func TestStreamingKMeansOnNumImagesData(t *testing.T) {
numClusters := 10
lines, err := utils.ReadLines("../demo/data/MNISTnumImages5000.txt")
if err != nil {
panic(err)
}
dimensionality := len(lines[0])
data := utils.StringArrayToFloatArray(lines)
start := time.Now()
kmeansStream := clusterer.NewKMeansStream(numClusters, 10, dimensionality)
for _, vector := range data {
kmeansStream.AddDataPoint(vector)
}
result := kmeansStream.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.")
}
}
func TestStreamingKMeansOnRandomData(t *testing.T) {
filereader := utils.NewDataFileReader(filePath)
start := time.Now()
kmeansStream := clusterer.NewKMeansStream(numClusters, 10, dimensionality)
elapsedtime := time.Since(start)
for {
vector := filereader.Next()
if vector == nil {
break
}
start := time.Now()
kmeansStream.AddDataPoint(vector)
elapsedtime = elapsedtime + time.Since(start)
}
start = time.Now()
result := kmeansStream.GetCentroids()
elapsedtime = elapsedtime + time.Since(start)
totalSqDist := float64(0)
filereader = utils.NewDataFileReader(filePath)
for {
vector := filereader.Next()
if vector == nil {
break
}
_, dist := utils.FindNearestDistance(vector, result)
totalSqDist += dist * dist
}
t.Log("Total Square Distance: ", totalSqDist)
t.Log("Average Square Distance: ", totalSqDist/numDataPoints)
t.Log("Runtime(seconds): ", elapsedtime.Seconds())
if len(result) != numClusters {
t.Errorf("RPHash Stream did not present the correct number of clusters.")
}
}
func NewKMeansStream(k int, n int, dimenstionality int) types.Clusterer {
return clusterer.NewKMeansStream(k, n, dimenstionality)
}