Add phpstan strict rules (#233)

* Add phpstan strict rules * Fix travis coveralls * Add phpstan-phpunit strict rules * Fix eigen decomposition test name and phpstan ingored error
ghostjat · Feb 16, 2018 · 16dc16b · 16dc16b
1 parent 6ac61a8
commit 16dc16b
Show file tree

Hide file tree

Showing 33 changed files with 164 additions and 71 deletions.
diff --git a/.travis.yml b/.travis.yml
@@ -41,5 +41,5 @@ after_success:
   - |
     if [[ $PHPUNIT_FLAGS != "" ]]; then
       wget https://github.com/php-coveralls/php-coveralls/releases/download/v2.0.0/php-coveralls.phar
-      php coveralls.phar --verbose;
+      php php-coveralls.phar --verbose;
     fi
diff --git a/composer.json b/composer.json
@@ -23,7 +23,9 @@
         "php": "^7.1"
     },
     "require-dev": {
+        "phpstan/phpstan-phpunit": "^0.9.4",
         "phpstan/phpstan-shim": "^0.9",
+        "phpstan/phpstan-strict-rules": "^0.9.0",
         "phpunit/phpunit": "^7.0.0",
         "symplify/coding-standard": "^3.1",
         "symplify/easy-coding-standard": "^3.1"

diff --git a/composer.lock b/composer.lock
diff --git a/phpstan.neon b/phpstan.neon
@@ -1,15 +1,17 @@
+includes:
+    - vendor/phpstan/phpstan-strict-rules/rules.neon
+    - vendor/phpstan/phpstan-phpunit/extension.neon
+    - vendor/phpstan/phpstan-phpunit/rules.neon
+    - vendor/phpstan/phpstan-phpunit/strictRules.neon
+
 parameters:
     ignoreErrors:
         - '#Phpml\\Dataset\\FilesDataset::__construct\(\) does not call parent constructor from Phpml\\Dataset\\ArrayDataset#'
 
-        # mocks
-        - '#PHPUnit_Framework_MockObject_MockObject#'
-
         # wide range cases
         - '#Call to function count\(\) with argument type array<int>\|Phpml\\Clustering\\KMeans\\Point will always result in number 1#'
         - '#Parameter \#1 \$coordinates of class Phpml\\Clustering\\KMeans\\Point constructor expects array, array<int>\|Phpml\\Clustering\\KMeans\\Point given#'
 
         # probably known value
-        - '#Variable \$j might not be defined#'
         - '#Method Phpml\\Classification\\DecisionTree::getBestSplit\(\) should return Phpml\\Classification\\DecisionTree\\DecisionTreeLeaf but returns Phpml\\Classification\\DecisionTree\\DecisionTreeLeaf\|null#'
         - '#Call to an undefined method Phpml\\Helper\\Optimizer\\Optimizer::getCostValues\(\)#'
diff --git a/src/Association/Apriori.php b/src/Association/Apriori.php
@@ -63,11 +63,11 @@ public function __construct(float $support = 0.0, float $confidence = 0.0)
      */
     public function getRules(): array
     {
-        if (!$this->large) {
+        if (empty($this->large)) {
             $this->large = $this->apriori();
         }
 
-        if ($this->rules) {
+        if (!empty($this->rules)) {
             return $this->rules;
         }
 

diff --git a/src/Classification/DecisionTree.php b/src/Classification/DecisionTree.php
@@ -273,15 +273,15 @@ protected function getSplitLeaf(array $records, int $depth = 0): DecisionTreeLea
         }
 
         if ($allSame || $depth >= $this->maxDepth || count($remainingTargets) === 1) {
-            $split->isTerminal = 1;
+            $split->isTerminal = true;
             arsort($remainingTargets);
             $split->classValue = key($remainingTargets);
         } else {
-            if ($leftRecords) {
+            if (!empty($leftRecords)) {
                 $split->leftLeaf = $this->getSplitLeaf($leftRecords, $depth + 1);
             }
 
-            if ($rightRecords) {
+            if (!empty($rightRecords)) {
                 $split->rightLeaf = $this->getSplitLeaf($rightRecords, $depth + 1);
             }
         }
@@ -312,13 +312,13 @@ protected function getBestSplit(array $records): DecisionTreeLeaf
                 $split->value = $baseValue;
                 $split->giniIndex = $gini;
                 $split->columnIndex = $i;
-                $split->isContinuous = $this->columnTypes[$i] == self::CONTINUOUS;
+                $split->isContinuous = $this->columnTypes[$i] === self::CONTINUOUS;
                 $split->records = $records;
 
                 // If a numeric column is to be selected, then
                 // the original numeric value and the selected operator
                 // will also be saved into the leaf for future access
-                if ($this->columnTypes[$i] == self::CONTINUOUS) {
+                if ($this->columnTypes[$i] === self::CONTINUOUS) {
                     $matches = [];
                     preg_match("/^([<>=]{1,2})\s*(.*)/", (string) $split->value, $matches);
                     $split->operator = $matches[1];
@@ -349,11 +349,11 @@ protected function getBestSplit(array $records): DecisionTreeLeaf
     protected function getSelectedFeatures(): array
     {
         $allFeatures = range(0, $this->featureCount - 1);
-        if ($this->numUsableFeatures === 0 && !$this->selectedFeatures) {
+        if ($this->numUsableFeatures === 0 && empty($this->selectedFeatures)) {
             return $allFeatures;
         }
 
-        if ($this->selectedFeatures) {
+        if (!empty($this->selectedFeatures)) {
             return $this->selectedFeatures;
         }
 
@@ -363,7 +363,7 @@ protected function getSelectedFeatures(): array
         }
 
         shuffle($allFeatures);
-        $selectedFeatures = array_slice($allFeatures, 0, $numFeatures, false);
+        $selectedFeatures = array_slice($allFeatures, 0, $numFeatures);
         sort($selectedFeatures);
 
         return $selectedFeatures;
@@ -406,7 +406,7 @@ protected static function isCategoricalColumn(array $columnValues): bool
         //	  all values in that column (Lower than or equal to %20 of all values)
         $numericValues = array_filter($columnValues, 'is_numeric');
         $floatValues = array_filter($columnValues, 'is_float');
-        if ($floatValues) {
+        if (!empty($floatValues)) {
             return false;
         }
 
@@ -433,7 +433,7 @@ protected function setSelectedFeatures(array $selectedFeatures): void
      */
     protected function getSplitNodesByColumn(int $column, DecisionTreeLeaf $node): array
     {
-        if (!$node || $node->isTerminal) {
+        if ($node->isTerminal) {
             return [];
         }
 
@@ -444,11 +444,11 @@ protected function getSplitNodesByColumn(int $column, DecisionTreeLeaf $node): a
 
         $lNodes = [];
         $rNodes = [];
-        if ($node->leftLeaf) {
+        if ($node->leftLeaf !== null) {
             $lNodes = $this->getSplitNodesByColumn($column, $node->leftLeaf);
         }
 
-        if ($node->rightLeaf) {
+        if ($node->rightLeaf !== null) {
             $rNodes = $this->getSplitNodesByColumn($column, $node->rightLeaf);
         }
 
@@ -475,6 +475,6 @@ protected function predictSample(array $sample)
             }
         } while ($node);
 
-        return $node ? $node->classValue : $this->labels[0];
+        return $node !== null ? $node->classValue : $this->labels[0];
     }
 }
diff --git a/src/Classification/DecisionTree/DecisionTreeLeaf.php b/src/Classification/DecisionTree/DecisionTreeLeaf.php
@@ -29,14 +29,14 @@ class DecisionTreeLeaf
     public $columnIndex;
 
     /**
-     * @var DecisionTreeLeaf
+     * @var ?DecisionTreeLeaf
      */
-    public $leftLeaf = null;
+    public $leftLeaf;
 
     /**
-     * @var DecisionTreeLeaf
+     * @var ?DecisionTreeLeaf
      */
-    public $rightLeaf = null;
+    public $rightLeaf;
 
     /**
      * @var array
@@ -52,7 +52,7 @@ class DecisionTreeLeaf
     public $classValue = '';
 
     /**
-     * @var bool|int
+     * @var bool
      */
     public $isTerminal = false;
 
@@ -103,12 +103,12 @@ public function getNodeImpurityDecrease(int $parentRecordCount): float
         $nodeSampleCount = (float) count($this->records);
         $iT = $this->giniIndex;
 
-        if ($this->leftLeaf) {
+        if ($this->leftLeaf !== null) {
             $pL = count($this->leftLeaf->records) / $nodeSampleCount;
             $iT -= $pL * $this->leftLeaf->giniIndex;
         }
 
-        if ($this->rightLeaf) {
+        if ($this->rightLeaf !== null) {
             $pR = count($this->rightLeaf->records) / $nodeSampleCount;
             $iT -= $pR * $this->rightLeaf->giniIndex;
         }
@@ -140,16 +140,16 @@ public function getHTML($columnNames = null): string
 
         $str = "<table ><tr><td colspan=3 align=center style='border:1px solid;'>${value}</td></tr>";
 
-        if ($this->leftLeaf || $this->rightLeaf) {
+        if ($this->leftLeaf !== null || $this->rightLeaf !== null) {
             $str .= '<tr>';
-            if ($this->leftLeaf) {
+            if ($this->leftLeaf !== null) {
                 $str .= '<td valign=top><b>| Yes</b><br>'.$this->leftLeaf->getHTML($columnNames).'</td>';
             } else {
                 $str .= '<td></td>';
             }
 
             $str .= '<td>&nbsp;</td>';
-            if ($this->rightLeaf) {
+            if ($this->rightLeaf !== null) {
                 $str .= '<td valign=top align=right><b>No |</b><br>'.$this->rightLeaf->getHTML($columnNames).'</td>';
             } else {
                 $str .= '<td></td>';

diff --git a/src/Classification/Ensemble/AdaBoost.php b/src/Classification/Ensemble/AdaBoost.php
@@ -158,7 +158,7 @@ public function predictSample(array $sample)
     protected function getBestClassifier(): Classifier
     {
         $ref = new ReflectionClass($this->baseClassifier);
-        if ($this->classifierOptions) {
+        if (!empty($this->classifierOptions)) {
             $classifier = $ref->newInstanceArgs($this->classifierOptions);
         } else {
             $classifier = $ref->newInstance();

diff --git a/src/Classification/Ensemble/Bagging.php b/src/Classification/Ensemble/Bagging.php
@@ -145,7 +145,7 @@ protected function initClassifiers(): array
         $classifiers = [];
         for ($i = 0; $i < $this->numClassifier; ++$i) {
             $ref = new ReflectionClass($this->classifier);
-            if ($this->classifierOptions) {
+            if (!empty($this->classifierOptions)) {
                 $obj = $ref->newInstanceArgs($this->classifierOptions);
             } else {
                 $obj = $ref->newInstance();

diff --git a/src/Classification/Linear/Adaline.php b/src/Classification/Linear/Adaline.php
@@ -42,7 +42,7 @@ public function __construct(
         bool $normalizeInputs = true,
         int $trainingType = self::BATCH_TRAINING
     ) {
-        if (!in_array($trainingType, [self::BATCH_TRAINING, self::ONLINE_TRAINING])) {
+        if (!in_array($trainingType, [self::BATCH_TRAINING, self::ONLINE_TRAINING], true)) {
             throw new Exception('Adaline can only be trained with batch and online/stochastic gradient descent algorithm');
         }
 

diff --git a/src/Classification/Linear/DecisionStump.php b/src/Classification/Linear/DecisionStump.php
@@ -118,7 +118,7 @@ protected function trainBinary(array $samples, array $targets, array $labels): v
 
         // Check the size of the weights given.
         // If none given, then assign 1 as a weight to each sample
-        if ($this->weights) {
+        if (!empty($this->weights)) {
             $numWeights = count($this->weights);
             if ($numWeights != count($samples)) {
                 throw new Exception('Number of sample weights does not match with number of samples');

diff --git a/src/Classification/Linear/LogisticRegression.php b/src/Classification/Linear/LogisticRegression.php
@@ -71,13 +71,13 @@ public function __construct(
         string $penalty = 'L2'
     ) {
         $trainingTypes = range(self::BATCH_TRAINING, self::CONJUGATE_GRAD_TRAINING);
-        if (!in_array($trainingType, $trainingTypes)) {
+        if (!in_array($trainingType, $trainingTypes, true)) {
             throw new Exception('Logistic regression can only be trained with '.
                 'batch (gradient descent), online (stochastic gradient descent) '.
                 'or conjugate batch (conjugate gradients) algorithms');
         }
 
-        if (!in_array($cost, ['log', 'sse'])) {
+        if (!in_array($cost, ['log', 'sse'], true)) {
             throw new Exception("Logistic regression cost function can be one of the following: \n".
                 "'log' for log-likelihood and 'sse' for sum of squared errors");
         }

diff --git a/src/Classification/Linear/Perceptron.php b/src/Classification/Linear/Perceptron.php
@@ -97,7 +97,7 @@ public function partialTrain(array $samples, array $targets, array $labels = [])
 
     public function trainBinary(array $samples, array $targets, array $labels): void
     {
-        if ($this->normalizer) {
+        if ($this->normalizer !== null) {
             $this->normalizer->transform($samples);
         }
 
@@ -196,7 +196,7 @@ protected function runGradientDescent(array $samples, array $targets, Closure $g
      */
     protected function checkNormalizedSample(array $sample): array
     {
-        if ($this->normalizer) {
+        if ($this->normalizer !== null) {
             $samples = [$sample];
             $this->normalizer->transform($samples);
             $sample = $samples[0];