echo "Fixing src/ folder"
+php-cs-fixer fix src/ --level=symfony
+
+echo "Fixing tests/ folder"
+php-cs-fixer fix tests/ --level=symfony

From 4235f143bf148e7899ff9d080056decc1a31b172 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Tue, 5 Apr 2016 20:46:57 +0200
Subject: [PATCH 07/27] update composer php required version to 7

---
 composer.json |   2 +-
 composer.lock | 183 ++++++++++++++++++++++++++++++++++++++------------
 2 files changed, 141 insertions(+), 44 deletions(-)

diff --git a/composer.json b/composer.json
index d8d5026..66083b2 100644
--- a/composer.json
+++ b/composer.json
@@ -20,7 +20,7 @@
         "bin-dir": "bin"
     },
     "require": {
-        "php": ">=5.5.0"
+        "php": ">=7.0.5"
     },
     "require-dev": {
         "phpunit/phpunit": "^5.2"
diff --git a/composer.lock b/composer.lock
index 1117546..0b9287b 100644
--- a/composer.lock
+++ b/composer.lock
@@ -4,8 +4,8 @@
         "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file",
         "This file is @generated automatically"
     ],
-    "hash": "640f762012a359b150ce245491743448",
-    "content-hash": "5efa8db5a672e2128d20c80c18746c72",
+    "hash": "54ea009d9b09c1886c0789dadc484a36",
+    "content-hash": "52c31f7df9edd7063e2489ed47e091a7",
     "packages": [],
     "packages-dev": [
         {
@@ -155,22 +155,24 @@
         },
         {
             "name": "phpspec/prophecy",
-            "version": "v1.5.0",
+            "version": "v1.6.0",
             "source": {
                 "type": "git",
                 "url": "https://github.com/phpspec/prophecy.git",
-                "reference": "4745ded9307786b730d7a60df5cb5a6c43cf95f7"
+                "reference": "3c91bdf81797d725b14cb62906f9a4ce44235972"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/phpspec/prophecy/zipball/4745ded9307786b730d7a60df5cb5a6c43cf95f7",
-                "reference": "4745ded9307786b730d7a60df5cb5a6c43cf95f7",
+                "url": "https://api.github.com/repos/phpspec/prophecy/zipball/3c91bdf81797d725b14cb62906f9a4ce44235972",
+                "reference": "3c91bdf81797d725b14cb62906f9a4ce44235972",
                 "shasum": ""
             },
             "require": {
                 "doctrine/instantiator": "^1.0.2",
+                "php": "^5.3|^7.0",
                 "phpdocumentor/reflection-docblock": "~2.0",
-                "sebastian/comparator": "~1.1"
+                "sebastian/comparator": "~1.1",
+                "sebastian/recursion-context": "~1.0"
             },
             "require-dev": {
                 "phpspec/phpspec": "~2.0"
@@ -178,7 +180,7 @@
             "type": "library",
             "extra": {
                 "branch-alias": {
-                    "dev-master": "1.4.x-dev"
+                    "dev-master": "1.5.x-dev"
                 }
             },
             "autoload": {
@@ -211,27 +213,28 @@
                 "spy",
                 "stub"
             ],
-            "time": "2015-08-13 10:07:40"
+            "time": "2016-02-15 07:46:21"
         },
         {
             "name": "phpunit/php-code-coverage",
-            "version": "3.1.1",
+            "version": "3.3.0",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/php-code-coverage.git",
-                "reference": "92f5c61b5c64159faec5298325ffab0c7e59dcc8"
+                "reference": "fe33716763b604ade4cb442c0794f5bd5ad73004"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/php-code-coverage/zipball/92f5c61b5c64159faec5298325ffab0c7e59dcc8",
-                "reference": "92f5c61b5c64159faec5298325ffab0c7e59dcc8",
+                "url": "https://api.github.com/repos/sebastianbergmann/php-code-coverage/zipball/fe33716763b604ade4cb442c0794f5bd5ad73004",
+                "reference": "fe33716763b604ade4cb442c0794f5bd5ad73004",
                 "shasum": ""
             },
             "require": {
-                "php": ">=5.6",
+                "php": "^5.6 || ^7.0",
                 "phpunit/php-file-iterator": "~1.3",
                 "phpunit/php-text-template": "~1.2",
-                "phpunit/php-token-stream": "~1.3",
+                "phpunit/php-token-stream": "^1.4.2",
+                "sebastian/code-unit-reverse-lookup": "~1.0",
                 "sebastian/environment": "^1.3.2",
                 "sebastian/version": "~1.0|~2.0"
             },
@@ -247,7 +250,7 @@
             "type": "library",
             "extra": {
                 "branch-alias": {
-                    "dev-master": "3.1.x-dev"
+                    "dev-master": "3.3.x-dev"
                 }
             },
             "autoload": {
@@ -273,7 +276,7 @@
                 "testing",
                 "xunit"
             ],
-            "time": "2016-02-04 13:05:19"
+            "time": "2016-03-03 08:49:08"
         },
         {
             "name": "phpunit/php-file-iterator",
@@ -455,16 +458,16 @@
         },
         {
             "name": "phpunit/phpunit",
-            "version": "5.2.3",
+            "version": "5.3.0",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/phpunit.git",
-                "reference": "6fdb1d3004ebc7071c4ac62f2881d67c5c11fb59"
+                "reference": "dd3001822b2df8f5add266020e3d2fd3c5db3ae9"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/6fdb1d3004ebc7071c4ac62f2881d67c5c11fb59",
-                "reference": "6fdb1d3004ebc7071c4ac62f2881d67c5c11fb59",
+                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/dd3001822b2df8f5add266020e3d2fd3c5db3ae9",
+                "reference": "dd3001822b2df8f5add266020e3d2fd3c5db3ae9",
                 "shasum": ""
             },
             "require": {
@@ -474,18 +477,19 @@
                 "ext-reflection": "*",
                 "ext-spl": "*",
                 "myclabs/deep-copy": "~1.3",
-                "php": ">=5.6",
+                "php": "^5.6 || ^7.0",
                 "phpspec/prophecy": "^1.3.1",
-                "phpunit/php-code-coverage": "~3.0",
+                "phpunit/php-code-coverage": "^3.3.0",
                 "phpunit/php-file-iterator": "~1.4",
                 "phpunit/php-text-template": "~1.2",
                 "phpunit/php-timer": ">=1.0.6",
-                "phpunit/phpunit-mock-objects": ">=3.0.5",
+                "phpunit/phpunit-mock-objects": "^3.1",
                 "sebastian/comparator": "~1.1",
                 "sebastian/diff": "~1.2",
                 "sebastian/environment": "~1.3",
                 "sebastian/exporter": "~1.2",
                 "sebastian/global-state": "~1.0",
+                "sebastian/object-enumerator": "~1.0",
                 "sebastian/resource-operations": "~1.0",
                 "sebastian/version": "~1.0|~2.0",
                 "symfony/yaml": "~2.1|~3.0"
@@ -499,7 +503,7 @@
             "type": "library",
             "extra": {
                 "branch-alias": {
-                    "dev-master": "5.2.x-dev"
+                    "dev-master": "5.3.x-dev"
                 }
             },
             "autoload": {
@@ -525,20 +529,20 @@
                 "testing",
                 "xunit"
             ],
-            "time": "2016-02-08 12:15:53"
+            "time": "2016-03-31 21:35:50"
         },
         {
             "name": "phpunit/phpunit-mock-objects",
-            "version": "3.0.6",
+            "version": "3.1.2",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/phpunit-mock-objects.git",
-                "reference": "49bc700750196c04dd6bc2c4c99cb632b893836b"
+                "reference": "7c34c9bdde4131b824086457a3145e27dba10ca1"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/phpunit-mock-objects/zipball/49bc700750196c04dd6bc2c4c99cb632b893836b",
-                "reference": "49bc700750196c04dd6bc2c4c99cb632b893836b",
+                "url": "https://api.github.com/repos/sebastianbergmann/phpunit-mock-objects/zipball/7c34c9bdde4131b824086457a3145e27dba10ca1",
+                "reference": "7c34c9bdde4131b824086457a3145e27dba10ca1",
                 "shasum": ""
             },
             "require": {
@@ -556,7 +560,7 @@
             "type": "library",
             "extra": {
                 "branch-alias": {
-                    "dev-master": "3.0.x-dev"
+                    "dev-master": "3.1.x-dev"
                 }
             },
             "autoload": {
@@ -581,7 +585,52 @@
                 "mock",
                 "xunit"
             ],
-            "time": "2015-12-08 08:47:06"
+            "time": "2016-03-24 05:58:25"
+        },
+        {
+            "name": "sebastian/code-unit-reverse-lookup",
+            "version": "1.0.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/sebastianbergmann/code-unit-reverse-lookup.git",
+                "reference": "c36f5e7cfce482fde5bf8d10d41a53591e0198fe"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/sebastianbergmann/code-unit-reverse-lookup/zipball/c36f5e7cfce482fde5bf8d10d41a53591e0198fe",
+                "reference": "c36f5e7cfce482fde5bf8d10d41a53591e0198fe",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=5.6"
+            },
+            "require-dev": {
+                "phpunit/phpunit": "~5"
+            },
+            "type": "library",
+            "extra": {
+                "branch-alias": {
+                    "dev-master": "1.0.x-dev"
+                }
+            },
+            "autoload": {
+                "classmap": [
+                    "src/"
+                ]
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "BSD-3-Clause"
+            ],
+            "authors": [
+                {
+                    "name": "Sebastian Bergmann",
+                    "email": "sebastian@phpunit.de"
+                }
+            ],
+            "description": "Looks up which function or method a line of code belongs to",
+            "homepage": "https://github.com/sebastianbergmann/code-unit-reverse-lookup/",
+            "time": "2016-02-13 06:45:14"
         },
         {
             "name": "sebastian/comparator",
@@ -701,16 +750,16 @@
         },
         {
             "name": "sebastian/environment",
-            "version": "1.3.3",
+            "version": "1.3.5",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/environment.git",
-                "reference": "6e7133793a8e5a5714a551a8324337374be209df"
+                "reference": "dc7a29032cf72b54f36dac15a1ca5b3a1b6029bf"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/environment/zipball/6e7133793a8e5a5714a551a8324337374be209df",
-                "reference": "6e7133793a8e5a5714a551a8324337374be209df",
+                "url": "https://api.github.com/repos/sebastianbergmann/environment/zipball/dc7a29032cf72b54f36dac15a1ca5b3a1b6029bf",
+                "reference": "dc7a29032cf72b54f36dac15a1ca5b3a1b6029bf",
                 "shasum": ""
             },
             "require": {
@@ -747,7 +796,7 @@
                 "environment",
                 "hhvm"
             ],
-            "time": "2015-12-02 08:37:27"
+            "time": "2016-02-26 18:40:46"
         },
         {
             "name": "sebastian/exporter",
@@ -866,6 +915,52 @@
             ],
             "time": "2015-10-12 03:26:01"
         },
+        {
+            "name": "sebastian/object-enumerator",
+            "version": "1.0.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/sebastianbergmann/object-enumerator.git",
+                "reference": "d4ca2fb70344987502567bc50081c03e6192fb26"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/sebastianbergmann/object-enumerator/zipball/d4ca2fb70344987502567bc50081c03e6192fb26",
+                "reference": "d4ca2fb70344987502567bc50081c03e6192fb26",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=5.6",
+                "sebastian/recursion-context": "~1.0"
+            },
+            "require-dev": {
+                "phpunit/phpunit": "~5"
+            },
+            "type": "library",
+            "extra": {
+                "branch-alias": {
+                    "dev-master": "1.0.x-dev"
+                }
+            },
+            "autoload": {
+                "classmap": [
+                    "src/"
+                ]
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "BSD-3-Clause"
+            ],
+            "authors": [
+                {
+                    "name": "Sebastian Bergmann",
+                    "email": "sebastian@phpunit.de"
+                }
+            ],
+            "description": "Traverses array structures and object graphs to enumerate all referenced objects",
+            "homepage": "https://github.com/sebastianbergmann/object-enumerator/",
+            "time": "2016-01-28 13:25:10"
+        },
         {
             "name": "sebastian/recursion-context",
             "version": "1.0.2",
@@ -1006,16 +1101,16 @@
         },
         {
             "name": "symfony/yaml",
-            "version": "v3.0.2",
+            "version": "v3.0.4",
             "source": {
                 "type": "git",
                 "url": "https://github.com/symfony/yaml.git",
-                "reference": "3cf0709d7fe936e97bee9e954382e449003f1d9a"
+                "reference": "0047c8366744a16de7516622c5b7355336afae96"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/symfony/yaml/zipball/3cf0709d7fe936e97bee9e954382e449003f1d9a",
-                "reference": "3cf0709d7fe936e97bee9e954382e449003f1d9a",
+                "url": "https://api.github.com/repos/symfony/yaml/zipball/0047c8366744a16de7516622c5b7355336afae96",
+                "reference": "0047c8366744a16de7516622c5b7355336afae96",
                 "shasum": ""
             },
             "require": {
@@ -1051,7 +1146,7 @@
             ],
             "description": "Symfony Yaml Component",
             "homepage": "https://symfony.com",
-            "time": "2016-02-02 13:44:19"
+            "time": "2016-03-04 07:55:57"
         }
     ],
     "aliases": [],
@@ -1059,6 +1154,8 @@
     "stability-flags": [],
     "prefer-stable": false,
     "prefer-lowest": false,
-    "platform": [],
+    "platform": {
+        "php": ">=7.0.5"
+    },
     "platform-dev": []
 }

From 469848ff4936772b03b7eaf86c6a52425649bc49 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Tue, 5 Apr 2016 21:06:53 +0200
Subject: [PATCH 08/27] implement k nearest neighbors classifier

---
 src/Phpml/Classifier/Classifier.php        |  8 ++--
 src/Phpml/Classifier/KNearestNeighbors.php | 47 ++++++++++++++++++----
 src/Phpml/Classifier/NaiveBayes.php        |  8 ++--
 3 files changed, 48 insertions(+), 15 deletions(-)

diff --git a/src/Phpml/Classifier/Classifier.php b/src/Phpml/Classifier/Classifier.php
index face7b2..6fad67a 100644
--- a/src/Phpml/Classifier/Classifier.php
+++ b/src/Phpml/Classifier/Classifier.php
@@ -7,15 +7,15 @@ namespace Phpml\Classifier;
 interface Classifier
 {
     /**
-     * @param array $features
+     * @param array $samples
      * @param array $labels
      */
-    public function train(array $features, array $labels);
+    public function train(array $samples, array $labels);
 
     /**
-     * @param mixed $feature
+     * @param array $sample
      *
      * @return mixed
      */
-    public function predict($feature);
+    public function predict(array $sample);
 }
diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
index e028d61..f454f9d 100644
--- a/src/Phpml/Classifier/KNearestNeighbors.php
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -4,6 +4,8 @@ declare (strict_types = 1);
 
 namespace Phpml\Classifier;
 
+use Phpml\Metric\Distance;
+
 class KNearestNeighbors implements Classifier
 {
     /**
@@ -14,7 +16,7 @@ class KNearestNeighbors implements Classifier
     /**
      * @var array
      */
-    private $features;
+    private $samples;
 
     /**
      * @var array
@@ -27,26 +29,57 @@ class KNearestNeighbors implements Classifier
     public function __construct(int $k = 3)
     {
         $this->k = $k;
-        $this->features = [];
+        $this->samples = [];
         $this->labels = [];
     }
 
     /**
-     * @param array $features
+     * @param array $samples
      * @param array $labels
      */
-    public function train(array $features, array $labels)
+    public function train(array $samples, array $labels)
     {
-        $this->features = $features;
+        $this->samples = $samples;
         $this->labels = $labels;
     }
 
     /**
-     * @param mixed $feature
+     * @param array $sample
      *
      * @return mixed
      */
-    public function predict($feature)
+    public function predict(array $sample)
     {
+        $distances = $this->kNeighborsDistances($sample);
+
+        $predictions = [];
+        foreach ($distances as $index => $distance) {
+            $predictions[$this->labels[$index]]++;
+        }
+
+        arsort($predictions);
+
+        return array_shift(array_keys($predictions));
+    }
+
+    /**
+     * @param array $sample
+     *
+     * @return array
+     *
+     * @throws \Phpml\Exception\InvalidArgumentException
+     */
+    private function kNeighborsDistances(array $sample): array
+    {
+        $distances = [];
+        foreach($this->samples as $index => $neighbor) {
+            $distances[$index] = Distance::euclidean($sample, $neighbor);
+            if(count($distances)==$this->k) {
+                break;
+            }
+        }
+        asort($distances);
+
+        return $distances;
     }
 }
diff --git a/src/Phpml/Classifier/NaiveBayes.php b/src/Phpml/Classifier/NaiveBayes.php
index ed6bb8c..c1cc902 100644
--- a/src/Phpml/Classifier/NaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes.php
@@ -7,19 +7,19 @@ namespace Phpml\Classifier;
 class NaiveBayes implements Classifier
 {
     /**
-     * @param array $features
+     * @param array $samples
      * @param array $labels
      */
-    public function train(array $features, array $labels)
+    public function train(array $samples, array $labels)
     {
     }
 
     /**
-     * @param mixed $feature
+     * @param array $sample
      *
      * @return mixed
      */
-    public function predict($feature)
+    public function predict(array $sample)
     {
     }
 }

From 7cbeaecffb76fbc7cbd76f8ddaca24b801c53ff2 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Tue, 5 Apr 2016 21:35:06 +0200
Subject: [PATCH 09/27] simple test for knn classifier

---
 src/Phpml/Classifier/KNearestNeighbors.php    | 17 ++++++-----
 .../Classifier/KNearestNeighborsTest.php      | 29 +++++++++++++++++++
 tests/Phpml/Metric/DistanceTest.php           |  6 ++--
 3 files changed, 41 insertions(+), 11 deletions(-)
 create mode 100644 tests/Phpml/Classifier/KNearestNeighborsTest.php

diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
index f454f9d..5a998d3 100644
--- a/src/Phpml/Classifier/KNearestNeighbors.php
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -52,14 +52,16 @@ class KNearestNeighbors implements Classifier
     {
         $distances = $this->kNeighborsDistances($sample);
 
-        $predictions = [];
+        $predictions = array_combine(array_values($this->labels), array_fill(0, count($this->labels), 0));
+
         foreach ($distances as $index => $distance) {
-            $predictions[$this->labels[$index]]++;
+            ++$predictions[$this->labels[$index]];
         }
 
         arsort($predictions);
+        reset($predictions);
 
-        return array_shift(array_keys($predictions));
+        return key($predictions);
     }
 
     /**
@@ -72,14 +74,13 @@ class KNearestNeighbors implements Classifier
     private function kNeighborsDistances(array $sample): array
     {
         $distances = [];
-        foreach($this->samples as $index => $neighbor) {
+
+        foreach ($this->samples as $index => $neighbor) {
             $distances[$index] = Distance::euclidean($sample, $neighbor);
-            if(count($distances)==$this->k) {
-                break;
-            }
         }
+
         asort($distances);
 
-        return $distances;
+        return array_slice($distances, 0, $this->k, true);
     }
 }
diff --git a/tests/Phpml/Classifier/KNearestNeighborsTest.php b/tests/Phpml/Classifier/KNearestNeighborsTest.php
new file mode 100644
index 0000000..2786ade
--- /dev/null
+++ b/tests/Phpml/Classifier/KNearestNeighborsTest.php
@@ -0,0 +1,29 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace tests\Classifier;
+
+use Phpml\Classifier\KNearestNeighbors;
+
+class KNearestNeighborsTest extends \PHPUnit_Framework_TestCase
+{
+    public function testPredictSimpleSampleWithDefaultK()
+    {
+        $samples = [[1, 3], [1, 4], [2, 4], [3, 1], [4, 1], [4, 2]];
+        $labels = ['a', 'a', 'a', 'b', 'b', 'b'];
+
+        $classifier = new KNearestNeighbors();
+        $classifier->train($samples, $labels);
+
+        $this->assertEquals('b', $classifier->predict([3, 2]));
+        $this->assertEquals('b', $classifier->predict([5, 1]));
+        $this->assertEquals('b', $classifier->predict([4, 3]));
+        $this->assertEquals('b', $classifier->predict([4, -5]));
+
+        $this->assertEquals('a', $classifier->predict([2, 3]));
+        $this->assertEquals('a', $classifier->predict([1, 2]));
+        $this->assertEquals('a', $classifier->predict([1, 5]));
+        $this->assertEquals('a', $classifier->predict([3, 10]));
+    }
+}
diff --git a/tests/Phpml/Metric/DistanceTest.php b/tests/Phpml/Metric/DistanceTest.php
index 249a9f8..b5fdc75 100644
--- a/tests/Phpml/Metric/DistanceTest.php
+++ b/tests/Phpml/Metric/DistanceTest.php
@@ -27,7 +27,7 @@ class DistanceTest extends \PHPUnit_Framework_TestCase
         $expectedDistance = 2;
         $actualDistance = Distance::euclidean($a, $b);
 
-        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
+        $this->assertEquals($expectedDistance, $actualDistance);
     }
 
     public function testCalculateEuclideanDistanceForTwoAndMoreDimension()
@@ -38,7 +38,7 @@ class DistanceTest extends \PHPUnit_Framework_TestCase
         $expectedDistance = 2.2360679774998;
         $actualDistance = Distance::euclidean($a, $b);
 
-        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
+        $this->assertEquals($expectedDistance, $actualDistance);
 
         $a = [6, 10, 3];
         $b = [2, 5, 5];
@@ -46,6 +46,6 @@ class DistanceTest extends \PHPUnit_Framework_TestCase
         $expectedDistance = 6.7082039324993694;
         $actualDistance = Distance::euclidean($a, $b);
 
-        \PHPUnit_Framework_Assert::assertEquals($expectedDistance, $actualDistance);
+        $this->assertEquals($expectedDistance, $actualDistance);
     }
 }

From e521fb8f803b1855f24336f95328e99b98c24eab Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Wed, 6 Apr 2016 21:46:17 +0200
Subject: [PATCH 10/27] iris dataset loader

---
 src/Phpml/Dataset/Dataset.php            | 58 ++++++++++++++++++++++++
 src/Phpml/Dataset/Iris.php               | 11 +++++
 src/Phpml/Exception/DatasetException.php | 22 +++++++++
 tests/Phpml/Dataset/IrisTest.php         | 23 ++++++++++
 4 files changed, 114 insertions(+)
 create mode 100644 src/Phpml/Exception/DatasetException.php
 create mode 100644 tests/Phpml/Dataset/IrisTest.php

diff --git a/src/Phpml/Dataset/Dataset.php b/src/Phpml/Dataset/Dataset.php
index 316ee1d..cf1574e 100644
--- a/src/Phpml/Dataset/Dataset.php
+++ b/src/Phpml/Dataset/Dataset.php
@@ -1,9 +1,67 @@
 <?php
 
+declare (strict_types = 1);
+
+namespace Phpml\Dataset;
+
+use Phpml\Exception\DatasetException;
+
 abstract class Dataset
 {
     /**
      * @var string
      */
     protected $filepath;
+
+    /**
+     * @var array
+     */
+    private $samples = [];
+
+    /**
+     * @var array
+     */
+    private $lables = [];
+    
+    public function __construct()
+    {
+        $filepath =  dirname(__FILE__) . '/../../../data/' . $this->filepath;
+
+        if(!file_exists($filepath)) {
+            throw DatasetException::missingFile(basename($filepath));
+        }
+
+        $row = 0;
+        if (($handle = fopen($filepath, "r")) !== FALSE) {
+            while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) {
+                $row++;
+                if($row==1) {
+                    continue;
+                }
+                $this->samples[] = array_slice($data, 0, 4);
+                $this->lables[] = $data[4];
+            }
+            fclose($handle);
+        } else {
+            throw DatasetException::cantOpenFile(basename($filepath));
+        }
+
+    }
+
+    /**
+     * @return array
+     */
+    public function getSamples()
+    {
+        return $this->samples;
+    }
+
+    /**
+     * @return array
+     */
+    public function getLabels()
+    {
+        return $this->lables;
+    }
+
 }
diff --git a/src/Phpml/Dataset/Iris.php b/src/Phpml/Dataset/Iris.php
index 0565558..b862a74 100644
--- a/src/Phpml/Dataset/Iris.php
+++ b/src/Phpml/Dataset/Iris.php
@@ -1,9 +1,20 @@
 <?php
 
+declare (strict_types = 1);
+
+namespace Phpml\Dataset;
+
+/**
+ * Classes: 3
+ * Samples per class: 50
+ * Samples total: 150
+ * Features per sample: 4
+ */
 class Iris extends Dataset
 {
     /**
      * @var string
      */
     protected $filepath = 'iris.csv';
+
 }
diff --git a/src/Phpml/Exception/DatasetException.php b/src/Phpml/Exception/DatasetException.php
new file mode 100644
index 0000000..f12c979
--- /dev/null
+++ b/src/Phpml/Exception/DatasetException.php
@@ -0,0 +1,22 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace Phpml\Exception;
+
+class DatasetException extends \Exception
+{
+    /**
+     * @return DatasetException
+     */
+    public static function missingFile($filepath)
+    {
+        return new self(sprintf('Dataset file %s missing.', $filepath));
+    }
+
+    public static function cantOpenFile($filepath)
+    {
+        return new self(sprintf('Dataset file %s can\'t be open.', $filepath));
+    }
+
+}
diff --git a/tests/Phpml/Dataset/IrisTest.php b/tests/Phpml/Dataset/IrisTest.php
new file mode 100644
index 0000000..6bce532
--- /dev/null
+++ b/tests/Phpml/Dataset/IrisTest.php
@@ -0,0 +1,23 @@
+<?php
+declare(strict_types = 1);
+
+namespace tests\Phpml\Dataset;
+
+use Phpml\Dataset\Iris;
+
+class IrisTest extends \PHPUnit_Framework_TestCase
+{
+
+    public function testLoadingIrisDataset()
+    {
+        $iris = new Iris();
+
+        // whole dataset
+        $this->assertEquals(150, count($iris->getSamples()));
+        $this->assertEquals(150, count($iris->getLabels()));
+
+        // one sample features count
+        $this->assertEquals(4, count($iris->getSamples()[0]));
+    }
+    
+}
\ No newline at end of file

From 649cbdb9a609bb125d6a3d87be81111bfdde618b Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Wed, 6 Apr 2016 22:38:08 +0200
Subject: [PATCH 11/27] prepare cross validation random splitter

---
 src/Phpml/Dataset/CsvDataset.php              | 65 +++++++++++++++++++
 src/Phpml/Dataset/Dataset.php                 | 57 ++--------------
 src/Phpml/Dataset/Iris.php                    |  5 +-
 src/Phpml/Exception/DatasetException.php      |  1 -
 .../Exception/InvalidArgumentException.php    | 10 +++
 tests/Phpml/Dataset/IrisTest.php              |  7 +-
 6 files changed, 84 insertions(+), 61 deletions(-)
 create mode 100644 src/Phpml/Dataset/CsvDataset.php

diff --git a/src/Phpml/Dataset/CsvDataset.php b/src/Phpml/Dataset/CsvDataset.php
new file mode 100644
index 0000000..6fa6b42
--- /dev/null
+++ b/src/Phpml/Dataset/CsvDataset.php
@@ -0,0 +1,65 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace Phpml\Dataset;
+
+use Phpml\Exception\DatasetException;
+
+abstract class CsvDataset implements Dataset
+{
+    /**
+     * @var string
+     */
+    protected $filepath;
+
+    /**
+     * @var array
+     */
+    private $samples = [];
+
+    /**
+     * @var array
+     */
+    private $lables = [];
+
+    public function __construct()
+    {
+        $filepath = dirname(__FILE__).'/../../../data/'.$this->filepath;
+
+        if (!file_exists($filepath)) {
+            throw DatasetException::missingFile(basename($filepath));
+        }
+
+        $row = 0;
+        if (($handle = fopen($filepath, 'r')) !== false) {
+            while (($data = fgetcsv($handle, 1000, ',')) !== false) {
+                ++$row;
+                if ($row == 1) {
+                    continue;
+                }
+                $this->samples[] = array_slice($data, 0, 4);
+                $this->lables[] = $data[4];
+            }
+            fclose($handle);
+        } else {
+            throw DatasetException::cantOpenFile(basename($filepath));
+        }
+    }
+
+    /**
+     * @return array
+     */
+    public function getSamples(): array
+    {
+        return $this->samples;
+    }
+
+    /**
+     * @return array
+     */
+    public function getLabels(): array
+    {
+        return $this->lables;
+    }
+}
diff --git a/src/Phpml/Dataset/Dataset.php b/src/Phpml/Dataset/Dataset.php
index cf1574e..4e04931 100644
--- a/src/Phpml/Dataset/Dataset.php
+++ b/src/Phpml/Dataset/Dataset.php
@@ -4,64 +4,15 @@ declare (strict_types = 1);
 
 namespace Phpml\Dataset;
 
-use Phpml\Exception\DatasetException;
-
-abstract class Dataset
+interface Dataset
 {
     /**
-     * @var string
+     * @return array
      */
-    protected $filepath;
-
-    /**
-     * @var array
-     */
-    private $samples = [];
-
-    /**
-     * @var array
-     */
-    private $lables = [];
-    
-    public function __construct()
-    {
-        $filepath =  dirname(__FILE__) . '/../../../data/' . $this->filepath;
-
-        if(!file_exists($filepath)) {
-            throw DatasetException::missingFile(basename($filepath));
-        }
-
-        $row = 0;
-        if (($handle = fopen($filepath, "r")) !== FALSE) {
-            while (($data = fgetcsv($handle, 1000, ",")) !== FALSE) {
-                $row++;
-                if($row==1) {
-                    continue;
-                }
-                $this->samples[] = array_slice($data, 0, 4);
-                $this->lables[] = $data[4];
-            }
-            fclose($handle);
-        } else {
-            throw DatasetException::cantOpenFile(basename($filepath));
-        }
-
-    }
+    public function getSamples(): array;
 
     /**
      * @return array
      */
-    public function getSamples()
-    {
-        return $this->samples;
-    }
-
-    /**
-     * @return array
-     */
-    public function getLabels()
-    {
-        return $this->lables;
-    }
-
+    public function getLabels(): array;
 }
diff --git a/src/Phpml/Dataset/Iris.php b/src/Phpml/Dataset/Iris.php
index b862a74..1353989 100644
--- a/src/Phpml/Dataset/Iris.php
+++ b/src/Phpml/Dataset/Iris.php
@@ -8,13 +8,12 @@ namespace Phpml\Dataset;
  * Classes: 3
  * Samples per class: 50
  * Samples total: 150
- * Features per sample: 4
+ * Features per sample: 4.
  */
-class Iris extends Dataset
+class Iris extends CsvDataset
 {
     /**
      * @var string
      */
     protected $filepath = 'iris.csv';
-
 }
diff --git a/src/Phpml/Exception/DatasetException.php b/src/Phpml/Exception/DatasetException.php
index f12c979..7b99e64 100644
--- a/src/Phpml/Exception/DatasetException.php
+++ b/src/Phpml/Exception/DatasetException.php
@@ -18,5 +18,4 @@ class DatasetException extends \Exception
     {
         return new self(sprintf('Dataset file %s can\'t be open.', $filepath));
     }
-
 }
diff --git a/src/Phpml/Exception/InvalidArgumentException.php b/src/Phpml/Exception/InvalidArgumentException.php
index 70bf918..48006fa 100644
--- a/src/Phpml/Exception/InvalidArgumentException.php
+++ b/src/Phpml/Exception/InvalidArgumentException.php
@@ -13,4 +13,14 @@ class InvalidArgumentException extends \Exception
     {
         return new self('Size of given arguments not match');
     }
+
+    /**
+     * @param $name
+     *
+     * @return InvalidArgumentException
+     */
+    public static function percentNotInRange($name)
+    {
+        return new self(sprintf('%s must be between 0.0 and 1.0', $name));
+    }
 }
diff --git a/tests/Phpml/Dataset/IrisTest.php b/tests/Phpml/Dataset/IrisTest.php
index 6bce532..99e19ad 100644
--- a/tests/Phpml/Dataset/IrisTest.php
+++ b/tests/Phpml/Dataset/IrisTest.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace tests\Phpml\Dataset;
 
@@ -7,7 +8,6 @@ use Phpml\Dataset\Iris;
 
 class IrisTest extends \PHPUnit_Framework_TestCase
 {
-
     public function testLoadingIrisDataset()
     {
         $iris = new Iris();
@@ -19,5 +19,4 @@ class IrisTest extends \PHPUnit_Framework_TestCase
         // one sample features count
         $this->assertEquals(4, count($iris->getSamples()[0]));
     }
-    
-}
\ No newline at end of file
+}

From c3f98e409382213ca3b7c66064403951d98b6487 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Wed, 6 Apr 2016 22:38:27 +0200
Subject: [PATCH 12/27] random splitter skeleton

---
 src/Phpml/CrossValidation/RandomSplit.php | 72 +++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100644 src/Phpml/CrossValidation/RandomSplit.php

diff --git a/src/Phpml/CrossValidation/RandomSplit.php b/src/Phpml/CrossValidation/RandomSplit.php
new file mode 100644
index 0000000..3cc6c05
--- /dev/null
+++ b/src/Phpml/CrossValidation/RandomSplit.php
@@ -0,0 +1,72 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace Phpml\CrossValidation;
+
+use Phpml\Dataset\Dataset;
+use Phpml\Exception\InvalidArgumentException;
+
+class RandomSplit
+{
+    /**
+     * @var array
+     */
+    private $trainSamples = [];
+
+    /**
+     * @var array
+     */
+    private $testSamples = [];
+
+    /**
+     * @var array
+     */
+    private $trainLabels = [];
+
+    /**
+     * @var array
+     */
+    private $testLabels = [];
+
+    public function __construct(Dataset $dataset, float $testSize = 0.3)
+    {
+        if (0 > $testSize || 1 < $testSize) {
+            throw InvalidArgumentException::percentNotInRange('testSize');
+        }
+
+        // TODO: implement this !
+    }
+
+    /**
+     * @return array
+     */
+    public function getTrainSamples()
+    {
+        return $this->trainSamples;
+    }
+
+    /**
+     * @return array
+     */
+    public function getTestSamples()
+    {
+        return $this->testSamples;
+    }
+
+    /**
+     * @return array
+     */
+    public function getTrainLabels()
+    {
+        return $this->trainLabels;
+    }
+
+    /**
+     * @return array
+     */
+    public function getTestLabels()
+    {
+        return $this->testLabels;
+    }
+}

From bbcc8a3e685290bea034186d0458fb9c77846fd6 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 22:12:36 +0200
Subject: [PATCH 13/27] random split implementation and tests

---
 src/Phpml/CrossValidation/RandomSplit.php     | 39 +++++++-
 src/Phpml/Dataset/ArrayDataset.php            | 46 +++++++++
 src/Phpml/Dataset/CsvDataset.php              |  6 +-
 src/Phpml/Dataset/{ => Demo}/Iris.php         |  4 +-
 .../Phpml/CrossValidation/RandomSplitTest.php | 95 +++++++++++++++++++
 tests/Phpml/Dataset/{ => Demo}/IrisTest.php   |  4 +-
 6 files changed, 185 insertions(+), 9 deletions(-)
 create mode 100644 src/Phpml/Dataset/ArrayDataset.php
 rename src/Phpml/Dataset/{ => Demo}/Iris.php (79%)
 create mode 100644 tests/Phpml/CrossValidation/RandomSplitTest.php
 rename tests/Phpml/Dataset/{ => Demo}/IrisTest.php (86%)

diff --git a/src/Phpml/CrossValidation/RandomSplit.php b/src/Phpml/CrossValidation/RandomSplit.php
index 3cc6c05..4e2ecc9 100644
--- a/src/Phpml/CrossValidation/RandomSplit.php
+++ b/src/Phpml/CrossValidation/RandomSplit.php
@@ -29,13 +29,34 @@ class RandomSplit
      */
     private $testLabels = [];
 
-    public function __construct(Dataset $dataset, float $testSize = 0.3)
+    /**
+     * @param Dataset $dataset
+     * @param float $testSize
+     * @param int $seed
+     *
+     * @throws InvalidArgumentException
+     */
+    public function __construct(Dataset $dataset, float $testSize = 0.3, int $seed = null)
     {
-        if (0 > $testSize || 1 < $testSize) {
+        if (0 >= $testSize || 1 <= $testSize) {
             throw InvalidArgumentException::percentNotInRange('testSize');
         }
+        $this->seedGenerator($seed);
 
-        // TODO: implement this !
+        $samples = $dataset->getSamples();
+        $labels = $dataset->getLabels();
+        $datasetSize = count($samples);
+
+        for($i=$datasetSize; $i>0; $i--) {
+            $key = mt_rand(0, $datasetSize-1);
+            $setName = count($this->testSamples) / $datasetSize >= $testSize ? 'train' : 'test';
+
+            $this->{$setName.'Samples'}[] = $samples[$key];
+            $this->{$setName.'Labels'}[] = $labels[$key];
+
+            $samples = array_values($samples);
+            $labels = array_values($labels);
+        }
     }
 
     /**
@@ -69,4 +90,16 @@ class RandomSplit
     {
         return $this->testLabels;
     }
+
+    /**
+     * @param int|null $seed
+     */
+    private function seedGenerator(int $seed = null)
+    {
+        if (null === $seed) {
+            mt_srand();
+        } else {
+            mt_srand($seed);
+        }
+    }
 }
diff --git a/src/Phpml/Dataset/ArrayDataset.php b/src/Phpml/Dataset/ArrayDataset.php
new file mode 100644
index 0000000..85f9914
--- /dev/null
+++ b/src/Phpml/Dataset/ArrayDataset.php
@@ -0,0 +1,46 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Dataset;
+
+class ArrayDataset implements Dataset
+{
+
+    /**
+     * @var array
+     */
+    private $samples = [];
+
+    /**
+     * @var array
+     */
+    private $labels = [];
+
+    /**
+     * @param array $samples
+     * @param array $labels
+     */
+    public function __construct(array $samples, array $labels)
+    {
+        $this->samples = $samples;
+        $this->labels = $labels;
+    }
+
+
+    /**
+     * @return array
+     */
+    public function getSamples(): array
+    {
+        return $this->samples;
+    }
+
+    /**
+     * @return array
+     */
+    public function getLabels(): array
+    {
+        return $this->labels;
+    }
+    
+}
diff --git a/src/Phpml/Dataset/CsvDataset.php b/src/Phpml/Dataset/CsvDataset.php
index 6fa6b42..c21ac97 100644
--- a/src/Phpml/Dataset/CsvDataset.php
+++ b/src/Phpml/Dataset/CsvDataset.php
@@ -21,7 +21,7 @@ abstract class CsvDataset implements Dataset
     /**
      * @var array
      */
-    private $lables = [];
+    private $labels = [];
 
     public function __construct()
     {
@@ -39,7 +39,7 @@ abstract class CsvDataset implements Dataset
                     continue;
                 }
                 $this->samples[] = array_slice($data, 0, 4);
-                $this->lables[] = $data[4];
+                $this->labels[] = $data[4];
             }
             fclose($handle);
         } else {
@@ -60,6 +60,6 @@ abstract class CsvDataset implements Dataset
      */
     public function getLabels(): array
     {
-        return $this->lables;
+        return $this->labels;
     }
 }
diff --git a/src/Phpml/Dataset/Iris.php b/src/Phpml/Dataset/Demo/Iris.php
similarity index 79%
rename from src/Phpml/Dataset/Iris.php
rename to src/Phpml/Dataset/Demo/Iris.php
index 1353989..d544a55 100644
--- a/src/Phpml/Dataset/Iris.php
+++ b/src/Phpml/Dataset/Demo/Iris.php
@@ -2,7 +2,9 @@
 
 declare (strict_types = 1);
 
-namespace Phpml\Dataset;
+namespace Phpml\Dataset\Demo;
+
+use Phpml\Dataset\CsvDataset;
 
 /**
  * Classes: 3
diff --git a/tests/Phpml/CrossValidation/RandomSplitTest.php b/tests/Phpml/CrossValidation/RandomSplitTest.php
new file mode 100644
index 0000000..cbbd497
--- /dev/null
+++ b/tests/Phpml/CrossValidation/RandomSplitTest.php
@@ -0,0 +1,95 @@
+<?php
+declare(strict_types = 1);
+
+namespace tests\Phpml\CrossValidation;
+
+use Phpml\CrossValidation\RandomSplit;
+use Phpml\Dataset\ArrayDataset;
+
+class RandomSplitTest extends \PHPUnit_Framework_TestCase
+{
+
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnToSmallTestSize()
+    {
+        new RandomSplit(new ArrayDataset([], []), 0);
+    }
+
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnToBigTestSize()
+    {
+        new RandomSplit(new ArrayDataset([], []), 1);
+    }
+
+    public function testDatasetRandomSplitWithoutSeed()
+    {
+        $dataset = new ArrayDataset(
+            $samples = [[1], [2], [3], [4]],
+            $labels = ['a', 'a', 'b', 'b']
+        );
+
+        $randomSplit1 = new RandomSplit($dataset, 0.5);
+
+        $this->assertEquals(2, count($randomSplit1->getTestSamples()));
+        $this->assertEquals(2, count($randomSplit1->getTrainSamples()));
+
+        $randomSplit2 = new RandomSplit($dataset, 0.25);
+
+        $this->assertEquals(1, count($randomSplit2->getTestSamples()));
+        $this->assertEquals(3, count($randomSplit2->getTrainSamples()));
+    }
+
+    public function testDatasetRandomSplitWithSameSeed()
+    {
+        $dataset = new ArrayDataset(
+            $samples = [[1], [2], [3], [4], [5], [6], [7], [8]],
+            $labels = ['a', 'a', 'a', 'a', 'b', 'b', 'b', 'b']
+        );
+
+        $seed = 123;
+
+        $randomSplit1 = new RandomSplit($dataset, 0.5, $seed);
+        $randomSplit2 = new RandomSplit($dataset, 0.5, $seed);
+
+        $this->assertEquals($randomSplit1->getTestLabels(), $randomSplit2->getTestLabels());
+        $this->assertEquals($randomSplit1->getTestSamples(), $randomSplit2->getTestSamples());
+        $this->assertEquals($randomSplit1->getTrainLabels(), $randomSplit2->getTrainLabels());
+        $this->assertEquals($randomSplit1->getTrainSamples(), $randomSplit2->getTrainSamples());
+    }
+
+    public function testDatasetRandomSplitWithDifferentSeed()
+    {
+        $dataset = new ArrayDataset(
+            $samples = [[1], [2], [3], [4], [5], [6], [7], [8]],
+            $labels = ['a', 'a', 'a', 'a', 'b', 'b', 'b', 'b']
+        );
+
+        $randomSplit1 = new RandomSplit($dataset, 0.5, 4321);
+        $randomSplit2 = new RandomSplit($dataset, 0.5, 1234);
+
+        $this->assertNotEquals($randomSplit1->getTestLabels(), $randomSplit2->getTestLabels());
+        $this->assertNotEquals($randomSplit1->getTestSamples(), $randomSplit2->getTestSamples());
+        $this->assertNotEquals($randomSplit1->getTrainLabels(), $randomSplit2->getTrainLabels());
+        $this->assertNotEquals($randomSplit1->getTrainSamples(), $randomSplit2->getTrainSamples());
+    }
+
+    public function testRandomSplitCorrectSampleAndLabelPosition()
+    {
+        $dataset = new ArrayDataset(
+            $samples = [[1], [2], [3], [4]],
+            $labels = [1, 2, 3, 4]
+        );
+
+        $randomSplit = new RandomSplit($dataset, 0.5);
+
+        $this->assertEquals($randomSplit->getTestSamples()[0][0], $randomSplit->getTestLabels()[0]);
+        $this->assertEquals($randomSplit->getTestSamples()[1][0], $randomSplit->getTestLabels()[1]);
+        $this->assertEquals($randomSplit->getTrainSamples()[0][0], $randomSplit->getTrainLabels()[0]);
+        $this->assertEquals($randomSplit->getTrainSamples()[1][0], $randomSplit->getTrainLabels()[1]);
+    }
+    
+}
\ No newline at end of file
diff --git a/tests/Phpml/Dataset/IrisTest.php b/tests/Phpml/Dataset/Demo/IrisTest.php
similarity index 86%
rename from tests/Phpml/Dataset/IrisTest.php
rename to tests/Phpml/Dataset/Demo/IrisTest.php
index 99e19ad..1f0da90 100644
--- a/tests/Phpml/Dataset/IrisTest.php
+++ b/tests/Phpml/Dataset/Demo/IrisTest.php
@@ -2,9 +2,9 @@
 
 declare (strict_types = 1);
 
-namespace tests\Phpml\Dataset;
+namespace tests\Phpml\Dataset\Demo;
 
-use Phpml\Dataset\Iris;
+use Phpml\Dataset\Demo\Iris;
 
 class IrisTest extends \PHPUnit_Framework_TestCase
 {

From d3247ebccb855a87118816c8a8d19b93bcd94e4d Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 22:13:31 +0200
Subject: [PATCH 14/27] random split implementation and tests

---
 src/Phpml/Dataset/ArrayDataset.php | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/src/Phpml/Dataset/ArrayDataset.php b/src/Phpml/Dataset/ArrayDataset.php
index 85f9914..b2e09b7 100644
--- a/src/Phpml/Dataset/ArrayDataset.php
+++ b/src/Phpml/Dataset/ArrayDataset.php
@@ -3,6 +3,8 @@ declare(strict_types = 1);
 
 namespace Phpml\Dataset;
 
+use Phpml\Exception\InvalidArgumentException;
+
 class ArrayDataset implements Dataset
 {
 
@@ -19,9 +21,15 @@ class ArrayDataset implements Dataset
     /**
      * @param array $samples
      * @param array $labels
+     *
+     * @throws InvalidArgumentException
      */
     public function __construct(array $samples, array $labels)
     {
+        if (count($samples) != count($labels)) {
+            throw InvalidArgumentException::sizeNotMatch();
+        }
+
         $this->samples = $samples;
         $this->labels = $labels;
     }

From a20f474324b4239753616d0527d02f8cf0d4de4b Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 22:19:04 +0200
Subject: [PATCH 15/27] refactor csv dataset definition

---
 src/Phpml/Dataset/ArrayDataset.php |  4 ++--
 src/Phpml/Dataset/CsvDataset.php   | 33 +++++-------------------------
 src/Phpml/Dataset/Demo/Iris.php    |  8 ++++++--
 3 files changed, 13 insertions(+), 32 deletions(-)

diff --git a/src/Phpml/Dataset/ArrayDataset.php b/src/Phpml/Dataset/ArrayDataset.php
index b2e09b7..580df0a 100644
--- a/src/Phpml/Dataset/ArrayDataset.php
+++ b/src/Phpml/Dataset/ArrayDataset.php
@@ -11,12 +11,12 @@ class ArrayDataset implements Dataset
     /**
      * @var array
      */
-    private $samples = [];
+    protected $samples = [];
 
     /**
      * @var array
      */
-    private $labels = [];
+    protected $labels = [];
 
     /**
      * @param array $samples
diff --git a/src/Phpml/Dataset/CsvDataset.php b/src/Phpml/Dataset/CsvDataset.php
index c21ac97..de540c9 100644
--- a/src/Phpml/Dataset/CsvDataset.php
+++ b/src/Phpml/Dataset/CsvDataset.php
@@ -6,7 +6,7 @@ namespace Phpml\Dataset;
 
 use Phpml\Exception\DatasetException;
 
-abstract class CsvDataset implements Dataset
+class CsvDataset extends ArrayDataset
 {
     /**
      * @var string
@@ -14,19 +14,12 @@ abstract class CsvDataset implements Dataset
     protected $filepath;
 
     /**
-     * @var array
+     * @param string|null $filepath
+     *
+     * @throws DatasetException
      */
-    private $samples = [];
-
-    /**
-     * @var array
-     */
-    private $labels = [];
-
-    public function __construct()
+    public function __construct(string $filepath = null)
     {
-        $filepath = dirname(__FILE__).'/../../../data/'.$this->filepath;
-
         if (!file_exists($filepath)) {
             throw DatasetException::missingFile(basename($filepath));
         }
@@ -46,20 +39,4 @@ abstract class CsvDataset implements Dataset
             throw DatasetException::cantOpenFile(basename($filepath));
         }
     }
-
-    /**
-     * @return array
-     */
-    public function getSamples(): array
-    {
-        return $this->samples;
-    }
-
-    /**
-     * @return array
-     */
-    public function getLabels(): array
-    {
-        return $this->labels;
-    }
 }
diff --git a/src/Phpml/Dataset/Demo/Iris.php b/src/Phpml/Dataset/Demo/Iris.php
index d544a55..5a4789e 100644
--- a/src/Phpml/Dataset/Demo/Iris.php
+++ b/src/Phpml/Dataset/Demo/Iris.php
@@ -15,7 +15,11 @@ use Phpml\Dataset\CsvDataset;
 class Iris extends CsvDataset
 {
     /**
-     * @var string
+     * @param string|null $filepath
      */
-    protected $filepath = 'iris.csv';
+    public function __construct(string $filepath = null)
+    {
+        $filepath = dirname(__FILE__).'/../../../../data/iris.csv';
+        parent::__construct($filepath);
+    }
 }

From 9c18a5a22d67937a79b834fd325c8cb4b389879e Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 22:35:49 +0200
Subject: [PATCH 16/27] add tests for datasets

---
 src/Phpml/CrossValidation/RandomSplit.php       |  8 ++++----
 src/Phpml/Dataset/ArrayDataset.php              |  6 ++----
 src/Phpml/Dataset/CsvDataset.php                | 12 +++++++-----
 src/Phpml/Dataset/Demo/Iris.php                 |  7 ++-----
 tests/Phpml/CrossValidation/RandomSplitTest.php |  7 +++----
 5 files changed, 18 insertions(+), 22 deletions(-)

diff --git a/src/Phpml/CrossValidation/RandomSplit.php b/src/Phpml/CrossValidation/RandomSplit.php
index 4e2ecc9..c5a24bd 100644
--- a/src/Phpml/CrossValidation/RandomSplit.php
+++ b/src/Phpml/CrossValidation/RandomSplit.php
@@ -31,8 +31,8 @@ class RandomSplit
 
     /**
      * @param Dataset $dataset
-     * @param float $testSize
-     * @param int $seed
+     * @param float   $testSize
+     * @param int     $seed
      *
      * @throws InvalidArgumentException
      */
@@ -47,8 +47,8 @@ class RandomSplit
         $labels = $dataset->getLabels();
         $datasetSize = count($samples);
 
-        for($i=$datasetSize; $i>0; $i--) {
-            $key = mt_rand(0, $datasetSize-1);
+        for ($i = $datasetSize; $i > 0; --$i) {
+            $key = mt_rand(0, $datasetSize - 1);
             $setName = count($this->testSamples) / $datasetSize >= $testSize ? 'train' : 'test';
 
             $this->{$setName.'Samples'}[] = $samples[$key];
diff --git a/src/Phpml/Dataset/ArrayDataset.php b/src/Phpml/Dataset/ArrayDataset.php
index 580df0a..d117122 100644
--- a/src/Phpml/Dataset/ArrayDataset.php
+++ b/src/Phpml/Dataset/ArrayDataset.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Dataset;
 
@@ -7,7 +8,6 @@ use Phpml\Exception\InvalidArgumentException;
 
 class ArrayDataset implements Dataset
 {
-
     /**
      * @var array
      */
@@ -34,7 +34,6 @@ class ArrayDataset implements Dataset
         $this->labels = $labels;
     }
 
-
     /**
      * @return array
      */
@@ -50,5 +49,4 @@ class ArrayDataset implements Dataset
     {
         return $this->labels;
     }
-    
 }
diff --git a/src/Phpml/Dataset/CsvDataset.php b/src/Phpml/Dataset/CsvDataset.php
index de540c9..e6dafd2 100644
--- a/src/Phpml/Dataset/CsvDataset.php
+++ b/src/Phpml/Dataset/CsvDataset.php
@@ -14,11 +14,13 @@ class CsvDataset extends ArrayDataset
     protected $filepath;
 
     /**
-     * @param string|null $filepath
+     * @param string $filepath
+     * @param int    $features
+     * @param bool   $headingRow
      *
      * @throws DatasetException
      */
-    public function __construct(string $filepath = null)
+    public function __construct(string $filepath, int $features, bool $headingRow = true)
     {
         if (!file_exists($filepath)) {
             throw DatasetException::missingFile(basename($filepath));
@@ -28,11 +30,11 @@ class CsvDataset extends ArrayDataset
         if (($handle = fopen($filepath, 'r')) !== false) {
             while (($data = fgetcsv($handle, 1000, ',')) !== false) {
                 ++$row;
-                if ($row == 1) {
+                if ($headingRow && $row == 1) {
                     continue;
                 }
-                $this->samples[] = array_slice($data, 0, 4);
-                $this->labels[] = $data[4];
+                $this->samples[] = array_slice($data, 0, $features);
+                $this->labels[] = $data[$features];
             }
             fclose($handle);
         } else {
diff --git a/src/Phpml/Dataset/Demo/Iris.php b/src/Phpml/Dataset/Demo/Iris.php
index 5a4789e..923f0ba 100644
--- a/src/Phpml/Dataset/Demo/Iris.php
+++ b/src/Phpml/Dataset/Demo/Iris.php
@@ -14,12 +14,9 @@ use Phpml\Dataset\CsvDataset;
  */
 class Iris extends CsvDataset
 {
-    /**
-     * @param string|null $filepath
-     */
-    public function __construct(string $filepath = null)
+    public function __construct()
     {
         $filepath = dirname(__FILE__).'/../../../../data/iris.csv';
-        parent::__construct($filepath);
+        parent::__construct($filepath, 4, true);
     }
 }
diff --git a/tests/Phpml/CrossValidation/RandomSplitTest.php b/tests/Phpml/CrossValidation/RandomSplitTest.php
index cbbd497..e6ae30e 100644
--- a/tests/Phpml/CrossValidation/RandomSplitTest.php
+++ b/tests/Phpml/CrossValidation/RandomSplitTest.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace tests\Phpml\CrossValidation;
 
@@ -8,7 +9,6 @@ use Phpml\Dataset\ArrayDataset;
 
 class RandomSplitTest extends \PHPUnit_Framework_TestCase
 {
-
     /**
      * @expectedException \Phpml\Exception\InvalidArgumentException
      */
@@ -91,5 +91,4 @@ class RandomSplitTest extends \PHPUnit_Framework_TestCase
         $this->assertEquals($randomSplit->getTrainSamples()[0][0], $randomSplit->getTrainLabels()[0]);
         $this->assertEquals($randomSplit->getTrainSamples()[1][0], $randomSplit->getTrainLabels()[1]);
     }
-    
-}
\ No newline at end of file
+}

From db9d57cd221e182aa086d69598b91ffbe9873072 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 22:36:02 +0200
Subject: [PATCH 17/27] add tests for datasets

---
 tests/Phpml/Dataset/ArrayDatasetTest.php  | 29 +++++++++++++++++++++++
 tests/Phpml/Dataset/CsvDatasetTest.php    | 28 ++++++++++++++++++++++
 tests/Phpml/Dataset/Resources/dataset.csv | 11 +++++++++
 3 files changed, 68 insertions(+)
 create mode 100644 tests/Phpml/Dataset/ArrayDatasetTest.php
 create mode 100644 tests/Phpml/Dataset/CsvDatasetTest.php
 create mode 100644 tests/Phpml/Dataset/Resources/dataset.csv

diff --git a/tests/Phpml/Dataset/ArrayDatasetTest.php b/tests/Phpml/Dataset/ArrayDatasetTest.php
new file mode 100644
index 0000000..7244b3e
--- /dev/null
+++ b/tests/Phpml/Dataset/ArrayDatasetTest.php
@@ -0,0 +1,29 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace tests\Phpml\Dataset;
+
+use Phpml\Dataset\ArrayDataset;
+
+class ArrayDatasetTest extends \PHPUnit_Framework_TestCase
+{
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnInvalidArgumentsSize()
+    {
+        new ArrayDataset([0, 1], [0]);
+    }
+
+    public function testArrayDataset()
+    {
+        $dataset = new ArrayDataset(
+            $samples = [[1], [2], [3], [4]],
+            $labels = ['a', 'a', 'b', 'b']
+        );
+
+        $this->assertEquals($samples, $dataset->getSamples());
+        $this->assertEquals($labels, $dataset->getLabels());
+    }
+}
diff --git a/tests/Phpml/Dataset/CsvDatasetTest.php b/tests/Phpml/Dataset/CsvDatasetTest.php
new file mode 100644
index 0000000..db87d62
--- /dev/null
+++ b/tests/Phpml/Dataset/CsvDatasetTest.php
@@ -0,0 +1,28 @@
+<?php
+
+declare (strict_types = 1);
+
+namespace tests\Phpml\Dataset;
+
+use Phpml\Dataset\CsvDataset;
+
+class CsvDatasetTest extends \PHPUnit_Framework_TestCase
+{
+    /**
+     * @expectedException \Phpml\Exception\DatasetException
+     */
+    public function testThrowExceptionOnMissingFile()
+    {
+        new CsvDataset('missingFile', 3);
+    }
+
+    public function testSampleCsvDataset()
+    {
+        $filePath = dirname(__FILE__).'/Resources/dataset.csv';
+
+        $dataset = new CsvDataset($filePath, 2, true);
+
+        $this->assertEquals(10, count($dataset->getSamples()));
+        $this->assertEquals(10, count($dataset->getLabels()));
+    }
+}
diff --git a/tests/Phpml/Dataset/Resources/dataset.csv b/tests/Phpml/Dataset/Resources/dataset.csv
new file mode 100644
index 0000000..fcf0121
--- /dev/null
+++ b/tests/Phpml/Dataset/Resources/dataset.csv
@@ -0,0 +1,11 @@
+feature1,feature2,label
+1,1,a
+2,1,b
+3,1,c
+4,5,a
+2,4,a
+1,5,a
+2,6,b
+3,7,c
+4,4,a
+2,0,a
\ No newline at end of file

From 9899da7143965f1dfe49c4f3ebc317297fef7ce2 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 23:08:04 +0200
Subject: [PATCH 18/27] remove count from test condition

---
 composer.json                 | 2 +-
 src/Phpml/Metric/Distance.php | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/composer.json b/composer.json
index 66083b2..d3569d0 100644
--- a/composer.json
+++ b/composer.json
@@ -1,7 +1,7 @@
 {
     "name": "php-ai/php-ml",
     "type": "library",
-    "description": "PHP Machine learning library",
+    "description": "PHP Machine Learning library",
     "license": "MIT",
     "keywords": ["machine learning","pattern recognition","computational learning theory","artificial intelligence"],
     "homepage": "https://github.com/php-ai/php-ml",
diff --git a/src/Phpml/Metric/Distance.php b/src/Phpml/Metric/Distance.php
index e0dce2d..1b92cef 100644
--- a/src/Phpml/Metric/Distance.php
+++ b/src/Phpml/Metric/Distance.php
@@ -23,8 +23,9 @@ class Distance
         }
 
         $distance = 0;
+        $count = count($a);
 
-        for ($i = 0; $i < count($a); ++$i) {
+        for ($i = 0; $i < $count; ++$i) {
             $distance += pow($a[$i] - $b[$i], 2);
         }
 

From bd34266ae1d4d32bba0fd6f89c6e04f64d4adddd Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 23:13:50 +0200
Subject: [PATCH 19/27] change min php version to 7.0.0

---
 composer.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/composer.json b/composer.json
index d3569d0..340f242 100644
--- a/composer.json
+++ b/composer.json
@@ -20,7 +20,7 @@
         "bin-dir": "bin"
     },
     "require": {
-        "php": ">=7.0.5"
+        "php": ">=7.0.0"
     },
     "require-dev": {
         "phpunit/phpunit": "^5.2"

From 63d49616d8e4d2b3d9788f1ea739fd2edd15ad65 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Thu, 7 Apr 2016 23:25:02 +0200
Subject: [PATCH 20/27] update composer

---
 composer.lock | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/composer.lock b/composer.lock
index 0b9287b..667ba6a 100644
--- a/composer.lock
+++ b/composer.lock
@@ -4,8 +4,8 @@
         "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file",
         "This file is @generated automatically"
     ],
-    "hash": "54ea009d9b09c1886c0789dadc484a36",
-    "content-hash": "52c31f7df9edd7063e2489ed47e091a7",
+    "hash": "7c34eebd6b8749a1cd09df57e5d1f47a",
+    "content-hash": "087091d0c339e9fa3a551a189ea658bf",
     "packages": [],
     "packages-dev": [
         {
@@ -458,16 +458,16 @@
         },
         {
             "name": "phpunit/phpunit",
-            "version": "5.3.0",
+            "version": "5.3.1",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/phpunit.git",
-                "reference": "dd3001822b2df8f5add266020e3d2fd3c5db3ae9"
+                "reference": "34a3acb401ae79deb37bc6e5f5ec3d325b369b4c"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/dd3001822b2df8f5add266020e3d2fd3c5db3ae9",
-                "reference": "dd3001822b2df8f5add266020e3d2fd3c5db3ae9",
+                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/34a3acb401ae79deb37bc6e5f5ec3d325b369b4c",
+                "reference": "34a3acb401ae79deb37bc6e5f5ec3d325b369b4c",
                 "shasum": ""
             },
             "require": {
@@ -482,7 +482,7 @@
                 "phpunit/php-code-coverage": "^3.3.0",
                 "phpunit/php-file-iterator": "~1.4",
                 "phpunit/php-text-template": "~1.2",
-                "phpunit/php-timer": ">=1.0.6",
+                "phpunit/php-timer": "^1.0.6",
                 "phpunit/phpunit-mock-objects": "^3.1",
                 "sebastian/comparator": "~1.1",
                 "sebastian/diff": "~1.2",
@@ -529,7 +529,7 @@
                 "testing",
                 "xunit"
             ],
-            "time": "2016-03-31 21:35:50"
+            "time": "2016-04-07 07:04:34"
         },
         {
             "name": "phpunit/phpunit-mock-objects",
@@ -1155,7 +1155,7 @@
     "prefer-stable": false,
     "prefer-lowest": false,
     "platform": {
-        "php": ">=7.0.5"
+        "php": ">=7.0.0"
     },
     "platform-dev": []
 }

From 0b6dc42807a2dd8e2fdcdb79690ebd6f8f5f585b Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Fri, 8 Apr 2016 21:37:26 +0200
Subject: [PATCH 21/27] change autoloader to psr-0

---
 composer.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/composer.json b/composer.json
index 340f242..4f0dd26 100644
--- a/composer.json
+++ b/composer.json
@@ -12,8 +12,8 @@
         }
     ],
     "autoload": {
-        "psr-4": {
-            "": "src/"
+        "psr-0": {
+            "Phpml": "src/"
         }
     },
     "config": {

From f1c81638d63ffa891f266a891683334158ffa5e8 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Fri, 8 Apr 2016 22:11:59 +0200
Subject: [PATCH 22/27] accuracy score with test

---
 src/Phpml/Metric/Accuracy.php       | 39 +++++++++++++++++++++++++++++
 tests/Phpml/Metric/AccuracyTest.php | 38 ++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)
 create mode 100644 src/Phpml/Metric/Accuracy.php
 create mode 100644 tests/Phpml/Metric/AccuracyTest.php

diff --git a/src/Phpml/Metric/Accuracy.php b/src/Phpml/Metric/Accuracy.php
new file mode 100644
index 0000000..878cadd
--- /dev/null
+++ b/src/Phpml/Metric/Accuracy.php
@@ -0,0 +1,39 @@
+<?php
+declare(strict_types = 1);
+
+namespace Phpml\Metric;
+
+use Phpml\Exception\InvalidArgumentException;
+
+class Accuracy
+{
+
+    /**
+     * @param array $actualLabels
+     * @param array $predictedLabels
+     * @param bool $normalize
+     *
+     * @return float|int
+     *
+     * @throws InvalidArgumentException
+     */
+    public static function score(array $actualLabels, array $predictedLabels, bool $normalize = true)
+    {
+        if (count($actualLabels) != count($predictedLabels)) {
+            throw InvalidArgumentException::sizeNotMatch();
+        }
+
+        $score = 0;
+        foreach ($actualLabels as $index => $label) {
+            if($label===$predictedLabels[$index]) {
+                $score++;
+            }
+        }
+
+        if($normalize) {
+            $score = $score / count($actualLabels);
+        }
+
+        return $score;
+    }
+}
diff --git a/tests/Phpml/Metric/AccuracyTest.php b/tests/Phpml/Metric/AccuracyTest.php
new file mode 100644
index 0000000..31bb0fc
--- /dev/null
+++ b/tests/Phpml/Metric/AccuracyTest.php
@@ -0,0 +1,38 @@
+<?php
+declare(strict_types = 1);
+
+namespace tests\Phpml\Metric;
+
+use Phpml\Metric\Accuracy;
+
+class AccuracyTest extends \PHPUnit_Framework_TestCase
+{
+
+    /**
+     * @expectedException \Phpml\Exception\InvalidArgumentException
+     */
+    public function testThrowExceptionOnInvalidArguments()
+    {
+        $actualLabels = ['a', 'b', 'a', 'b'];
+        $predictedLabels = ['a', 'a'];
+
+        Accuracy::score($actualLabels, $predictedLabels);
+    }
+
+    public function testCalculateNormalizedScore()
+    {
+        $actualLabels = ['a', 'b', 'a', 'b'];
+        $predictedLabels = ['a', 'a', 'b', 'b'];
+
+        $this->assertEquals(0.5, Accuracy::score($actualLabels, $predictedLabels));
+    }
+
+    public function testCalculateNotNormalizedScore()
+    {
+        $actualLabels = ['a', 'b', 'a', 'b'];
+        $predictedLabels = ['a', 'b', 'b', 'b'];
+
+        $this->assertEquals(3, Accuracy::score($actualLabels, $predictedLabels, false));
+    }
+
+}

From e7d27801503136cd4450bbc3a8014ef13595f5ba Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Fri, 8 Apr 2016 22:25:15 +0200
Subject: [PATCH 23/27] classifier predict array of samples or one sample

---
 src/Phpml/Classifier/Classifier.php           |  4 ++--
 src/Phpml/Classifier/KNearestNeighbors.php    | 21 ++++++++++++++++++-
 src/Phpml/Classifier/NaiveBayes.php           |  4 ++--
 .../Classifier/KNearestNeighborsTest.php      | 15 +++++++++++++
 4 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/src/Phpml/Classifier/Classifier.php b/src/Phpml/Classifier/Classifier.php
index 6fad67a..90250a9 100644
--- a/src/Phpml/Classifier/Classifier.php
+++ b/src/Phpml/Classifier/Classifier.php
@@ -13,9 +13,9 @@ interface Classifier
     public function train(array $samples, array $labels);
 
     /**
-     * @param array $sample
+     * @param array $samples
      *
      * @return mixed
      */
-    public function predict(array $sample);
+    public function predict(array $samples);
 }
diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
index 5a998d3..53c66b0 100644
--- a/src/Phpml/Classifier/KNearestNeighbors.php
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -43,12 +43,31 @@ class KNearestNeighbors implements Classifier
         $this->labels = $labels;
     }
 
+    /**
+     * @param array $samples
+     *
+     * @return mixed
+     */
+    public function predict(array $samples)
+    {
+        if(!is_array($samples[0])) {
+            $predicted = $this->predictSample($samples);
+        } else {
+            $predicted = [];
+            foreach ($samples as $index => $sample) {
+                $predicted[$index] = $this->predictSample($sample);
+            }
+        }
+
+        return $predicted;
+    }
+
     /**
      * @param array $sample
      *
      * @return mixed
      */
-    public function predict(array $sample)
+    private function predictSample(array $sample)
     {
         $distances = $this->kNeighborsDistances($sample);
 
diff --git a/src/Phpml/Classifier/NaiveBayes.php b/src/Phpml/Classifier/NaiveBayes.php
index c1cc902..7324d79 100644
--- a/src/Phpml/Classifier/NaiveBayes.php
+++ b/src/Phpml/Classifier/NaiveBayes.php
@@ -15,11 +15,11 @@ class NaiveBayes implements Classifier
     }
 
     /**
-     * @param array $sample
+     * @param array $samples
      *
      * @return mixed
      */
-    public function predict(array $sample)
+    public function predict(array $samples)
     {
     }
 }
diff --git a/tests/Phpml/Classifier/KNearestNeighborsTest.php b/tests/Phpml/Classifier/KNearestNeighborsTest.php
index 2786ade..06ae42f 100644
--- a/tests/Phpml/Classifier/KNearestNeighborsTest.php
+++ b/tests/Phpml/Classifier/KNearestNeighborsTest.php
@@ -26,4 +26,19 @@ class KNearestNeighborsTest extends \PHPUnit_Framework_TestCase
         $this->assertEquals('a', $classifier->predict([1, 5]));
         $this->assertEquals('a', $classifier->predict([3, 10]));
     }
+
+    public function testPredictArrayOfSamples()
+    {
+        $trainSamples = [[1, 3], [1, 4], [2, 4], [3, 1], [4, 1], [4, 2]];
+        $trainLabels = ['a', 'a', 'a', 'b', 'b', 'b'];
+
+        $testSamples = [[3, 2], [5, 1], [4, 3], [4, -5], [2, 3], [1, 2], [1, 5], [3, 10]];
+        $testLabels = ['b', 'b', 'b', 'b', 'a', 'a', 'a', 'a',];
+
+        $classifier = new KNearestNeighbors();
+        $classifier->train($trainSamples, $trainLabels);
+        $predicted = $classifier->predict($testSamples);
+
+        $this->assertEquals($testLabels, $predicted);
+    }
 }

From 62ec4ec2f240781ac0e82778144699ff364ddb15 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Fri, 8 Apr 2016 22:49:17 +0200
Subject: [PATCH 24/27] integration tests for knn classifier

---
 src/Phpml/Classifier/KNearestNeighbors.php     |  2 +-
 src/Phpml/Metric/Accuracy.php                  | 12 ++++++------
 .../Phpml/Classifier/KNearestNeighborsTest.php | 18 ++++++++++++++++--
 tests/Phpml/Metric/AccuracyTest.php            |  5 ++---
 4 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/src/Phpml/Classifier/KNearestNeighbors.php b/src/Phpml/Classifier/KNearestNeighbors.php
index 53c66b0..f913488 100644
--- a/src/Phpml/Classifier/KNearestNeighbors.php
+++ b/src/Phpml/Classifier/KNearestNeighbors.php
@@ -50,7 +50,7 @@ class KNearestNeighbors implements Classifier
      */
     public function predict(array $samples)
     {
-        if(!is_array($samples[0])) {
+        if (!is_array($samples[0])) {
             $predicted = $this->predictSample($samples);
         } else {
             $predicted = [];
diff --git a/src/Phpml/Metric/Accuracy.php b/src/Phpml/Metric/Accuracy.php
index 878cadd..d871e85 100644
--- a/src/Phpml/Metric/Accuracy.php
+++ b/src/Phpml/Metric/Accuracy.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace Phpml\Metric;
 
@@ -7,11 +8,10 @@ use Phpml\Exception\InvalidArgumentException;
 
 class Accuracy
 {
-
     /**
      * @param array $actualLabels
      * @param array $predictedLabels
-     * @param bool $normalize
+     * @param bool  $normalize
      *
      * @return float|int
      *
@@ -25,12 +25,12 @@ class Accuracy
 
         $score = 0;
         foreach ($actualLabels as $index => $label) {
-            if($label===$predictedLabels[$index]) {
-                $score++;
+            if ($label === $predictedLabels[$index]) {
+                ++$score;
             }
         }
 
-        if($normalize) {
+        if ($normalize) {
             $score = $score / count($actualLabels);
         }
 
diff --git a/tests/Phpml/Classifier/KNearestNeighborsTest.php b/tests/Phpml/Classifier/KNearestNeighborsTest.php
index 06ae42f..1050607 100644
--- a/tests/Phpml/Classifier/KNearestNeighborsTest.php
+++ b/tests/Phpml/Classifier/KNearestNeighborsTest.php
@@ -5,10 +5,13 @@ declare (strict_types = 1);
 namespace tests\Classifier;
 
 use Phpml\Classifier\KNearestNeighbors;
+use Phpml\CrossValidation\RandomSplit;
+use Phpml\Dataset\Demo\Iris;
+use Phpml\Metric\Accuracy;
 
 class KNearestNeighborsTest extends \PHPUnit_Framework_TestCase
 {
-    public function testPredictSimpleSampleWithDefaultK()
+    public function testPredictSingleSampleWithDefaultK()
     {
         $samples = [[1, 3], [1, 4], [2, 4], [3, 1], [4, 1], [4, 2]];
         $labels = ['a', 'a', 'a', 'b', 'b', 'b'];
@@ -33,7 +36,7 @@ class KNearestNeighborsTest extends \PHPUnit_Framework_TestCase
         $trainLabels = ['a', 'a', 'a', 'b', 'b', 'b'];
 
         $testSamples = [[3, 2], [5, 1], [4, 3], [4, -5], [2, 3], [1, 2], [1, 5], [3, 10]];
-        $testLabels = ['b', 'b', 'b', 'b', 'a', 'a', 'a', 'a',];
+        $testLabels = ['b', 'b', 'b', 'b', 'a', 'a', 'a', 'a'];
 
         $classifier = new KNearestNeighbors();
         $classifier->train($trainSamples, $trainLabels);
@@ -41,4 +44,15 @@ class KNearestNeighborsTest extends \PHPUnit_Framework_TestCase
 
         $this->assertEquals($testLabels, $predicted);
     }
+
+    public function testAccuracyOnIrisDataset()
+    {
+        $dataset = new RandomSplit(new Iris(), $testSize = 0.5, $seed = 123);
+        $classifier = new KNearestNeighbors($k = 4);
+        $classifier->train($dataset->getTrainSamples(), $dataset->getTrainLabels());
+        $predicted = $classifier->predict($dataset->getTestSamples());
+        $score = Accuracy::score($dataset->getTestLabels(), $predicted);
+
+        $this->assertEquals(0.96, $score);
+    }
 }
diff --git a/tests/Phpml/Metric/AccuracyTest.php b/tests/Phpml/Metric/AccuracyTest.php
index 31bb0fc..aa68b22 100644
--- a/tests/Phpml/Metric/AccuracyTest.php
+++ b/tests/Phpml/Metric/AccuracyTest.php
@@ -1,5 +1,6 @@
 <?php
-declare(strict_types = 1);
+
+declare (strict_types = 1);
 
 namespace tests\Phpml\Metric;
 
@@ -7,7 +8,6 @@ use Phpml\Metric\Accuracy;
 
 class AccuracyTest extends \PHPUnit_Framework_TestCase
 {
-
     /**
      * @expectedException \Phpml\Exception\InvalidArgumentException
      */
@@ -34,5 +34,4 @@ class AccuracyTest extends \PHPUnit_Framework_TestCase
 
         $this->assertEquals(3, Accuracy::score($actualLabels, $predictedLabels, false));
     }
-
 }

From 83b4a9e19c3a0bbdaa6871a2edc4b5c44fe002ee Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Fri, 8 Apr 2016 23:22:55 +0200
Subject: [PATCH 25/27] add instal info and badges to readme

---
 README.md | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/README.md b/README.md
index 457f3c1..568c3ab 100644
--- a/README.md
+++ b/README.md
@@ -1,18 +1,23 @@
 # PHP Machine learning library
 
+[![Build Status](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/build.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/build-status/develop)
+[![Total Downloads](https://poser.pugx.org/php-ai/php-ml/downloads.svg)](https://packagist.org/packages/php-ai/php-ml)
+[![License](https://poser.pugx.org/php-ai/php-ml/license.svg)](https://packagist.org/packages/php-ai/php-ml)
+[![Scrutinizer Code Quality](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/quality-score.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/?branch=develop)
+
 Fresh approach to machine learning in PHP. Note that at the moment PHP is not the best choice for machine learning but maybe this will change ...
 
-## Available Algorithms
+## Documentation
 
-### Classification
-
-Identifying to which category an object belongs to.
-
-*  **Naive Bayes** - algorithm based on applying Bayes’ theorem with the “naive” assumption of independence between every pair of features
+The documentation will be available on `Read the Docs` soon ...
 
 ## Installation
 
-This repo will be published do packagist.org soon...
+Currently this library is in the process of developing, but You can install it with Composer:
+
+```
+composer require php-ai/php-ml
+```
 
 ## To-Do
 
@@ -21,7 +26,7 @@ This repo will be published do packagist.org soon...
 
 ## Testing
 
-After installation, you can launch the test suite in project root directory (you will need to install dev requiremnts with composer)
+After installation, you can launch the test suite in project root directory (you will need to install dev requirements with composer)
 
 ```
 bin/phpunit
@@ -33,3 +38,4 @@ PHP-ML is released under the MIT Licence. See the bundled LICENSE file for detai
 
 ## Author
 
+Arkadiusz Kondas (@ArkadiuszKondas)
\ No newline at end of file

From 5be21477840b64336be8b6e5e4713074fc2159fc Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Sat, 9 Apr 2016 00:36:48 +0200
Subject: [PATCH 26/27] creat docs files

---
 docs/index.md                                 | 37 +++++++++++++++++++
 .../classification/knearestneighbors.md       | 35 ++++++++++++++++++
 .../cross-validation/randomsplit.md           | 29 +++++++++++++++
 .../datasets/array-dataset.md                 | 21 +++++++++++
 docs/machine-learning/datasets/csv-dataset.md | 15 ++++++++
 docs/machine-learning/datasets/demo/iris.md   | 34 +++++++++++++++++
 docs/machine-learning/metric/accuracy.md      | 24 ++++++++++++
 docs/machine-learning/metric/distance.md      | 17 +++++++++
 mkdocs.yml                                    | 17 +++++++++
 .../Phpml/CrossValidation/RandomSplitTest.php |  6 +--
 10 files changed, 232 insertions(+), 3 deletions(-)
 create mode 100644 docs/index.md
 create mode 100644 docs/machine-learning/classification/knearestneighbors.md
 create mode 100644 docs/machine-learning/cross-validation/randomsplit.md
 create mode 100644 docs/machine-learning/datasets/array-dataset.md
 create mode 100644 docs/machine-learning/datasets/csv-dataset.md
 create mode 100644 docs/machine-learning/datasets/demo/iris.md
 create mode 100644 docs/machine-learning/metric/accuracy.md
 create mode 100644 docs/machine-learning/metric/distance.md
 create mode 100644 mkdocs.yml

diff --git a/docs/index.md b/docs/index.md
new file mode 100644
index 0000000..c3e2703
--- /dev/null
+++ b/docs/index.md
@@ -0,0 +1,37 @@
+# PHP Machine Learning (PHP-ML)
+
+[![Build Status](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/build.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/build-status/develop)
+[![Total Downloads](https://poser.pugx.org/php-ai/php-ml/downloads.svg)](https://packagist.org/packages/php-ai/php-ml)
+[![License](https://poser.pugx.org/php-ai/php-ml/license.svg)](https://packagist.org/packages/php-ai/php-ml)
+[![Scrutinizer Code Quality](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/quality-score.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/?branch=develop)
+
+Fresh approach to machine learning in PHP. Note that at the moment PHP is not the best choice for machine learning but maybe this will change ...
+
+## Installation
+
+Currently this library is in the process of developing, but You can install it with Composer:
+
+```
+composer require php-ai/php-ml
+```
+
+## To-Do
+
+* implements more algorithms
+* integration with Lavacharts for data visualization
+
+## Testing
+
+After installation, you can launch the test suite in project root directory (you will need to install dev requirements with composer)
+
+```
+bin/phpunit
+```
+
+## License
+
+PHP-ML is released under the MIT Licence. See the bundled LICENSE file for details.
+
+## Author
+
+Arkadiusz Kondas (@ArkadiuszKondas)
\ No newline at end of file
diff --git a/docs/machine-learning/classification/knearestneighbors.md b/docs/machine-learning/classification/knearestneighbors.md
new file mode 100644
index 0000000..569c48b
--- /dev/null
+++ b/docs/machine-learning/classification/knearestneighbors.md
@@ -0,0 +1,35 @@
+# KNearestNeighbors Classifier
+
+Classifier implementing the k-nearest neighbors algorithm.
+
+### Constructor Parameters
+
+* $k - number of nearest neighbors to scan (default: 3)
+
+```
+$classifier = new KNearestNeighbors($k=4);
+```
+
+### Train
+
+To train a classifier simply provide train samples and labels (as `array`):
+
+```
+$samples = [[1, 3], [1, 4], [2, 4], [3, 1], [4, 1], [4, 2]];
+$labels = ['a', 'a', 'a', 'b', 'b', 'b'];
+
+$classifier = new KNearestNeighbors();
+$classifier->train($samples, $labels);
+```
+
+### Predict
+
+To predict sample class use `predict` method. You can provide one sample or array of samples:
+
+```
+$classifier->predict([3, 2]);
+// return 'b'
+
+$classifier->predict([[3, 2], [1, 5]]);
+// return ['b', 'a']
+```
diff --git a/docs/machine-learning/cross-validation/randomsplit.md b/docs/machine-learning/cross-validation/randomsplit.md
new file mode 100644
index 0000000..464f0db
--- /dev/null
+++ b/docs/machine-learning/cross-validation/randomsplit.md
@@ -0,0 +1,29 @@
+# RandomSplit
+
+One of the simplest methods from Cross-validation is implemented as `RandomSpilt` class. Samples are split to two groups: train group and test group. You can adjust number of samples in each group.
+
+### Constructor Parameters
+
+* $dataset - object that implements `Dataset` interface
+* $testSize - a fraction of test split (float, from 0 to 1, default: 0.3)
+* $seed - seed for random generator (for tests)
+ 
+```
+$randomSplit = new RandomSplit($dataset, 0.2);
+```
+
+### Samples and labels groups
+
+To get samples or labels from test and train group you can use getters:
+
+```
+$dataset = new RandomSplit($dataset, 0.3, 1234);
+
+// train group
+$dataset->getTrainSamples();
+$dataset->getTrainLabels();
+
+// test group
+$dataset->getTestSamples();
+$dataset->getTestLabels();
+```
diff --git a/docs/machine-learning/datasets/array-dataset.md b/docs/machine-learning/datasets/array-dataset.md
new file mode 100644
index 0000000..5081ed8
--- /dev/null
+++ b/docs/machine-learning/datasets/array-dataset.md
@@ -0,0 +1,21 @@
+# ArrayDataset
+
+Helper class that holds data as PHP `array` type. Implements the `Dataset` interface which is used heavily in other classes.
+
+### Constructors Parameters
+
+* $samples - (array) of samples
+* $labels - (array) of labels
+
+```
+$dataset = new ArrayDataset([[1, 1], [2, 1], [3, 2], [4, 1]], ['a', 'a', 'b', 'b']);
+```
+
+### Samples and labels
+
+To get samples or labels you can use getters:
+
+```
+$dataset->getSamples();
+$dataset->getLabels();
+```
diff --git a/docs/machine-learning/datasets/csv-dataset.md b/docs/machine-learning/datasets/csv-dataset.md
new file mode 100644
index 0000000..553bc60
--- /dev/null
+++ b/docs/machine-learning/datasets/csv-dataset.md
@@ -0,0 +1,15 @@
+# CsvDataset
+
+Helper class that loads data from CSV file. It extends the `ArrayDataset`.
+
+### Constructors Parameters
+
+* $filepath - (string) path to `.csv` file
+* $features - (int) number of columns that are features (starts from first column), last column must be a label
+* $headingRow - (bool) define is file have a heading row (if `true` then first row will be ignored)
+
+```
+$dataset = new CsvDataset('dataset.csv', 2, true);
+```
+
+See Array Dataset for more information.
diff --git a/docs/machine-learning/datasets/demo/iris.md b/docs/machine-learning/datasets/demo/iris.md
new file mode 100644
index 0000000..9e00d5c
--- /dev/null
+++ b/docs/machine-learning/datasets/demo/iris.md
@@ -0,0 +1,34 @@
+# Iris Dataset
+
+Most popular and widely available dataset of iris flower measurement and class names. 
+
+### Specification
+
+| Classes               | 3     |
+| Samples per class     | 50    |
+| Samples total         | 150   |
+| Features per sample   | 4     |
+
+### Load
+
+To load Iris dataset simple use:
+
+```
+$dataset = new Iris();
+```
+
+### Several samples
+
+```
+sepal length,sepal width,petal length,petal width,class
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginicacs
+```
diff --git a/docs/machine-learning/metric/accuracy.md b/docs/machine-learning/metric/accuracy.md
new file mode 100644
index 0000000..b8ec70a
--- /dev/null
+++ b/docs/machine-learning/metric/accuracy.md
@@ -0,0 +1,24 @@
+# Accuracy
+
+Class for calculate classifier accuracy.
+
+### Score
+
+To calculate classifier accuracy score use `score` static method. Parametrs:
+
+* $actualLabels - (array) true sample labels
+* $predictedLabels - (array) predicted labels (e.x. from test group)
+* $normalize - (bool) normalize or not the result (default: true)
+
+### Example
+
+```
+$actualLabels = ['a', 'b', 'a', 'b'];
+$predictedLabels = ['a', 'a', 'a', 'b'];
+
+Accuracy::score($actualLabels, $predictedLabels);
+// return 0.75
+
+Accuracy::score($actualLabels, $predictedLabels, false);
+// return 3
+```
diff --git a/docs/machine-learning/metric/distance.md b/docs/machine-learning/metric/distance.md
new file mode 100644
index 0000000..de8bcb1
--- /dev/null
+++ b/docs/machine-learning/metric/distance.md
@@ -0,0 +1,17 @@
+# Distance
+
+Special class for calculation of different types of distance.
+
+### Euclidean
+
+![euclidean](https://upload.wikimedia.org/math/8/4/9/849f040fd10bb86f7c85eb0bbe3566a4.png "Euclidean Distance")
+
+To calculate euclidean distance:
+
+```
+$a = [4, 6];
+$b = [2, 5];
+        
+Distance::euclidean($a, $b);
+// return 2.2360679774998
+```
diff --git a/mkdocs.yml b/mkdocs.yml
new file mode 100644
index 0000000..f20036f
--- /dev/null
+++ b/mkdocs.yml
@@ -0,0 +1,17 @@
+site_name: PHP Machine Learning (PHP-ML)
+pages:
+  - Home: index.md
+  - Machine Learning:
+    - Classification:
+      - KNearestNeighbors: machine-learning/classification/knearestneighbors.md
+    - Cross Validation:
+      - RandomSplit: machine-learning/cross-validation/randomsplit.md
+    - Datasets:
+      - Array Dataset: machine-learning/datasets/array-dataset.md
+      - CSV Dataset: machine-learning/datasets/csv-dataset.md
+      - Demo:
+        - Iris: machine-learning/datasets/demo/iris.md
+    - Metric:
+      - Accuracy: machine-learning/metric/accuracy.md
+      - Distance: machine-learning/metric/distance.md
+theme: readthedocs
\ No newline at end of file
diff --git a/tests/Phpml/CrossValidation/RandomSplitTest.php b/tests/Phpml/CrossValidation/RandomSplitTest.php
index e6ae30e..d31c6a6 100644
--- a/tests/Phpml/CrossValidation/RandomSplitTest.php
+++ b/tests/Phpml/CrossValidation/RandomSplitTest.php
@@ -32,10 +32,10 @@ class RandomSplitTest extends \PHPUnit_Framework_TestCase
             $labels = ['a', 'a', 'b', 'b']
         );
 
-        $randomSplit1 = new RandomSplit($dataset, 0.5);
+        $randomSplit = new RandomSplit($dataset, 0.5);
 
-        $this->assertEquals(2, count($randomSplit1->getTestSamples()));
-        $this->assertEquals(2, count($randomSplit1->getTrainSamples()));
+        $this->assertEquals(2, count($randomSplit->getTestSamples()));
+        $this->assertEquals(2, count($randomSplit->getTrainSamples()));
 
         $randomSplit2 = new RandomSplit($dataset, 0.25);
 

From 04763b16f0065115fd05a799b111c26b96562c01 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kondas <arkadiusz.kondas@gmail.com>
Date: Sat, 9 Apr 2016 00:50:08 +0200
Subject: [PATCH 27/27] add documentation link

---
 README.md | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 568c3ab..feac3e5 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,7 @@
-# PHP Machine learning library
+# PHP Machine Learning library
 
 [![Build Status](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/build.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/build-status/develop)
+[![Documentation Status](https://readthedocs.org/projects/php-ml/badge/?version=develop)](http://php-ml.readthedocs.org/en/develop/?badge=develop)
 [![Total Downloads](https://poser.pugx.org/php-ai/php-ml/downloads.svg)](https://packagist.org/packages/php-ai/php-ml)
 [![License](https://poser.pugx.org/php-ai/php-ml/license.svg)](https://packagist.org/packages/php-ai/php-ml)
 [![Scrutinizer Code Quality](https://scrutinizer-ci.com/g/php-ai/php-ml/badges/quality-score.png?b=develop)](https://scrutinizer-ci.com/g/php-ai/php-ml/?branch=develop)
@@ -9,7 +10,7 @@ Fresh approach to machine learning in PHP. Note that at the moment PHP is not th
 
 ## Documentation
 
-The documentation will be available on `Read the Docs` soon ...
+To find out how to use PHP-ML follow [Documentation](php-ml.readthedocs.org).
 
 ## Installation