Ejemplo n.º 1
0
Archivo: web.go Proyecto: NioTeX/neat
func updateComplexity(v *Web, pop neat.Population) {
	// Build complexity slice
	x := make([]float64, len(pop.Genomes))
	for i, g := range pop.Genomes {
		x[i] = float64(g.Complexity())
	}

	var b neat.Genome
	max := -1.0
	for _, g := range pop.Genomes {
		if g.Fitness > max {
			b = g
			max = g.Fitness
		}
	}

	// Append the record
	min, _ := stats.Min(x)
	max, _ = stats.Max(x)
	mean, _ := stats.Mean(x)

	v.complexity = append(v.complexity, [4]float64{
		min,
		mean,
		max,
		float64(b.Complexity()),
	})
}
Ejemplo n.º 2
0
// startStats blocks and periodically logs transaction statistics (throughput,
// success rates, durations, ...).
// TODO(tschottdorf): Use a proper metrics subsystem for this (+the store-level
// stats).
// TODO(mrtracy): Add this to TimeSeries.
func (tc *TxnCoordSender) startStats() {
	res := time.Millisecond // for duration logging resolution
	lastNow := tc.clock.PhysicalNow()
	for {
		select {
		case <-time.After(statusLogInterval):
			if !log.V(1) {
				continue
			}

			tc.Lock()
			curStats := tc.txnStats
			tc.txnStats = txnCoordStats{}
			tc.Unlock()

			now := tc.clock.PhysicalNow()

			// Tests have weird clocks.
			if now-lastNow <= 0 {
				continue
			}

			num := len(curStats.durations)
			dMax := time.Duration(stats.Max(curStats.durations))
			dMean := time.Duration(stats.Mean(curStats.durations))
			dDev := time.Duration(stats.StdDevP(curStats.durations))
			rMax := stats.Max(curStats.restarts)
			rMean := stats.Mean(curStats.restarts)
			rDev := stats.StdDevP(curStats.restarts)

			rate := float64(int64(num)*int64(time.Second)) / float64(now-lastNow)
			var pCommitted, pAbandoned, pAborted float32
			if num > 0 {
				pCommitted = 100 * float32(curStats.committed) / float32(num)
				pAbandoned = 100 * float32(curStats.abandoned) / float32(num)
				pAborted = 100 * float32(curStats.aborted) / float32(num)
			}
			log.Infof("txn coordinator: %.2f txn/sec, %.2f/%.2f/%.2f %%cmmt/abrt/abnd, %s/%s/%s avg/σ/max duration, %.1f/%.1f/%.1f avg/σ/max restarts (%d samples)",
				rate, pCommitted, pAborted, pAbandoned, util.TruncateDuration(dMean, res),
				util.TruncateDuration(dDev, res), util.TruncateDuration(dMax, res),
				rMean, rDev, rMax, num)
			lastNow = now
		case <-tc.stopper.ShouldStop():
			return
		}
	}
}
Ejemplo n.º 3
0
// Finalize calculation of the risk using available datapoints
func riskFinalize(op opContext, rs *slib.RRAServiceRisk) error {
	var (
		rvals []float64
		err   error
	)
	for _, x := range rs.Scenarios {
		// If the scenario had no data, don't include it in the
		// final scoring
		if x.NoData {
			continue
		}
		rvals = append(rvals, x.Score)
	}

	// Note the highest business impact value that was determined from
	// the RRA. This can be used as an indication of the business impact
	// for the service.
	rs.Risk.Impact = rs.UsedRRAAttrib.Impact
	rs.Risk.ImpactLabel, err = slib.ImpactLabelFromValue(rs.Risk.Impact)
	if err != nil {
		return err
	}

	if len(rvals) == 0 {
		// This can occur if we have no metric data, including no valid
		// information in the RRA
		logf("error in risk calculation: %q has no valid scenarios", rs.RRA.Name)
		rs.Risk.Median = 0.0
		rs.Risk.Average = 0.0
		rs.Risk.WorstCase = 0.0
		rs.Risk.MedianLabel = "unknown"
		rs.Risk.AverageLabel = "unknown"
		rs.Risk.WorstCaseLabel = "unknown"
		rs.Risk.DataClass, err = slib.DataValueFromLabel(rs.RRA.DefData)
		return nil
	}
	rs.Risk.Median, err = stats.Median(rvals)
	if err != nil {
		return err
	}
	rs.Risk.MedianLabel = slib.NormalLabelFromValue(rs.Risk.Median)
	rs.Risk.Average, err = stats.Mean(rvals)
	if err != nil {
		return err
	}
	rs.Risk.AverageLabel = slib.NormalLabelFromValue(rs.Risk.Average)
	rs.Risk.WorstCase, err = stats.Max(rvals)
	if err != nil {
		return err
	}
	rs.Risk.WorstCaseLabel = slib.NormalLabelFromValue(rs.Risk.WorstCase)

	rs.Risk.DataClass, err = slib.DataValueFromLabel(rs.RRA.DefData)
	if err != nil {
		return err
	}
	return nil
}
Ejemplo n.º 4
0
Archivo: count.go Proyecto: samuell/exp
func (hist *History) PrintSummary() {
	nanos := []float64{}
	for _, duration := range hist.values {
		nanos = append(nanos, float64(duration))
	}

	fmt.Printf("%10s", hist.name)
	fmt.Printf(" %10s", time.Duration(stats.Min(nanos)))
	for _, p := range percentiles {
		nano := time.Duration(stats.Percentile(nanos, p))
		fmt.Printf(" %10s", nano)
	}
	fmt.Printf(" %10s", time.Duration(stats.Max(nanos)))
	fmt.Println()
}
Ejemplo n.º 5
0
Archivo: web.go Proyecto: NioTeX/neat
func updateFitness(v *Web, pop neat.Population) {
	// Build fitness slice
	x := make([]float64, len(pop.Genomes))
	for i, g := range pop.Genomes {
		x[i] = g.Fitness
	}

	// Append the record
	min, _ := stats.Min(x)
	max, _ := stats.Max(x)
	mean, _ := stats.Mean(x)
	v.fitness = append(v.fitness, [3]float64{
		min,
		mean,
		max,
	})
}
Ejemplo n.º 6
0
Archivo: count.go Proyecto: samuell/exp
func FprintSummary(out io.Writer, hists ...*History) {
	fmt.Fprintf(out, "%10s", "")
	fmt.Fprintf(out, " %10s", "MIN")
	for _, p := range percentiles {
		fmt.Fprintf(out, " %9d%%", int(p))
	}
	fmt.Fprintf(out, " %10s", "MAX")
	fmt.Fprintln(out)

	for _, hist := range hists {
		nanos := []float64{}
		for _, duration := range hist.values {
			nanos = append(nanos, float64(duration))
		}

		fmt.Fprintf(out, "%10s", hist.name)
		fmt.Fprintf(out, " %10s", time.Duration(stats.Min(nanos)))
		for _, p := range percentiles {
			fmt.Fprintf(out, " %10s", time.Duration(stats.Percentile(nanos, p)))
		}
		fmt.Fprintf(out, " %10s", time.Duration(stats.Max(nanos)))
		fmt.Fprintln(out)
	}
}
Ejemplo n.º 7
0
// startStats blocks and periodically logs transaction statistics (throughput,
// success rates, durations, ...). Note that this only captures write txns,
// since read-only txns are stateless as far as TxnCoordSender is concerned.
// stats).
// TODO(mrtracy): Add this to TimeSeries.
func (tc *TxnCoordSender) startStats() {
	res := time.Millisecond // for duration logging resolution
	lastNow := tc.clock.PhysicalNow()
	for {
		select {
		case <-time.After(statusLogInterval):
			if !log.V(1) {
				continue
			}

			tc.Lock()
			curStats := tc.txnStats
			tc.txnStats = txnCoordStats{}
			tc.Unlock()

			now := tc.clock.PhysicalNow()

			// Tests have weird clocks.
			if now-lastNow <= 0 {
				continue
			}

			num := len(curStats.durations)
			// Only compute when non-empty input.
			var dMax, dMean, dDev, rMax, rMean, rDev float64
			var err error
			if num > 0 {
				// There should never be an error in the below
				// computations.
				dMax, err = stats.Max(curStats.durations)
				if err != nil {
					panic(err)
				}
				dMean, err = stats.Mean(curStats.durations)
				if err != nil {
					panic(err)
				}
				dDev, err = stats.StdDevP(curStats.durations)
				if err != nil {
					panic(err)
				}
				rMax, err = stats.Max(curStats.restarts)
				if err != nil {
					panic(err)
				}
				rMean, err = stats.Mean(curStats.restarts)
				if err != nil {
					panic(err)
				}
				rDev, err = stats.StdDevP(curStats.restarts)
				if err != nil {
					panic(err)
				}
			}

			rate := float64(int64(num)*int64(time.Second)) / float64(now-lastNow)
			var pCommitted, pAbandoned, pAborted float32

			if fNum := float32(num); fNum > 0 {
				pCommitted = 100 * float32(curStats.committed) / fNum
				pAbandoned = 100 * float32(curStats.abandoned) / fNum
				pAborted = 100 * float32(curStats.aborted) / fNum
			}
			log.Infof(
				"txn coordinator: %.2f txn/sec, %.2f/%.2f/%.2f %%cmmt/abrt/abnd, %s/%s/%s avg/σ/max duration, %.1f/%.1f/%.1f avg/σ/max restarts (%d samples)",
				rate, pCommitted, pAborted, pAbandoned,
				util.TruncateDuration(time.Duration(dMean), res),
				util.TruncateDuration(time.Duration(dDev), res),
				util.TruncateDuration(time.Duration(dMax), res),
				rMean, rDev, rMax, num,
			)
			lastNow = now
		case <-tc.stopper.ShouldStop():
			return
		}
	}
}
Ejemplo n.º 8
0
Archivo: ocr.go Proyecto: NioTeX/neat
func (e Evaluator) Evaluate(p neat.Phenome) (r neat.Result) {

	// Iterate the inputs and ask about
	letters := []uint8{'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'}
	guesses := make([][]uint8, 26)
	values := make([]float64, 26)
	sum := 0.0
	cnt := 0.0
	stop := true
	for i, input := range inputs {
		// Query the network for this letter
		outputs, err := p.Activate(input)
		if err != nil {
			return result.New(p.ID(), 0, err, false)
		}

		// Identify the max
		max, _ := stats.Max(outputs)
		values[i] = max

		// Determine success
		s2 := 0.0
		for j := 0; j < len(outputs); j++ {
			if outputs[j] == max {
				guesses[i] = append(guesses[i], letters[j])
				if j != i {
					stop = false // picked another letter
					s2 += 1.0
				} else {
					s2 += 1.0 - max
				}
			}
			cnt += 1
		}
		sum += s2
	}

	if e.show {
		b := bytes.NewBufferString("\n")
		fmt.Println()
		if e.useTrial {
			b.WriteString(fmt.Sprintf("Trial %d ", e.trialNum))
		}
		b.WriteString(fmt.Sprintf("OCR Evaluation for genome %d. Letter->Guess(confidence)\n", p.ID()))
		b.WriteString(fmt.Sprintf("------------------------------------------\n"))
		for i := 0; i < len(letters); i++ {
			b.WriteString(fmt.Sprintf("%s (%0.2f)", string(letters[i]), values[i]))
			cl := ""
			il := ""
			for j := 0; j < len(guesses[i]); j++ {
				if guesses[i][j] == letters[i] {
					cl = "   correct"
				} else {
					if il != "" {
						il += ", "
					}
					il += string(guesses[i][j])
				}
			}
			if cl == "" {
				cl = " incorrect"
			}
			b.WriteString(cl)
			if il != "" {
				b.WriteString(" but also guessed ")
				b.WriteString(il)
			}
			b.WriteString("\n")
		}
		fmt.Println(b.String())
	}

	return result.New(p.ID(), math.Pow(cnt-sum, 2), nil, stop || !time.Now().Before(e.stopTime))
}
Ejemplo n.º 9
0
func main() {

	d := stats.LoadRawData([]interface{}{1.1, "2", 3.0, 4, "5"})

	a, _ := stats.Min(d)
	fmt.Println(a) // 1.1

	a, _ = stats.Max(d)
	fmt.Println(a) // 5

	a, _ = stats.Sum([]float64{1.1, 2.2, 3.3})
	fmt.Println(a) // 6.6

	a, _ = stats.Mean([]float64{1, 2, 3, 4, 5})
	fmt.Println(a) // 3

	a, _ = stats.Median([]float64{1, 2, 3, 4, 5, 6, 7})
	fmt.Println(a) // 4

	m, _ := stats.Mode([]float64{5, 5, 3, 3, 4, 2, 1})
	fmt.Println(m) // [5 3]

	a, _ = stats.PopulationVariance([]float64{1, 2, 3, 4, 5})
	fmt.Println(a) // 2

	a, _ = stats.SampleVariance([]float64{1, 2, 3, 4, 5})
	fmt.Println(a) // 2.5

	a, _ = stats.MedianAbsoluteDeviationPopulation([]float64{1, 2, 3})
	fmt.Println(a) // 1

	a, _ = stats.StandardDeviationPopulation([]float64{1, 2, 3})
	fmt.Println(a) // 0.816496580927726

	a, _ = stats.StandardDeviationSample([]float64{1, 2, 3})
	fmt.Println(a) // 1

	a, _ = stats.Percentile([]float64{1, 2, 3, 4, 5}, 75)
	fmt.Println(a) // 4

	a, _ = stats.PercentileNearestRank([]float64{35, 20, 15, 40, 50}, 75)
	fmt.Println(a) // 40

	c := []stats.Coordinate{
		{1, 2.3},
		{2, 3.3},
		{3, 3.7},
		{4, 4.3},
		{5, 5.3},
	}

	r, _ := stats.LinearRegression(c)
	fmt.Println(r) // [{1 2.3800000000000026} {2 3.0800000000000014} {3 3.7800000000000002} {4 4.479999999999999} {5 5.179999999999998}]

	r, _ = stats.ExponentialRegression(c)
	fmt.Println(r) // [{1 2.5150181024736638} {2 3.032084111136781} {3 3.6554544271334493} {4 4.406984298281804} {5 5.313022222665875}]

	r, _ = stats.LogarithmicRegression(c)
	fmt.Println(r) // [{1 2.1520822363811702} {2 3.3305559222492214} {3 4.019918836568674} {4 4.509029608117273} {5 4.888413396683663}]

	s, _ := stats.Sample([]float64{0.1, 0.2, 0.3, 0.4}, 3, false)
	fmt.Println(s) // [0.2,0.4,0.3]

	s, _ = stats.Sample([]float64{0.1, 0.2, 0.3, 0.4}, 10, true)
	fmt.Println(s) // [0.2,0.2,0.4,0.1,0.2,0.4,0.3,0.2,0.2,0.1]

	q, _ := stats.Quartile([]float64{7, 15, 36, 39, 40, 41})
	fmt.Println(q) // {15 37.5 40}

	iqr, _ := stats.InterQuartileRange([]float64{102, 104, 105, 107, 108, 109, 110, 112, 115, 116, 118})
	fmt.Println(iqr) // 10

	mh, _ := stats.Midhinge([]float64{1, 3, 4, 4, 6, 6, 6, 6, 7, 7, 7, 8, 8, 9, 9, 10, 11, 12, 13})
	fmt.Println(mh) // 7.5

	tr, _ := stats.Trimean([]float64{1, 3, 4, 4, 6, 6, 6, 6, 7, 7, 7, 8, 8, 9, 9, 10, 11, 12, 13})
	fmt.Println(tr) // 7.25

	o, _ := stats.QuartileOutliers([]float64{-1000, 1, 3, 4, 4, 6, 6, 6, 6, 7, 8, 15, 18, 100})
	fmt.Printf("%+v\n", o) //  {Mild:[15 18] Extreme:[-1000 100]}

	gm, _ := stats.GeometricMean([]float64{10, 51.2, 8})
	fmt.Println(gm) // 15.999999999999991

	hm, _ := stats.HarmonicMean([]float64{1, 2, 3, 4, 5})
	fmt.Println(hm) // 2.18978102189781

	a, _ = stats.Round(2.18978102189781, 3)
	fmt.Println(a) // 2.189
}
Ejemplo n.º 10
0
Archivo: main.go Proyecto: samuell/exp
func main() {
	verbose := flag.Bool("v", false, "verbose output")
	flag.Parse()

	file, err := os.Open("delta_data.bin")
	check(err)
	defer file.Close()

	buffer := bufio.NewReader(file)

	sizes := make([]float64, 0)
	speeds := make([]float64, 0)

	encode := qpc.NewHistory("encode")
	decode := qpc.NewHistory("decode")

	server := physics.NewState(901)
	client := physics.NewState(901)

	// initialize the base state
	for i := 0; i < 6; i += 1 {
		server.ReadNext(buffer)
		client.IncFrame()
		client.Current().Assign(server.Current())
	}

	frame := 6
	for {
		err = server.ReadNext(buffer)
		if err == io.EOF {
			break
		}
		check(err)
		frame += 1

		runtime.GC()

		// Server side
		encode.Start()
		snapshot := server.Encode()
		encode.Stop()
		// ===

		runtime.GC()

		// Client side
		decode.Start()
		client.IncFrame()
		client.Decode(snapshot)
		decode.Stop()
		// ===

		size := float64(len(snapshot)*8) / 1000.0
		sizes = append(sizes, size)

		speed := size * 60.0
		speeds = append(speeds, speed)

		equal := server.Current().Equals(client.Current())
		if *verbose {
			if !equal {
				fmt.Print("! ")
			}
			fmt.Printf("%04d %8.3fkbps %10s %10s\n", frame, speed, encode.Last(), decode.Last())
		} else {
			if equal {
				fmt.Print(".")
			} else {
				fmt.Print("X")
			}
		}
	}

	fmt.Println()
	fmt.Printf("#%d %.3fkbps ±%.3fkbps\n", len(sizes), stats.Mean(speeds), stats.StdDevS(speeds))
	fmt.Println()

	fmt.Printf("MIN %10.3f kbps\n", stats.Min(speeds))
	for _, p := range []float64{5, 10, 25, 50, 75, 90, 95} {
		fmt.Printf("P%02.f %10.3f kbps\n", p, stats.Percentile(speeds, p))
	}
	fmt.Printf("MAX %10.3f kbps\n", stats.Max(speeds))

	fmt.Println()

	fmt.Printf("TOTAL  %10.3f kb\n", stats.Sum(sizes))
	fmt.Printf("  AVG  %10.3f kb per frame\n", stats.Mean(sizes))
	fmt.Printf("  AVG  %10.3f bits per cube\n", stats.Mean(sizes)*1000/float64(len(sizes)))

	fmt.Println()
	fmt.Println("TIMING:")
	qpc.PrintSummary(encode, decode)
}
Ejemplo n.º 11
0
func main() {
	flag.Parse()
	n := *concurrency
	m := *total / n

	fmt.Printf("concurrency: %d\nrequests per client: %d\n\n", n, m)

	args := prepareArgs()

	b, _ := proto.Marshal(args)
	fmt.Printf("message size: %d bytes\n\n", len(b))

	var wg sync.WaitGroup
	wg.Add(n * m)

	var trans uint64
	var transOK uint64

	d := make([][]int64, n, n)

	//it contains warmup time but we can ignore it
	totalT := time.Now().UnixNano()
	for i := 0; i < n; i++ {
		dt := make([]int64, 0, m)
		d = append(d, dt)

		go func(i int) {
			conn, err := grpc.Dial(*host, grpc.WithInsecure())
			if err != nil {
				log.Fatalf("did not connect: %v", err)
			}
			c := NewHelloClient(conn)

			//warmup
			for j := 0; j < 5; j++ {
				c.Say(context.Background(), args)
			}

			for j := 0; j < m; j++ {
				t := time.Now().UnixNano()
				reply, err := c.Say(context.Background(), args)
				t = time.Now().UnixNano() - t

				d[i] = append(d[i], t)

				if err == nil && *(reply.Field1) == "OK" {
					atomic.AddUint64(&transOK, 1)
				}

				atomic.AddUint64(&trans, 1)
				wg.Done()
			}

			conn.Close()

		}(i)

	}

	wg.Wait()
	totalT = time.Now().UnixNano() - totalT
	totalT = totalT / 1000000
	fmt.Printf("took %d ms for %d requests", totalT, n*m)

	totalD := make([]int64, 0, n*m)
	for _, k := range d {
		totalD = append(totalD, k...)
	}
	totalD2 := make([]float64, 0, n*m)
	for _, k := range totalD {
		totalD2 = append(totalD2, float64(k))
	}

	mean, _ := stats.Mean(totalD2)
	median, _ := stats.Median(totalD2)
	max, _ := stats.Max(totalD2)
	min, _ := stats.Min(totalD2)

	fmt.Printf("sent     requests    : %d\n", n*m)
	fmt.Printf("received requests    : %d\n", atomic.LoadUint64(&trans))
	fmt.Printf("received requests_OK : %d\n", atomic.LoadUint64(&transOK))
	fmt.Printf("throughput  (TPS)    : %d\n", int64(n*m)*1000/totalT)
	fmt.Printf("mean: %.f ns, median: %.f ns, max: %.f ns, min: %.f ns\n", mean, median, max, min)
	fmt.Printf("mean: %d ms, median: %d ms, max: %d ms, min: %d ms\n", int64(mean/1000000), int64(median/1000000), int64(max/1000000), int64(min/1000000))

}
Ejemplo n.º 12
0
func main() {
	flag.Parse()
	n := *concurrency
	m := *total / n

	fmt.Printf("concurrency: %d\nrequests per client: %d\n\n", n, m)

	serviceMethodName := "Hello.Say"
	args := prepareArgs()

	b := make([]byte, 1024*1024)
	i, _ := args.MarshalTo(b)
	fmt.Printf("message size: %d bytes\n\n", i)

	var wg sync.WaitGroup
	wg.Add(n * m)

	var trans uint64
	var transOK uint64

	d := make([][]int64, n, n)

	//it contains warmup time but we can ignore it
	totalT := time.Now().UnixNano()
	for i := 0; i < n; i++ {
		dt := make([]int64, 0, m)
		d = append(d, dt)

		go func(i int) {
			s := &rpcx.DirectClientSelector{Network: "tcp", Address: *host}
			client := rpcx.NewClient(s)
			client.ClientCodecFunc = codec.NewProtobufClientCodec

			var reply BenchmarkMessage

			//warmup
			for j := 0; j < 5; j++ {
				client.Call(serviceMethodName, args, &reply)
			}

			for j := 0; j < m; j++ {
				t := time.Now().UnixNano()
				err := client.Call(serviceMethodName, args, &reply)
				t = time.Now().UnixNano() - t

				d[i] = append(d[i], t)

				if err == nil && reply.Field1 == "OK" {
					atomic.AddUint64(&transOK, 1)
				}

				atomic.AddUint64(&trans, 1)
				wg.Done()
			}

			client.Close()

		}(i)

	}

	wg.Wait()
	totalT = time.Now().UnixNano() - totalT
	totalT = totalT / 1000000
	fmt.Printf("took %d ms for %d requests", totalT, n*m)

	totalD := make([]int64, 0, n*m)
	for _, k := range d {
		totalD = append(totalD, k...)
	}
	totalD2 := make([]float64, 0, n*m)
	for _, k := range totalD {
		totalD2 = append(totalD2, float64(k))
	}

	mean, _ := stats.Mean(totalD2)
	median, _ := stats.Median(totalD2)
	max, _ := stats.Max(totalD2)
	min, _ := stats.Min(totalD2)

	fmt.Printf("sent     requests    : %d\n", n*m)
	fmt.Printf("received requests    : %d\n", atomic.LoadUint64(&trans))
	fmt.Printf("received requests_OK : %d\n", atomic.LoadUint64(&transOK))
	fmt.Printf("throughput  (TPS)    : %d\n", int64(n*m)*1000/totalT)
	fmt.Printf("mean: %.f ns, median: %.f ns, max: %.f ns, min: %.f ns\n", mean, median, max, min)
	fmt.Printf("mean: %d ms, median: %d ms, max: %d ms, min: %d ms\n", int64(mean/1000000), int64(median/1000000), int64(max/1000000), int64(min/1000000))

}
Ejemplo n.º 13
0
func main() {
	t := time.Now()
	fmt.Println(t.Format(time.RFC3339))

	rand.Seed(1)

	// Read in data
	readData()

	// Set one level with all row criteria,
	// this is used to start the set creation
	levelOne = fullOneLevel()

	//levels = fullTwoLevel()
	outputRowCriteria(levels)

	// experiment variables
	rand_numSets = 1000
	rand_maxSetMembers = 5
	maxExperiments = 1

	var expMin []float64
	var expMax []float64
	scoreCutoff = -0.89
	rowThreshhold = 2
	zScore = 2.58
	for experiment := 1; experiment <= maxExperiments; experiment++ {
		// experiment variables, changes per experiment
		rand_numSets += 0
		rand_maxSetMembers += 0
		scoreCutoff += -0.00
		zScore += 0.0

		// Setup experiment variables
		var scores []scoreResult
		var minScore float64 = -100
		var maxScore float64 = 0
		levels = fullFourLevel() //randLevels()
		fmt.Printf("sets count: %d, max set members: %d, level 1 count: %d, rowThreshhold: %d, scoreCutoff: %f, zScore: %f\n", len(levels), rand_maxSetMembers+2, len(levelOne), rowThreshhold, scoreCutoff, zScore)

		for dataSetId := 1; dataSetId <= datasets; dataSetId++ {
			s := levelEval(dataSetId)
			sort.Sort(scoreResults(s))

			// s contains a list of scores for one dataset, sorted
			// this is were we can get some info on that data
			//outputScoreList(s)

			if len(s) > 0 {
				//var sEval = evaluateScores(s)
				// pick the top score
				var sEval = s[0]
				scores = append(scores, sEval)
				fmt.Printf("%d, %f \n", sEval.dataSetId, sEval.score)

				if minScore < sEval.score {
					minScore = sEval.score
				}
				if maxScore > sEval.score {
					maxScore = sEval.score
				}
			}

			// For all score in this set write out the median and standard deviation
			var set []float64
			for _, scoreItem := range s {
				if scoreItem.score < 0.0 {
					set = append(set, scoreItem.score)
				}
			}

			var median, _ = stats.Median(set)
			var sd, _ = stats.StandardDeviation(set)
			var min, _ = stats.Min(set)
			var max, _ = stats.Max(set)
			fmt.Printf("dataset: %d, median: %f, sd: %f, min: %f, max: %f, len: %d\n", dataSetId, median, sd, min, max, len(set))

		}

		expMin = append(expMin, minScore)
		expMax = append(expMax, maxScore)

		//scoreCutoff = (minScore * (percentRofMin / 100.0)) + minScore
		//fmt.Printf(" scoreCutoff: %f \n", scoreCutoff)

		outputScores(scores)
		// Write output file
		outputResults(scores)

		// Compare to training truth data
		// compareTrainingDataWithResults()
	}

	t = time.Now()
	fmt.Println(t.Format(time.RFC3339))

	// Output min max scores per experiment
	for _, each := range expMin {
		fmt.Printf("min: %f, ", each)
	}
	fmt.Println()
	for _, each := range expMax {
		fmt.Printf("max: %f, ", each)
	}
}
Ejemplo n.º 14
0
// Updates the statistics of the population and determines if a phase switch is required.
func (m *Phased) SetPopulation(p neat.Population) error {

	// Calculate the tnew MPC and fitness
	var n float64
	fit := make([]float64, len(p.Genomes))
	for i, g := range p.Genomes {
		n += float64(g.Complexity())
		fit[i] = g.Improvement
	}
	mpc := n / float64(len(p.Genomes))
	//neat.DBG("mpc %f fit %f", mpc, fit)
	if mpc < m.minMPC { // Looking for a drop in MPC
		m.ageMPC = 0
		m.minMPC = mpc
	} else {
		m.ageMPC += 1
	}

	var f float64
	if m.ImprovementType() == neat.Absolute {
		f, _ = stats.Max(fit)
	} else {
		f, _ = stats.VarP(fit)
	}

	// Looking for a continued increase in fitness (Absolute) or an uptick in variance (RelativeImprovement)
	if f > m.lastImprovement {
		m.ageImprovement = 0
		m.lastImprovement = f
	} else {
		m.ageImprovement += 1
	}

	// First run, just set the initial threshold and return
	if m.targetMPC == 0 {
		m.isPruning = false
		m.targetMPC = mpc + m.PruningPhaseThreshold()
		return nil
	}

	// Check for a phase change
	if m.isPruning {
		if m.ageMPC > m.MaxMPCAge() {
			m.isPruning = false
			m.targetMPC = mpc + m.PruningPhaseThreshold()
			m.ageImprovement = 0
			m.lastImprovement = 0
		}
	} else {
		if mpc >= m.targetMPC && m.ageImprovement > m.MaxImprovementAge() {
			m.isPruning = true
			m.ageMPC = 0
			m.minMPC = mpc
		}
	}

	// Toggle crossover as necessary
	if crs, ok := m.ctx.(neat.Crossoverable); ok {
		crs.SetCrossover(!m.isPruning)
	}
	return nil
}
Ejemplo n.º 15
0
//apply transforms an array of data
func apply(data []string, transformation templates.Transformation) ([]string, []Mapping) {
	p := transformation.Parameters
	var wg sync.WaitGroup
	var mapping []Mapping

	switch transformation.Operation {
	case "toDate":
		if len(p) != 2 {
			log.Fatal("toDate transformation requires 2 parameters:  current format, new format")
		}

		oldFormat := p[0]
		newFormat := p[1]

		for i, x := range data {
			y, err := time.Parse(oldFormat, x)
			if err != nil {
				log.Print("Error parsing date with index ", i, " with format: ", oldFormat)
			} else {
				data[i] = y.Format(newFormat)
			}
		}
	case "setNull":
		for i, x := range data {
			if arrayPos(x, p) != -1 {
				data[i] = ""
			}
		}
	case "standardize":
		if len(p) != 1 {
			log.Fatal("standardize transformation requires 1 parameter:  type (min-max|z-score)")
		}

		stype := p[0]
		switch stype {
		case "min-max":
			newData := strArrToFloatArr(data)
			min, err := stats.Min(newData)
			if err != nil {
				log.Fatal("Error finding minimum of data: ", err)
			}
			max, err := stats.Max(newData)
			if err != nil {
				log.Fatal("Error finding maximum of data: ", err)
			}
			srange := max - min

			for i, x := range newData {
				data[i] = floatToString((x - min) / srange)
			}
		case "z-score":
			newData := strArrToFloatArr(data)
			mean, err := stats.Mean(newData)
			if err != nil {
				log.Fatal("Error finding mean of data: ", err)
			}
			sd, err := stats.StandardDeviation(newData)
			if err != nil {
				log.Fatal("Error finding standard deviation of data: ", err)
			}

			for i, x := range newData {
				data[i] = floatToString((x - mean) / sd)
			}
		case "decimal":
			newData := strArrToFloatArr(data)
			max, err := stats.Max(newData)
			if err != nil {
				log.Fatal("Error finding maximum of data: ", err)
			}
			min, err := stats.Min(newData)
			if err != nil {
				log.Fatal("Error finding minimum of data: ", err)
			}

			var maxAbs float64
			if math.Abs(max) > math.Abs(min) {
				maxAbs = math.Abs(max)
			} else {
				maxAbs = math.Abs(min)
			}
			c := math.Ceil(math.Log10(maxAbs))
			for i, x := range newData {
				data[i] = floatToString(x / math.Pow10(int(c)))
			}
		}
	case "binPercent":
		table := NewPivotTable(data)
		intP := strArrToIntArr(p)
		sort.Ints(intP)
		ps := NewPercentileService(*table, intP)
		mapping = ps.CreateMappings()
		ps.Bin(mapping, data)
	case "fuzzyMap":
		if len(p) != 3 {
			log.Fatal("fuzzyMap transformation requires 3 parameters:  datasource GUID, match, put")
		}

		dsGUID := p[0]
		ds := datasources.NewDatasourceService(database.GetDatabase())
		dsObj, err := ds.GetDatasource(dsGUID)
		if err != nil {
			log.Fatal("Error finding Datasource: ", err)
		}
		distinctValues := getDistinctValues(data)
		for i, datum := range distinctValues {
			wg.Add(1)
			go func(i int, datum string, dsObj datasources.Datasource) {
				result := fuzzyMap(datum, dsObj.Settings)
				fuzzyMapping := NewMapping(datum, result)
				mapping = append(mapping, *fuzzyMapping)
				defer wg.Done()
			}(i, datum, dsObj)
		}
		wg.Wait()
		data = applyMappings(mapping, data)
	}

	return data, mapping
}