Golang matrix.Zeros函数代码示例

func TestDoPairPointCentroidJobs(t *testing.T) {
	r := 4
	c := 2
	dataPoints := matrix.Zeros(r, c)
	//	centroidSqDist := matrix.Zeros(r, c)
	centroids := matrix.Zeros(r, c)

	done := make(chan int)
	jobs := make(chan PairPointCentroidJob, r)
	results := make(chan PairPointCentroidResult, minimum(1024, r))

	var md ManhattanDist

	go addPairPointCentroidJobs(jobs, dataPoints, centroids, md, results)

	for i := 0; i < r; i++ {
		go doPairPointCentroidJobs(done, jobs)
	}

	j := 0
	for ; j < r; j++ {
		<-done
	}

	if j != r {
		t.Errorf("doPairPointToCentroidJobs jobs processed=%d.  Should be %d", j, r)
	}
}

// Kmeansp returns means and distance squared of the coordinates for each
// centroid using parallel computation.
//
// Input values
//
// datapoints - a kX2 matrix of R^2 coordinates
//
// centroids - a kX2 matrix of R^2 coordinates for centroids.
//
// measurer - anythng that implements the matutil.VectorMeasurer interface to
// calculate the distance between a centroid and datapoint. (e.g., Euclidian
// distance)
//
// Return values
//
// centroidMean - a kX2 matrix where the row number corresponds to the same
// row in the centroid matrix and the two columns are the means of the
// coordinates for that cluster.  i.e., the best centroids that could
// be determined.
//
//  ____      ______
//  | 12.29   32.94 | <-- The mean of coordinates for centroid 0
//  | 4.6     29.22 | <-- The mean of coordinates for centroid 1
//  |_____    ______|
//
//
// centroidSqErr - a kX2 matrix where the first column contains a number
// indicating the centroid and the second column contains the minimum
// distance between centroid and point squared.  (i.e., the squared error)
//
//  ____      _______
//  | 0        38.01 | <-- Centroid 0, squared error for the coordinates in row 0 of datapoints
//  | 1        23 .21| <-- Centroid 1, squared error for the coordinates in row 1 of datapoints
//  | 0        14.12 | <-- Centroid 0, squared error for the coordinates in row 2 of datapoints
//  _____     _______
//func Kmeansp(datapoints, centroids *matrix.DenseMatrix, measurer matutil.VectorMeasurer) (centroidMean,
func Kmeansp(datapoints *matrix.DenseMatrix, k int, cc CentroidChooser, measurer matutil.VectorMeasurer) (centroidMean,
	centroidSqErr *matrix.DenseMatrix, err error) {
	//k, _ := centroids.GetSize()
	fp, _ := os.Create("/var/tmp/km.log")
	w := io.Writer(fp)
	log.SetOutput(w)

	centroids := cc.ChooseCentroids(datapoints, k)
	numRows, numCols := datapoints.GetSize()
	centroidSqErr = matrix.Zeros(numRows, numCols)
	centroidMean = matrix.Zeros(k, numCols)

	jobs := make(chan PairPointCentroidJob, numworkers)
	results := make(chan PairPointCentroidResult, minimum(1024, numRows))
	done := make(chan int, numworkers)

	go addPairPointCentroidJobs(jobs, datapoints, centroidSqErr, centroids, measurer, results)
	for i := 0; i < numworkers; i++ {
		go doPairPointCentroidJobs(done, jobs)
	}
	go awaitPairPointCentroidCompletion(done, results)
	processPairPointToCentroidResults(centroidSqErr, results) // This blocks so that all the results can be processed

	// Now that you have each data point grouped with a centroid, iterate
	// through the  centroidSqErr martix and for each centroid retrieve the
	// original coordinates from datapoints and place the results in
	// pointsInCuster.
	for c := 0; c < k; c++ {
		// c is the index that identifies the current centroid.
		// d is the index that identifies a row in centroidSqErr and datapoints.
		// Select all the rows in centroidSqErr whose first col value == c.
		// Get the corresponding row vector from datapoints and place it in pointsInCluster.
		matches, err := centroidSqErr.FiltColMap(float64(c), float64(c), 0) //rows with c in column 0.
		if err != nil {
			return centroidMean, centroidSqErr, nil
		}
		// It is possible that some centroids will not have any points, so there
		// may not be any matches in the first column of centroidSqErr.
		if len(matches) == 0 {
			continue
		}

		pointsInCluster := matrix.Zeros(len(matches), 2)
		for d, rownum := range matches {
			pointsInCluster.Set(d, 0, datapoints.Get(int(rownum), 0))
			pointsInCluster.Set(d, 1, datapoints.Get(int(rownum), 1))
		}

		// pointsInCluster now contains all the data points for the current
		// centroid.  Take the mean of each of the 2 cols in pointsInCluster.
		means := pointsInCluster.MeanCols()
		centroidMean.Set(c, 0, means.Get(0, 0))
		centroidMean.Set(c, 1, means.Get(0, 1))
	}
	return
}

func TestAssessClusters(t *testing.T) {
	r, c := DATAPOINTS.GetSize()
	CentPointDist := matrix.Zeros(r, c)

	done := make(chan int)
	jobs := make(chan PairPointCentroidJob, r)
	results := make(chan PairPointCentroidResult, minimum(1024, r))

	var md ManhattanDist
	go addPairPointCentroidJobs(jobs, DATAPOINTS, CENTROIDS, md, results)

	for i := 0; i < r; i++ {
		go doPairPointCentroidJobs(done, jobs)
	}
	go awaitPairPointCentroidCompletion(done, results)

	clusterChanged := assessClusters(CentPointDist, results)
	if clusterChanged != true {
		t.Errorf("TestAssessClusters: clusterChanged=%b and should be true.", clusterChanged)
	}

	if CentPointDist.Get(9, 0) != 0 || CentPointDist.Get(10, 0) != 1 {
		t.Errorf("TestAssessClusters: rows 9 and 10 should have 0 and 1 in column 0, but received %v", CentPointDist)
	}
}

func TestComputeCentroid(t *testing.T) {
	empty := matrix.Zeros(0, 0)
	_, err := ComputeCentroid(empty)
	if err == nil {
		t.Errorf("Did not raise error on empty matrix")
	}
	twoByTwo := matrix.Ones(2, 2)
	centr, err := ComputeCentroid(twoByTwo)
	if err != nil {
		t.Errorf("Could not compute centroid, err=%v", err)
	}
	expected := matrix.MakeDenseMatrix([]float64{1.0, 1.0}, 1, 2)
	if !matrix.Equals(centr, expected) {
		t.Errorf("Incorrect centroid: was %v, should have been %v", expected, centr)
	}
	twoByTwo.Set(0, 0, 3.0)
	expected.Set(0, 0, 2.0)
	centr, err = ComputeCentroid(twoByTwo)
	if err != nil {
		t.Errorf("Could not compute centroid, err=%v", err)
	}
	if !matrix.Equals(centr, expected) {
		t.Errorf("Incorrect centroid: was %v, should have been %v", expected, centr)
	}
}

// chooseCentroids picks random centroids based on the min and max values in the matrix
// and return a k by m matrix of the centroids.
func (c randCentroids) ChooseCentroids(mat *matrix.DenseMatrix, k int) *matrix.DenseMatrix {
	_, cols := mat.GetSize()
	centroids := matrix.Zeros(k, cols)

	for colnum := 0; colnum < cols; colnum++ {
		r := mat.ColSlice(colnum)

		minj := float64(0)
		// min value from column
		for _, val := range r {
			minj = math.Min(minj, val)
		}

		// max value from column
		maxj := float64(0)
		for _, val := range r {
			maxj = math.Max(maxj, val)
		}

		// create a slice of random centroids
		// based on maxj + minJ * random num to stay in range
		for h := 0; h < k; h++ {
			randInRange := ((maxj - minj) * rand.Float64()) + minj
			centroids.Set(h, colnum, randInRange)
		}
	}
	return centroids
}

// modelMean calculates the mean between all points in a model and a centroid.
func modelMean(points, centroid *matrix.DenseMatrix) *matrix.DenseMatrix {
	prows, pcols := points.GetSize()
	pdist := matrix.Zeros(prows, pcols)

	for i := 0; i < prows; i++ {
		diff := matrix.Difference(centroid, points.GetRowVector(i))
		pdist.SetRowVector(diff, i)
	}
	return pdist.MeanCols()
}

func TestAddPairPointToCentroidJob(t *testing.T) {
	r := 4
	c := 2
	jobs := make(chan PairPointCentroidJob, r)
	results := make(chan PairPointCentroidResult, minimum(1024, r))
	dataPoints := matrix.Zeros(r, c)
	//	centroidSqDist := matrix.Zeros(r, c)
	centroids := matrix.Zeros(r, c)

	var ed EuclidDist

	go addPairPointCentroidJobs(jobs, dataPoints, centroids, ed, results)
	i := 0
	for ; i < r; i++ {
		<-jobs
	}

	if i != r {
		t.Errorf("addPairPointToCentroidJobs number of jobs=%d.  Should be %d", i, r)
	}
}

func TestProcessPairPointToCentroidResults(t *testing.T) {
	r := 4
	c := 2
	dataPoints := matrix.Zeros(r, c)
	centroidSqDist := matrix.Zeros(r, c)
	centroids := matrix.Zeros(r, c)

	done := make(chan int)
	jobs := make(chan PairPointCentroidJob, r)
	results := make(chan PairPointCentroidResult, minimum(1024, r))

	var md matutil.ManhattanDist
	go addPairPointCentroidJobs(jobs, dataPoints, centroids, centroidSqDist, md, results)

	for i := 0; i < r; i++ {
		go doPairPointCentroidJobs(done, jobs)
	}
	go awaitPairPointCentroidCompletion(done, results)

	//TODO check deterministic results of centroidDistSq
	processPairPointToCentroidResults(centroidSqDist, results)

}

// Needs comments
func (c EllipseCentroids) ChooseCentroids(mat *matrix.DenseMatrix, k int) *matrix.DenseMatrix {
	_, cols := mat.GetSize()
	var xmin, xmax, ymin, ymax = matutil.GetBoundaries(mat)
	x0, y0 := xmin+(xmax-xmin)/2.0, ymin+(ymax-ymin)/2.0
	centroids := matrix.Zeros(k, cols)
	rx, ry := xmax-x0, ymax-y0
	thetaInit := rand.Float64() * math.Pi

	for i := 0; i < k; i++ {
		centroids.Set(i, 0, rx*c.frac*math.Cos(thetaInit+float64(i)*math.Pi/float64(k)))
		centroids.Set(i, 1, ry*c.frac*math.Sin(thetaInit+float64(i)*math.Pi/float64(k)))
	}
	return centroids
}

func makeCentPointDist(datapoints, centroids *matrix.DenseMatrix) *matrix.DenseMatrix {
	r, c := datapoints.GetSize()
	CentPointDist := matrix.Zeros(r, c)

	done := make(chan int)
	jobs := make(chan PairPointCentroidJob, r)
	results := make(chan PairPointCentroidResult, minimum(1024, r))
	var ed EuclidDist

	go addPairPointCentroidJobs(jobs, datapoints, centroids, ed, results)

	for i := 0; i < r; i++ {
		go doPairPointCentroidJobs(done, jobs)
	}
	go awaitPairPointCentroidCompletion(done, results)

	clusterChanged := assessClusters(CentPointDist, results)

	if clusterChanged == true || clusterChanged == false {
	}
	return CentPointDist
}

// Load loads a tab delimited text file of floats into a matrix.
func Load(fname, sep string) (*matrix.DenseMatrix, error) {
	z := matrix.Zeros(1, 1)

	fp, err := os.Open(fname)
	if err != nil {
		return z, err
	}
	defer fp.Close()

	data := make([]float64, 0)
	cols := 0
	r := bufio.NewReader(fp)
	linenum := 0
	eof := false

	for !eof {
		var line string
		var buf []byte

		buf, _, err := r.ReadLine()
		line = string(buf)

		if err == io.EOF {
			err = nil
			eof = true
			break
		} else if err != nil {
			return z, errors.New(fmt.Sprintf("goxmean.Load: reading linenum %d: %v", linenum, err))
		}

		l1 := strings.TrimRight(line, "\n")
		l := strings.Split(l1, sep)

		// If each line does not have the same number of columns then error
		if linenum == 0 {
			cols = len(l)
		}

		if len(l) != cols {
			return z, errors.New(fmt.Sprintf("Load(): linenum %d has %d columns.  It should have %d columns.", linenum, len(line), cols))
		}

		if len(l) < 2 {
			return z, errors.New(fmt.Sprintf("Load(): linenum %d has only %d elements", linenum, len(line)))
		}

		linenum++

		// Convert the strings to  float64 and build up the slice t by appending.
		t := make([]float64, 0)

		for _, v := range l {
			v = strings.TrimSpace(v)
			f, err := strconv.ParseFloat(v, 64)
			if err != nil {
				return z, errors.New(fmt.Sprintf("goxmeans.Load: cannot convert value %s to float64.", v))
			}
			t = append(t, f)
		}
		data = append(data, t...)
	}
	mat := matrix.MakeDenseMatrix(data, linenum, cols)
	//fmt.Println(time.Now())n // flag for debugging
	return mat, nil
}

// kmeans partitions datapoints into K clusters.  This results in a partitioning of
// the data space into Voronoi cells.  The problem is NP-hard so here we attempt
// to parallelize or make concurrent as many processes as possible to reduce the
// running time.
//
// 1. Place K points into the space represented by the objects that are being clustered.
// These points represent initial group centroids.
//
// 2. Assign each object to the group that has the closest centroid.
//
// 3. When all objects have been assigned, recalculate the positions of the K centroids
// by calculating the mean of all cooridnates in a cluster and making that
// the new centroid.
//
// 4. Repeat Steps 2 and 3 until the centroids no longer move.
//
// centroids is K x M matrix that cotains the coordinates for the centroids.
// The centroids are indexed by the 0 based rows of this matrix.
//  ____      _________
//  | 12.29   32.94 ... | <-- The coordinates for centroid 0
//  | 4.6     29.22 ... | <-- The coordinates for centroid 1
//  |_____    __________|
//
//
// CentPointDist is ax R x M matrix.  The rows have a 1:1 relationship to
// the rows in datapoints.  Column 0 contains the row number in centroids
// that corresponds to the centroid for the datapoint in row i of this matrix.
// Column 1 contains (x_i - mu(i))^2.
//  ____      _______
//  | 3        38.01 | <-- Centroid 3, squared error for the coordinates in row 0 of datapoints
//  | 1        23 .21| <-- Centroid 1, squared error for the coordinates in row 1 of datapoints
//  | 0        14.12 | <-- Centroid 0, squared error for the coordinates in row 2 of datapoints
//  _____     _______
//
func kmeans(datapoints, centroids *matrix.DenseMatrix, measurer VectorMeasurer) Model {
	/*  datapoints				  CentPoinDist            centroids
	                                  ________________
	    ____	  ____				  __|__	  ______	 |	  ____	___________
	    | ...	 |				 |	...			|	 V	 | ...		       |
	    | 3.0  5.1| <-- row i --> |	3	  32.12 |  row 3 | 3	 38.1, ... |
	    |____  ___|				 |____	  ______|	     |___	__________ |
	*/
	R, M := datapoints.GetSize()
	CentPointDist := matrix.Zeros(R, 2)
	k, _ := centroids.GetSize()

	clusterChanged := true
	var clusters []cluster

	for clusterChanged == true {
		clusterChanged = false
		clusters = make([]cluster, 0)

		jobs := make(chan PairPointCentroidJob, 1024)
		results := make(chan PairPointCentroidResult, 1024)
		done := make(chan int, 1024)

		// Pair each point with its closest centroid.
		go addPairPointCentroidJobs(jobs, datapoints, centroids, measurer, results)
		for i := 0; i < numworkers; i++ {
			go doPairPointCentroidJobs(done, jobs)
		}
		go awaitPairPointCentroidCompletion(done, results)

		clusterChanged = assessClusters(CentPointDist, results) // This blocks so that all the results can be processed

		// You have each data point grouped with a centroid,
		for idx, cent := 0, 0; cent < k; cent++ {
			// Select all the rows in CentPointDist whose first col value == cent.
			// Get the corresponding row vector from datapoints and place it in pointsInCluster.
			r, _ := CentPointDist.GetSize()
			matches := make([]int, 0)

			for i := 0; i < r; i++ {
				v := CentPointDist.Get(i, 0)
				if v == float64(cent) {
					matches = append(matches, i)
				}
			}

			// It is possible that some centroids may have zero points, so there
			// may not be any matches.
			if len(matches) == 0 {
				continue
			}

			pointsInCluster := matrix.Zeros(len(matches), M)
			i := 0

			for _, rownum := range matches {
				pointsInCluster.Set(i, 0, datapoints.Get(int(rownum), 0))
				pointsInCluster.Set(i, 1, datapoints.Get(int(rownum), 1))
				i++
			}

			// pointsInCluster now contains all the data points for the current
			// centroid.  The mean of the coordinates for this cluster becomes
			// the new centroid for this cluster.
			mean := pointsInCluster.MeanCols()
			centroids.SetRowVector(mean, cent)
//.........这里部分代码省略.........

// Load loads a tab delimited text file of floats into a slice.
// Assume last column is the target.
// For now, we limit ourselves to two columns
func Load(fname string) (*matrix.DenseMatrix, error) {
	datamatrix := matrix.Zeros(1, 1)
	data := make([]float64, 2048)
	idx := 0

	fp, err := os.Open(fname)
	if err != nil {
		return datamatrix, err
	}
	defer fp.Close()

	r := bufio.NewReader(fp)
	linenum := 1
	eof := false
	for !eof {
		var line string
		var buf []byte
		//		line, err := r.ReadString('\n')
		buf, _, err := r.ReadLine()
		line = string(buf)
		//	fmt.Printf("linenum=%d buf=%v line=%v\n",linenum,buf, line)

		if err == io.EOF {
			err = nil
			eof = true
			break
		} else if err != nil {
			return datamatrix, errors.New(fmt.Sprintf("means.Load: reading linenum %d: %v", linenum, err))
		}

		linenum++
		l1 := strings.TrimRight(line, "\n")
		l := strings.Split(l1, "\t")

		if len(l) < 2 {
			return datamatrix, errors.New(fmt.Sprintf("means.Load: linenum %d has only %d elements", linenum, len(line)))
		}

		// for now assume 2 dimensions only
		f0, err := Atof64(string(l[0]))
		if err != nil {
			return datamatrix, errors.New(fmt.Sprintf("means.Load: cannot convert f0 %s to float64.", l[0]))
		}
		f1, err := Atof64(string(l[1]))

		if err != nil {
			return datamatrix, errors.New(fmt.Sprintf("means.Load: cannot convert f1 %s to float64.", l[1]))
		}

		if linenum >= len(data) {
			data = append(data, f0, f1)
		} else {
			data[idx] = f0
			idx++
			data[idx] = f1
			idx++
		}
	}
	numcols := 2
	datamatrix = matrix.MakeDenseMatrix(data, linenum-1, numcols)
	return datamatrix, nil
}

// Kmeansbi bisects a given cluster and determines which centroids give the lowest error.
// Take the points in a cluster
// While the number of cluster < k
//    for every cluster
//        measure total error
//        cacl kmeansp with k=2 on a given cluster
//        measure total error after kmeansp split
//    choose the cluster split with the lowest SSE
//    commit the chosen split
//
// N.B. We are using SSE until the BIC is completed.
func Kmeansbi(datapoints *matrix.DenseMatrix, k int, cc CentroidChooser, measurer matutil.VectorMeasurer) (matCentroidlist, clusterAssignment *matrix.DenseMatrix, err error) {
	numRows, numCols := datapoints.GetSize()
	clusterAssignment = matrix.Zeros(numRows, numCols)
	matCentroidlist = matrix.Zeros(k, numCols)
	centroid0 := datapoints.MeanCols()
	centroidlist := []*matrix.DenseMatrix{centroid0}

	// Initially create one cluster.
	for j := 0; j < numRows; j++ {
		point := datapoints.GetRowVector(j)
		distJ, err := measurer.CalcDist(centroid0, point)
		if err != nil {
			return matCentroidlist, clusterAssignment, errors.New(fmt.Sprintf("Kmeansbi: CalcDist returned err=%v", err))
		}
		clusterAssignment.Set(j, 1, math.Pow(distJ, 2))
	}

	var bestClusterAssignment, bestNewCentroids *matrix.DenseMatrix
	var bestCentroidToSplit int

	// Find the best centroid configuration.
	for len(centroidlist) < k {
		lowestSSE := math.Inf(1)
		// Split cluster
		for i, _ := range centroidlist {
			// Get the points in this cluster
			pointsCurCluster, err := clusterAssignment.FiltCol(float64(i), float64(i), 0)
			if err != nil {
				return matCentroidlist, clusterAssignment, err
			}

			centroids, splitClusterAssignment, err := Kmeansp(pointsCurCluster, 2, cc, measurer)
			if err != nil {
				return matCentroidlist, clusterAssignment, err
			}

			/* centroids is a 2X2 matrix of the best centroids found by kmeans

			   splitClustAssignment is a mX2 matrix where col0 is either 0 or 1 and refers to the rows in centroids
			   where col1 cotains the squared error between a centroid and a point.  The rows here correspond to
			   the rows in ptsInCurrCluster.  For example, if row 2 contains [1, 7.999] this means that centroid 1
			   has been paired with the point in row 2 of splitClustAssignment and that the squared error (distance
			   between centroid and point) is 7.999.
			*/

			// Calculate the sum of squared errors for each centroid.
			// This give a statistcal measurement of how good
			// the clustering is for this cluster.
			sseSplit := splitClusterAssignment.SumCol(1)
			// Calculate the SSE for the original cluster
			sqerr, err := clusterAssignment.FiltCol(float64(0), math.Inf(1), 0)
			if err != nil {
				return matCentroidlist, clusterAssignment, err
			}
			sseNotSplit := sqerr.SumCol(1)

			// TODO: Pre-BCI is this the best way to evaluate?
			if sseSplit+sseNotSplit < lowestSSE {
				bestCentroidToSplit = 1
				bestNewCentroids = matrix.MakeDenseCopy(centroids)
				bestClusterAssignment = matrix.MakeDenseCopy(splitClusterAssignment)
			}
		}

		// Applying the split overwrites the existing cluster assginments for the
		// cluster you have decided to split.  Kmeansp() returned two clusters
		// labeled 0 and 1. Change these cluster numbers to the cluster number
		// you are splitting and the next cluster to be added.
		m, err := bestClusterAssignment.FiltColMap(1, 1, 0)
		if err != nil {
			return matCentroidlist, clusterAssignment, err
		}
		for i, _ := range m {
			bestClusterAssignment.Set(i, 0, float64(len(centroidlist)))
		}

		n, err := bestClusterAssignment.FiltColMap(0, 0, 0)
		if err != nil {
			return matCentroidlist, clusterAssignment, err
		}
		for i, _ := range n {
			bestClusterAssignment.Set(i, 1, float64(bestCentroidToSplit))
		}

		fmt.Printf("Best centroid to split %f\n", bestCentroidToSplit)
		r, _ := bestClusterAssignment.GetSize()
		fmt.Printf("The length of best cluster assesment is %f\n", r)

		// Replace a centroid with the two best centroids from the split.
//.........这里部分代码省略.........