Fix support of a rule in Apriori (#229)

* Clean up test code

* Add test to check support and confidence (failed due to a bug)

* Fix support value of rules
This commit is contained in:
Yuji Uchiyama 2018-02-11 20:42:46 +09:00 committed by Arkadiusz Kondas
parent 3ba35918a3
commit 53f8a89556
2 changed files with 170 additions and 141 deletions

View File

@ -138,7 +138,7 @@ class Apriori implements Associator
$this->rules[] = [ $this->rules[] = [
self::ARRAY_KEY_ANTECEDENT => $antecedent, self::ARRAY_KEY_ANTECEDENT => $antecedent,
self::ARRAY_KEY_CONSEQUENT => $consequent, self::ARRAY_KEY_CONSEQUENT => $consequent,
self::ARRAY_KEY_SUPPORT => $this->support($consequent), self::ARRAY_KEY_SUPPORT => $this->support($frequent),
self::ARRAY_KEY_CONFIDENCE => $confidence, self::ARRAY_KEY_CONFIDENCE => $confidence,
]; ];
} }

View File

@ -46,15 +46,18 @@ class AprioriTest extends TestCase
$apriori = new Apriori(0.5, 0.5); $apriori = new Apriori(0.5, 0.5);
$apriori->train($this->sampleGreek, []); $apriori->train($this->sampleGreek, []);
$this->assertEquals('beta', $apriori->predict([['alpha', 'epsilon'], ['beta', 'theta']])[0][0][0]); $predicted = $apriori->predict([['alpha', 'epsilon'], ['beta', 'theta']]);
$this->assertEquals('alpha', $apriori->predict([['alpha', 'epsilon'], ['beta', 'theta']])[1][0][0]);
$this->assertCount(2, $predicted);
$this->assertEquals([['beta']], $predicted[0]);
$this->assertEquals([['alpha']], $predicted[1]);
} }
public function testPowerSet(): void public function testPowerSet(): void
{ {
$apriori = new Apriori(); $apriori = new Apriori();
$this->assertCount(8, $this->invoke($apriori, 'powerSet', [['a', 'b', 'c']])); $this->assertCount(8, self::invoke($apriori, 'powerSet', [['a', 'b', 'c']]));
} }
public function testApriori(): void public function testApriori(): void
@ -65,143 +68,12 @@ class AprioriTest extends TestCase
$L = $apriori->apriori(); $L = $apriori->apriori();
$this->assertCount(4, $L[2]); $this->assertCount(4, $L[2]);
$this->assertTrue($this->invoke($apriori, 'contains', [$L[2], [1, 2]])); $this->assertTrue(self::invoke($apriori, 'contains', [$L[2], [1, 2]]));
$this->assertFalse($this->invoke($apriori, 'contains', [$L[2], [1, 3]])); $this->assertFalse(self::invoke($apriori, 'contains', [$L[2], [1, 3]]));
$this->assertFalse($this->invoke($apriori, 'contains', [$L[2], [1, 4]])); $this->assertFalse(self::invoke($apriori, 'contains', [$L[2], [1, 4]]));
$this->assertTrue($this->invoke($apriori, 'contains', [$L[2], [2, 3]])); $this->assertTrue(self::invoke($apriori, 'contains', [$L[2], [2, 3]]));
$this->assertTrue($this->invoke($apriori, 'contains', [$L[2], [2, 4]])); $this->assertTrue(self::invoke($apriori, 'contains', [$L[2], [2, 4]]));
$this->assertTrue($this->invoke($apriori, 'contains', [$L[2], [3, 4]])); $this->assertTrue(self::invoke($apriori, 'contains', [$L[2], [3, 4]]));
}
public function testGetRules(): void
{
$apriori = new Apriori(0.4, 0.8);
$apriori->train($this->sampleChars, []);
$this->assertCount(19, $apriori->getRules());
}
public function testAntecedents(): void
{
$apriori = new Apriori();
$this->assertCount(6, $this->invoke($apriori, 'antecedents', [['a', 'b', 'c']]));
}
public function testItems(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertCount(4, $this->invoke($apriori, 'items', []));
}
public function testFrequent(): void
{
$apriori = new Apriori(0.51);
$apriori->train($this->sampleGreek, []);
$this->assertCount(0, $this->invoke($apriori, 'frequent', [[['epsilon'], ['theta']]]));
$this->assertCount(2, $this->invoke($apriori, 'frequent', [[['alpha'], ['beta']]]));
}
public function testCandidates(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertArraySubset([0 => ['alpha', 'beta']], $this->invoke($apriori, 'candidates', [[['alpha'], ['beta'], ['theta']]]));
$this->assertArraySubset([1 => ['alpha', 'theta']], $this->invoke($apriori, 'candidates', [[['alpha'], ['beta'], ['theta']]]));
$this->assertArraySubset([2 => ['beta', 'theta']], $this->invoke($apriori, 'candidates', [[['alpha'], ['beta'], ['theta']]]));
$this->assertCount(3, $this->invoke($apriori, 'candidates', [[['alpha'], ['beta'], ['theta']]]));
}
public function testConfidence(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(0.5, $this->invoke($apriori, 'confidence', [['alpha', 'beta', 'theta'], ['alpha', 'beta']]));
$this->assertEquals(1, $this->invoke($apriori, 'confidence', [['alpha', 'beta'], ['alpha']]));
}
public function testSupport(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(1.0, $this->invoke($apriori, 'support', [['alpha', 'beta']]));
$this->assertEquals(0.5, $this->invoke($apriori, 'support', [['epsilon']]));
}
public function testFrequency(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(4, $this->invoke($apriori, 'frequency', [['alpha', 'beta']]));
$this->assertEquals(2, $this->invoke($apriori, 'frequency', [['epsilon']]));
}
public function testContains(): void
{
$apriori = new Apriori();
$this->assertTrue($this->invoke($apriori, 'contains', [[['a'], ['b']], ['a']]));
$this->assertTrue($this->invoke($apriori, 'contains', [[[1, 2]], [1, 2]]));
$this->assertFalse($this->invoke($apriori, 'contains', [[['a'], ['b']], ['c']]));
}
public function testSubset(): void
{
$apriori = new Apriori();
$this->assertTrue($this->invoke($apriori, 'subset', [['a', 'b'], ['a']]));
$this->assertTrue($this->invoke($apriori, 'subset', [['a'], ['a']]));
$this->assertFalse($this->invoke($apriori, 'subset', [['a'], ['a', 'b']]));
}
public function testEquals(): void
{
$apriori = new Apriori();
$this->assertTrue($this->invoke($apriori, 'equals', [['a'], ['a']]));
$this->assertFalse($this->invoke($apriori, 'equals', [['a'], []]));
$this->assertFalse($this->invoke($apriori, 'equals', [['a'], ['b', 'a']]));
}
/**
* Invokes objects method. Private/protected will be set accessible.
*
* @param string $method Method name to be called
* @param array $params Array of params to be passed
*
* @return mixed
*/
public function invoke(&$object, string $method, array $params = [])
{
$reflection = new ReflectionClass(get_class($object));
$method = $reflection->getMethod($method);
$method->setAccessible(true);
return $method->invokeArgs($object, $params);
}
public function testSaveAndRestore(): void
{
$classifier = new Apriori(0.5, 0.5);
$classifier->train($this->sampleGreek, []);
$testSamples = [['alpha', 'epsilon'], ['beta', 'theta']];
$predicted = $classifier->predict($testSamples);
$filename = 'apriori-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));
} }
public function testAprioriEmpty(): void public function testAprioriEmpty(): void
@ -228,4 +100,161 @@ class AprioriTest extends TestCase
$this->assertEquals([1], array_keys($L)); $this->assertEquals([1], array_keys($L));
$this->assertEquals([['a']], $L[1]); $this->assertEquals([['a']], $L[1]);
} }
public function testGetRules(): void
{
$apriori = new Apriori(0.4, 0.8);
$apriori->train($this->sampleChars, []);
$this->assertCount(19, $apriori->getRules());
}
public function testGetRulesSupportAndConfidence(): void
{
$sample = [['a', 'b'], ['a', 'c']];
$apriori = new Apriori(0, 0);
$apriori->train($sample, []);
$rules = $apriori->getRules();
$this->assertCount(4, $rules);
$this->assertContains([
Apriori::ARRAY_KEY_ANTECEDENT => ['a'],
Apriori::ARRAY_KEY_CONSEQUENT => ['b'],
Apriori::ARRAY_KEY_SUPPORT => 0.5,
Apriori::ARRAY_KEY_CONFIDENCE => 0.5,
], $rules);
$this->assertContains([
Apriori::ARRAY_KEY_ANTECEDENT => ['b'],
Apriori::ARRAY_KEY_CONSEQUENT => ['a'],
Apriori::ARRAY_KEY_SUPPORT => 0.5,
Apriori::ARRAY_KEY_CONFIDENCE => 1.0,
], $rules);
}
public function testAntecedents(): void
{
$apriori = new Apriori();
$this->assertCount(6, self::invoke($apriori, 'antecedents', [['a', 'b', 'c']]));
}
public function testItems(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertCount(4, self::invoke($apriori, 'items', []));
}
public function testFrequent(): void
{
$apriori = new Apriori(0.51);
$apriori->train($this->sampleGreek, []);
$this->assertCount(0, self::invoke($apriori, 'frequent', [[['epsilon'], ['theta']]]));
$this->assertCount(2, self::invoke($apriori, 'frequent', [[['alpha'], ['beta']]]));
}
public function testCandidates(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$candidates = self::invoke($apriori, 'candidates', [[['alpha'], ['beta'], ['theta']]]);
$this->assertCount(3, $candidates);
$this->assertEquals(['alpha', 'beta'], $candidates[0]);
$this->assertEquals(['alpha', 'theta'], $candidates[1]);
$this->assertEquals(['beta', 'theta'], $candidates[2]);
}
public function testConfidence(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(0.5, self::invoke($apriori, 'confidence', [['alpha', 'beta', 'theta'], ['alpha', 'beta']]));
$this->assertEquals(1, self::invoke($apriori, 'confidence', [['alpha', 'beta'], ['alpha']]));
}
public function testSupport(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(1.0, self::invoke($apriori, 'support', [['alpha', 'beta']]));
$this->assertEquals(0.5, self::invoke($apriori, 'support', [['epsilon']]));
}
public function testFrequency(): void
{
$apriori = new Apriori();
$apriori->train($this->sampleGreek, []);
$this->assertEquals(4, self::invoke($apriori, 'frequency', [['alpha', 'beta']]));
$this->assertEquals(2, self::invoke($apriori, 'frequency', [['epsilon']]));
}
public function testContains(): void
{
$apriori = new Apriori();
$this->assertTrue(self::invoke($apriori, 'contains', [[['a'], ['b']], ['a']]));
$this->assertTrue(self::invoke($apriori, 'contains', [[[1, 2]], [1, 2]]));
$this->assertFalse(self::invoke($apriori, 'contains', [[['a'], ['b']], ['c']]));
}
public function testSubset(): void
{
$apriori = new Apriori();
$this->assertTrue(self::invoke($apriori, 'subset', [['a', 'b'], ['a']]));
$this->assertTrue(self::invoke($apriori, 'subset', [['a'], ['a']]));
$this->assertFalse(self::invoke($apriori, 'subset', [['a'], ['a', 'b']]));
}
public function testEquals(): void
{
$apriori = new Apriori();
$this->assertTrue(self::invoke($apriori, 'equals', [['a'], ['a']]));
$this->assertFalse(self::invoke($apriori, 'equals', [['a'], []]));
$this->assertFalse(self::invoke($apriori, 'equals', [['a'], ['b', 'a']]));
}
public function testSaveAndRestore(): void
{
$classifier = new Apriori(0.5, 0.5);
$classifier->train($this->sampleGreek, []);
$testSamples = [['alpha', 'epsilon'], ['beta', 'theta']];
$predicted = $classifier->predict($testSamples);
$filename = 'apriori-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));
}
/**
* Invokes objects method. Private/protected will be set accessible.
*
* @param string $method Method name to be called
* @param array $params Array of params to be passed
*
* @return mixed
*/
private static function invoke(&$object, string $method, array $params = [])
{
$reflection = new ReflectionClass(get_class($object));
$method = $reflection->getMethod($method);
$method->setAccessible(true);
return $method->invokeArgs($object, $params);
}
} }