예제 #1
0
func TestKMeansOnNumImagesData(t *testing.T) {
	numClusters := 10
	lines, err := utils.ReadLines("../demo/data/MNISTnumImages5000.txt")
	if err != nil {
		panic(err)
	}
	data := utils.StringArrayToFloatArray(lines)

	start := time.Now()
	clusterer := clusterer.NewKMeansSimple(numClusters, data)
	clusterer.Run()

	result := clusterer.GetCentroids()
	time := time.Since(start)

	totalSqDist := float64(0)
	for _, vector := range data {
		_, dist := utils.FindNearestDistance(vector, result)
		totalSqDist += dist * dist
	}

	t.Log("Total Square Distance: ", totalSqDist)
	t.Log("Average Square Distance: ", totalSqDist/float64(len(data)))
	t.Log("Runtime(seconds): ", time.Seconds())

	if len(result) != numClusters {
		t.Errorf("RPHash Stream did not present the correct number of clusters.")
	}
}
예제 #2
0
func TestSimpleLeastDistanceVsKmeans(t *testing.T) {

	//Create fake data
	var numClusters = 5
	var numRows = 400
	var dimensionality = 1000
	data := make([][]float64, numRows, numRows)
	for i := 0; i < numRows; i++ {
		row := make([]float64, dimensionality, dimensionality)
		for j := 0; j < dimensionality; j++ {
			row[j] = rand.Float64()
		}
		data[i] = row
	}

	start := time.Now()
	//Test RPHash with Fake Object
	RPHashObject := reader.NewSimpleArray(data, numClusters)
	simpleObject := simple.NewSimple(RPHashObject)
	simpleObject.Run()

	if len(RPHashObject.GetCentroids()) != numClusters {
		t.Errorf("Requested %v centriods. But RPHashSimple returned %v.", numClusters, len(RPHashObject.GetCentroids()))
	}
	rpHashResult := RPHashObject.GetCentroids()
	fmt.Println("RPHash: ", time.Since(start))
	//Find clusters using KMeans
	start = time.Now()
	clusterer := clusterer.NewKMeansSimple(numClusters, data)
	clusterer.Run()

	kMeansResult := clusterer.GetCentroids()
	fmt.Println("kMeans: ", time.Since(start))

	var kMeansAssignment = 0
	var rpHashAssignment = 0
	var matchingAssignmentCount = 0
	var kMeansTotalDist = float64(0)
	var rpHashTotalDist = float64(0)
	for _, vector := range data {
		rpHashAssignment, _ = utils.FindNearestDistance(vector, rpHashResult)
		kMeansAssignment, _ = utils.FindNearestDistance(vector, kMeansResult)
		kMeansTotalDist += utils.Distance(vector, kMeansResult[kMeansAssignment])
		rpHashTotalDist += utils.Distance(vector, rpHashResult[rpHashAssignment])
		//t.Log(rpHashAssignments[i], kMeansAssignments[i]);
		if rpHashAssignment == kMeansAssignment {
			matchingAssignmentCount += 1
		}
	}
	t.Log("RPHash:", rpHashTotalDist)
	t.Log("KMeans:", kMeansTotalDist)
	t.Log("Ratio: ", kMeansTotalDist/rpHashTotalDist)
}
예제 #3
0
func BenchmarkKMeans(b *testing.B) {
	var numClusters = 5
	var numRows = 4000
	var dimensionality = 1000
	data := make([][]float64, numRows, numRows)
	for i := 0; i < numRows; i++ {
		row := make([]float64, dimensionality, dimensionality)
		for j := 0; j < dimensionality; j++ {
			row[j] = rand.Float64()
		}
		data[i] = row
	}
	for i := 0; i < b.N; i++ {
		clusterer := clusterer.NewKMeansSimple(numClusters, data)
		clusterer.Run()

		clusterer.GetCentroids()
	}
}
예제 #4
0
func TestClustererUniformVectors(t *testing.T) {
	//initilize data
	var numClusters = 2
	var numDataPoints = 8
	var dimensionality = 4
	data := make([][]float64, numDataPoints)
	for i := 0; i < numDataPoints; i++ {
		data[i] = make([]float64, dimensionality)
		for j := 0; j < dimensionality; j++ {
			data[i][j] = float64(i)
		}
	}

	//run test
	clusterer := clusterer.NewKMeansSimple(numClusters, data)
	clusterer.Run()
	var result = clusterer.GetCentroids()

	//Test Results
	if len(result) != numClusters {
		t.Errorf("Clusterer created %v clusters. When %v was input for k.", len(result), numClusters)
	}
	if len(result[0]) != dimensionality {
		t.Errorf("Cluster dimensionalioty of %v does not match the dimensionality of the input data, %v.", len(result[0]), dimensionality)
	}
	expectedResults := make([]float64, numClusters)
	expectedResults[0] = 1.5 // (0+1+2+3)/4 = 1.5
	expectedResults[1] = 5.5 //  (4+5+6+7)/4 = 5.5
	for i := 0; i < numClusters; i++ {
		for j := 0; j < dimensionality; j++ {
			if result[i][j] != expectedResults[i] {
				t.Errorf("Data did not cluster as expected. Data: %v, Clusters: %v. Failure at %v, %v.", data, result, i, j)
			}
		}
	}
}