Moved function wk to kmeansEstimator

Author: mpraski

clusters.go

@@ -93,7 +93,15 @@ var (
 	}
 
 	EuclideanDistanceSquared = func(a, b []float64) float64 {
-		t := floats.Distance(a, b, 2)
-		return t * t
+		var (
+			s, t float64
+		)
+
+		for i, _ := range a {
+			t = a[i] - b[i]
+			s += t * t
+		}
+
+		return s
 	}
 )

common.go

@@ -4,8 +4,6 @@ import (
 	"container/heap"
 	"math/rand"
 	"sync"
-
-	"gonum.org/v1/gonum/floats"
 )
 
 // struct denoting start and end indices of database portion to be scanned for nearest neighbours by workers in DBSCAN and OPTICS
@@ -68,19 +66,6 @@ func (pq *priorityQueue) Update(item *pItem, value int, priority float64) {
 	heap.Fix(pq, item.i)
 }
 
-func wk(data [][]float64, centroids [][]float64, mapping []int) float64 {
-	var (
-		l  = float64(2 * len(data[0]))
-		wk = make([]float64, len(centroids))
-	)
-
-	for i := 0; i < len(mapping); i++ {
-		wk[mapping[i]-1] += EuclideanDistanceSquared(centroids[mapping[i]-1], data[i]) / l
-	}
-
-	return floats.Sum(wk)
-}
-
 func bounds(data [][]float64) []*[2]float64 {
 	var (
 		wg sync.WaitGroup

common_test.go

@@ -95,7 +95,7 @@ func TestBounds(t *testing.T) {
 
 	d, e := i.Import(f, 0, 2)
 	if e != nil {
-		t.Errorf("Error importing data: %s", e.Error())
+		t.Errorf("Error importing data: %s\n", e.Error())
 	}
 
 	bounds := bounds(d)

errors.go

@@ -3,14 +3,13 @@ package clusters
 import "errors"
 
 var (
-	ErrEmptySet            = errors.New("Empty training set")
-	ErrNotTrained          = errors.New("You need to train the algorithm first")
-	ErrZeroIterations      = errors.New("Number of iterations cannot be less than 1")
-	ErrOneCluster          = errors.New("Number of clusters cannot be less than 2")
-	ErrZeroEpsilon         = errors.New("Epsilon cannot be 0")
-	ErrZeroMinpts          = errors.New("MinPts cannot be 0")
-	ErrZeroWorkers         = errors.New("Number of workers cannot be less than 0")
-	ErrZeroXi              = errors.New("Xi cannot be 0")
-	ErrInvalidRange        = errors.New("Range is invalid")
-	ErrTestingNotSupported = errors.New("Testing is not supported for this algorithm")
+	ErrEmptySet       = errors.New("Empty training set")
+	ErrNotTrained     = errors.New("You need to train the algorithm first")
+	ErrZeroIterations = errors.New("Number of iterations cannot be less than 1")
+	ErrOneCluster     = errors.New("Number of clusters cannot be less than 2")
+	ErrZeroEpsilon    = errors.New("Epsilon cannot be 0")
+	ErrZeroMinpts     = errors.New("MinPts cannot be 0")
+	ErrZeroWorkers    = errors.New("Number of workers cannot be less than 0")
+	ErrZeroXi         = errors.New("Xi cannot be 0")
+	ErrInvalidRange   = errors.New("Range is invalid")
 )

kmeans_estimator.go

@@ -1,7 +1,6 @@
 package clusters
 
 import (
-	"fmt"
 	"math"
 	"math/rand"
 	"time"
@@ -72,12 +71,12 @@ func (c *kmeansEstimator) Estimate(data [][]float64) (int, error) {
 
 		c.learn(data)
 
-		wks[i] = math.Log(wk(c.d, c.m, c.a))
+		wks[i] = math.Log(c.wk(c.d, c.m, c.a))
 
 		for j := 0; j < c.max; j++ {
 			c.learn(c.buildRandomizedSet(size, bounds))
 
-			bwkbs[j] = math.Log(wk(c.d, c.m, c.a))
+			bwkbs[j] = math.Log(c.wk(c.d, c.m, c.a))
 			one[j] = 1
 		}
 
@@ -92,9 +91,6 @@ func (c *kmeansEstimator) Estimate(data [][]float64) (int, error) {
 
 	floats.Scale(math.Sqrt(1+(1/float64(c.max))), sk)
 
-	fmt.Printf("WKBS: %v\n", wkbs)
-	fmt.Printf("SK: %v\n", sk)
-
 	for i := 0; i < c.max-1; i++ {
 		if wkbs[i] >= wkbs[i+1]-sk[i+1] {
 			estimated = i + 1
@@ -106,7 +102,6 @@ func (c *kmeansEstimator) Estimate(data [][]float64) (int, error) {
 }
 
 // private
-
 func (c *kmeansEstimator) learn(data [][]float64) {
 	c.d = data
 
@@ -124,8 +119,6 @@ func (c *kmeansEstimator) learn(data [][]float64) {
 		c.run()
 		c.check()
 	}
-
-	c.n = nil
 }
 
 func (c *kmeansEstimator) initializeMeansWithData() {
@@ -223,6 +216,19 @@ func (c *kmeansEstimator) check() {
 	c.oldchanges = c.changes
 }
 
+func (c *kmeansEstimator) wk(data [][]float64, centroids [][]float64, mapping []int) float64 {
+	var (
+		l  = float64(2 * len(data[0]))
+		wk = make([]float64, len(centroids))
+	)
+
+	for i := 0; i < len(mapping); i++ {
+		wk[mapping[i]-1] += EuclideanDistanceSquared(centroids[mapping[i]-1], data[i]) / l
+	}
+
+	return floats.Sum(wk)
+}
+
 func (c *kmeansEstimator) buildRandomizedSet(size int, bounds []*[2]float64) [][]float64 {
 	var (
 		l = len(bounds)