Пример #1
0
func TestSpherical(t *testing.T) {
	var d, k, l, iterations int = 64, 6, 4, 1000
	sphere := decoder.NewSpherical(d, k, l)
	for i := 0; i < 100; i++ {
		var ct int = 0
		var distavg float64 = 0.0
		for j := 0; j < iterations; j++ {
			p1, p2 := make([]float64, d), make([]float64, d)
			for k := 0; k < d; k++ {
				p1[k] = rand.Float64()*2 - 1
				p2[k] = p1[k] + rand.NormFloat64()*float64(i/100)
			}
			/* Get the distance of each vector from eachother. */
			distavg += utils.Distance(p1, p2)
			t.Log(distavg)
			mh := hash.NewMurmur(1<<63 - 1)
			/* Decode from 24-dimensions -> 1-dimensional integer */
			hp1, hp2 := sphere.Hash(utils.Normalize(p1)), sphere.Hash(utils.Normalize(p2))
			/* Blurring the integers into a smaller space. */
			hash1, hash2 := mh.Hash(hp1), mh.Hash(hp2)
			if hash1 == hash2 {
				/* Update collision counts. */
				ct++
			}
		}
		t.Log(distavg/float64(iterations), "\t", ct/iterations)
		//TODO test actual output of spherical decoder. here rather than logging
	}
	t.Log("√ Spherical Decoder test complete")
}
Пример #2
0
func TestLSHStream(t *testing.T) {
	var seed int64 = 0
	var d, k, l int = 64, 6, 4
	data := []float64{1.0, 0.0, 2.0, 7.0, 4.0, 0.0, 8.0, 3.0, 2.0, 1.0}
	var inDimensions, outDimentions int = 10, 2
	hash := hash.NewMurmur(1<<63 - 1)
	decoder := decoder.NewSpherical(d, k, l)
	projector := projector.NewDBFriendly(inDimensions, outDimentions, seed)
	lsh := lsh.NewLSH(hash, decoder, projector)
	lsh.LSHHashStream(data, 1)
	t.Log("√ LSH Stream test complete")
}
Пример #3
0
func BenchmarkLargeArray(b *testing.B) {
	var hashSize = 1000
	testHash := hash.NewMurmur(int64(hashSize))
	testArray := make([]int64, 1000)
	for i := 0; i < b.N; i++ {
		b.StopTimer()
		for j := 0; j < len(testArray); j++ {
			testArray[j] = int64(i * j)
		}
		b.StartTimer()
		testHash.Hash(testArray)
	}
}
Пример #4
0
func BenchmarkStream(b *testing.B) {
	var seed int64 = 0
	var d, k, l int = 64, 6, 4
	data := []float64{1.0, 0.0, 2.0, 7.0, 4.0, 0.0, 8.0, 3.0, 2.0, 1.0}
	var inDimensions, outDimentions int = 10, 2
	hash := hash.NewMurmur(1<<63 - 1)
	decoder := decoder.NewSpherical(d, k, l)
	projector := projector.NewDBFriendly(inDimensions, outDimentions, seed)
	for i := 0; i < b.N; i++ {
		lsh := lsh.NewLSH(hash, decoder, projector)
		b.StopTimer()
		lsh.LSHHashStream(data, 1)
		b.StartTimer()
	}
}
Пример #5
0
func TestMurmur(t *testing.T) {
	var hashSize = 100

	testHash := hash.NewMurmur(int64(hashSize))
	resultCount := make([]int64, hashSize)
	for i := 0; i < hashSize*100; i++ {
		fakeArray := make([]int64, 1)
		fakeArray[0] = int64(i)
		resultCount[testHash.Hash(fakeArray)]++
	}
	var maxCount = hashSize * 13 / 10
	var minCount = hashSize * 7 / 10
	for index, indexCount := range resultCount {
		if indexCount > int64(maxCount) || indexCount < int64(minCount) {
			t.Errorf("X - Expected  between %d - %d results, for index %d got %d", minCount, maxCount, index, indexCount)
		}
	}
	t.Log("√ Murmur Hash test complete")
}
Пример #6
0
// The datapoints are seeded in so that the first two data points are near eachother in euclidian geometery and the 3rd and 4th datapoint are
// near eachother in euclidian geometery. So the result1Cluster1 and result2Cluster1 should be closer together than the other two points.
//The same is true for the points in cluster two vs either point in cluster one.
func TestLSHSimple(t *testing.T) {
	var seed int64 = 0
	var d, k, l int = 10, 6, 4
	dataPoint1Cluster1 := []float64{1.0, 0.0, 2.0, 7.0, 4.0, 0.0, 8.0, 3.0, 2.0, 1.0}
	dataPoint2Cluster1 := []float64{2.0, 3.0, 2.0, 6.0, 5.5, 2.0, 8.0, 3.1, 2.0, 0.0}

	dataPoint1Cluster2 := []float64{100.0, -120.0, 6.0, 18.0, 209.0, 0.0, -2.0, 1036.0, 15.0, 123.0}
	dataPoint2Cluster2 := []float64{99.0, -119.0, 2.0, 18.0, 208.5, 0.0, -3.0, 1048.0, 13.0, 122.0}

	var inDimensions, outDimentions int = 10, 2
	hash := hash.NewMurmur(1<<63 - 1)
	decoder := decoder.NewSpherical(d, k, l)
	projector := projector.NewDBFriendly(inDimensions, outDimentions, seed)
	lsh := lsh.NewLSH(hash, decoder, projector)
	result1Cluster1 := lsh.LSHHashSimple(dataPoint1Cluster1)
	result2Cluster1 := lsh.LSHHashSimple(dataPoint2Cluster1)
	result1Cluster2 := lsh.LSHHashSimple(dataPoint1Cluster2)
	result2Cluster2 := lsh.LSHHashSimple(dataPoint2Cluster2)
	// Assert that results are still localy sensetive based on the original euclidian geometry
	if math.Abs(float64(result1Cluster1-result2Cluster1)) > math.Abs(float64(result1Cluster1-result1Cluster2)) {
		t.Errorf("\nThe first datapoint in cluster two is closer to the first data point in cluster one than the second data point in cluster one"+
			"\ndatapoint cluster one datapoint one: %d, \ndatapoint cluster one datapoint two: %d, \ndatapoint cluster two datapoint one: %d",
			result1Cluster1, result2Cluster1, result1Cluster2)
	}
	if math.Abs(float64(result1Cluster1-result2Cluster1)) > math.Abs(float64(result1Cluster1-result2Cluster2)) {
		t.Errorf("\nThe second datapoint in cluster two is closer to the first data point in cluster one than the second data point in cluster one"+
			"\nCluster one datapoint one: %d, \nCluster one datapoint two: %d, \nCluster two datapoint two: %d",
			result1Cluster1, result2Cluster1, result2Cluster2)
	}
	if math.Abs(float64(result1Cluster2-result2Cluster2)) > math.Abs(float64(result1Cluster1-result1Cluster2)) {
		t.Errorf("\nThe first datapoint in cluster one is closer to the first data point in cluster two than the second data point in cluster two"+
			"\nCluster one datapoint one: %d, \nCluster two datapoint one: %d, \nCluster two datapoint two: %d",
			result1Cluster1, result1Cluster2, result2Cluster2)
	}

	t.Log("√ LSH Simple test complete")
}
Пример #7
0
func NewHash(hashMod int32) types.Hash {
	return hash.NewMurmur(hashMod)
}