octoleo/php-ml
1
0
Fork 0
mirror of https://github.com/Llewellynvdm/php-ml.git synced 2025-01-09 16:36:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix string representation of integer labels issue in NaiveBayes (#206)

Browse Source 
* Update NaiveBayes.php

This fixes an issue using string labels that are string representations of integers, e.g. "1998" getting cast to (int)1998.

* Update NaiveBayes.php

fixes superfluous whitespace error

* added tests for naive bayes with numeric labels

* added array_unique

* nested array_flips for speed

* nested the array flips inside the array map

* to appear style CI test
This commit is contained in:
Jonathan Baldie 2018-01-31 20:44:44 +00:00 committed by Arkadiusz Kondas
parent 10070d97fd
commit e318921076
2 changed files with 60 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/Phpml/Classification/NaiveBayes.php
View File

@ -66,8 +66,7 @@ class NaiveBayes implements Classifier
$this->sampleCount = count($this->samples); $this->sampleCount = count($this->samples);
$this->featureCount = count($this->samples[0]); $this->featureCount = count($this->samples[0]);
$labelCounts = array_count_values($this->targets); $this->labels = array_map('strval', array_flip(array_flip($this->targets)));
$this->labels = array_keys($labelCounts);
foreach ($this->labels as $label) { foreach ($this->labels as $label) {
$samples = $this->getSamplesByLabel($label); $samples = $this->getSamplesByLabel($label);
$this->p[$label] = count($samples) / $this->sampleCount; $this->p[$label] = count($samples) / $this->sampleCount;

59
tests/Phpml/Classification/NaiveBayesTest.php
View File

@ -68,4 +68,63 @@ class NaiveBayesTest extends TestCase
$this->assertEquals($classifier, $restoredClassifier); $this->assertEquals($classifier, $restoredClassifier);
$this->assertEquals($predicted, $restoredClassifier->predict($testSamples)); $this->assertEquals($predicted, $restoredClassifier->predict($testSamples));
} }
public function testPredictSimpleNumericLabels(): void
{
$samples = [[5, 1, 1], [1, 5, 1], [1, 1, 5]];
$labels = ['1996', '1997', '1998'];
$classifier = new NaiveBayes();
$classifier->train($samples, $labels);
$this->assertEquals('1996', $classifier->predict([3, 1, 1]));
$this->assertEquals('1997', $classifier->predict([1, 4, 1]));
$this->assertEquals('1998', $classifier->predict([1, 1, 6]));
}
public function testPredictArrayOfSamplesNumericalLabels(): void
{
$trainSamples = [[5, 1, 1], [1, 5, 1], [1, 1, 5]];
$trainLabels = ['1996', '1997', '1998'];
$testSamples = [[3, 1, 1], [5, 1, 1], [4, 3, 8], [1, 1, 2], [2, 3, 2], [1, 2, 1], [9, 5, 1], [3, 1, 2]];
$testLabels = ['1996', '1996', '1998', '1998', '1997', '1997', '1996', '1996'];
$classifier = new NaiveBayes();
$classifier->train($trainSamples, $trainLabels);
$predicted = $classifier->predict($testSamples);
$this->assertEquals($testLabels, $predicted);
// Feed an extra set of training data.
$samples = [[1, 1, 6]];
$labels = ['1999'];
$classifier->train($samples, $labels);
$testSamples = [[1, 1, 6], [5, 1, 1]];
$testLabels = ['1999', '1996'];
$this->assertEquals($testLabels, $classifier->predict($testSamples));
}
public function testSaveAndRestoreNumericLabels(): void
{
$trainSamples = [[5, 1, 1], [1, 5, 1], [1, 1, 5]];
$trainLabels = ['1996', '1997', '1998'];
$testSamples = [[3, 1, 1], [5, 1, 1], [4, 3, 8]];
$testLabels = ['1996', '1996', '1998'];
$classifier = new NaiveBayes();
$classifier->train($trainSamples, $trainLabels);
$predicted = $classifier->predict($testSamples);
$filename = 'naive-bayes-test-'.random_int(100, 999).'-'.uniqid();
$filepath = tempnam(sys_get_temp_dir(), $filename);
$modelManager = new ModelManager();
$modelManager->saveToFile($classifier, $filepath);
$restoredClassifier = $modelManager->restoreFromFile($filepath);
$this->assertEquals($classifier, $restoredClassifier);
$this->assertEquals($predicted, $restoredClassifier->predict($testSamples));
}
} }