README.md

usage

cat example-data.txt | go run hist.go -c 1 -g 2 -b 30

example-data.txt

0.53	a
-1.47	a
0.02	a
-0.01	a
-1.20	a
1.10	a
0.34	a
-1.27	a
-0.82	a
1.48	a
0.55	a
0.62	a
0.88	a
0.67	a
-0.99	a
-0.54	a
0.75	a
1.07	a
-0.11	a
0.67	a
0.88	a
0.42	a
-0.09	a
1.96	a
-0.22	a
-0.82	a
0.25	a
-0.84	a
0.70	a
-1.01	a
0.37	a
0.84	a
-0.19	a
1.09	a
0.94	a
-0.80	a
1.05	a
0.52	a
0.10	a
-0.35	a
1.81	a
-0.54	a
-0.69	a
1.01	a
0.46	a
-0.48	a
-1.36	a
2.43	a
-0.01	a
0.38	a
-0.77	a
0.17	a
-1.09	a
-0.47	a
-2.40	a
-1.30	a
1.38	a
0.80	a
0.91	a
0.18	a
1.93	a
0.67	a
-0.51	a
0.27	a
-2.40	a
-1.86	a
-0.37	a
-0.74	a
0.12	a
0.53	a
-1.63	a
0.13	a
-0.17	a
2.76	a
-0.74	a
0.92	a
1.68	a
0.96	a
0.01	a
0.45	a
0.41	a
-0.46	a
-0.39	a
-0.93	a
2.07	a
0.77	a
1.81	a
-0.26	a
0.29	a
0.45	a
0.82	a
-0.61	a
0.19	a
1.27	a
-2.13	a
-0.83	a
0.69	a
-1.03	a
-1.79	a
-0.75	a
-0.87	a
1.46	a
-0.27	a
-0.79	a
-0.16	a
0.53	a
-0.25	a
0.30	a
-0.30	a
1.38	a
0.36	a
-1.55	a
0.81	a
-1.68	a
-0.69	a
0.66	a
-0.65	a
-1.13	a
-0.79	a
0.80	a
-0.26	a
-0.34	a
0.16	a
-0.18	a
-1.42	a
0.38	a
0.14	a
-0.29	a
-0.67	a
0.13	a
1.15	a
-1.13	a
-1.54	a
0.42	a
-0.44	a
0.10	a
-0.20	a
-1.54	a
0.92	a
0.28	a
-1.14	a
1.07	a
-0.82	a
-1.25	a
0.49	a
-0.22	a
-0.55	a
0.39	a
0.32	a
0.05	a
1.41	a
0.04	a
0.81	a
-0.55	a
-1.79	a
0.77	a
0.18	a
-0.50	a
-0.49	a
1.25	a
-0.09	a
1.13	a
2.05	a
-1.35	a
0.06	a
-0.86	a
-2.27	a
1.74	a
1.39	a
-0.16	a
1.55	a
1.22	a
-0.20	a
-1.00	a
2.06	a
1.52	a
0.18	a
0.24	a
-0.70	a
1.86	a
-0.67	a
2.12	a
-0.51	a
-0.85	a
0.64	a
-0.72	a
-1.13	a
1.20	a
-1.74	a
0.93	a
-0.33	a
1.36	a
-1.29	a
0.04	a
1.59	a
0.89	a
-0.87	a
-0.82	a
-0.98	a
1.42	a
-0.05	b
0.19	b
0.18	b
0.78	b
-1.14	b
-0.45	b
-0.74	b
-0.95	b
-0.72	b
2.22	b
-0.58	b
-2.37	b
-0.86	b
1.55	b
-0.12	b
1.10	b
-1.69	b
1.65	b
0.53	b
0.81	b
0.57	b
-0.98	b
0.88	b
2.62	b
0.56	b
-1.15	b
-0.43	b
0.48	b
1.59	b
-0.96	b
0.13	b
0.50	b
-1.89	b
-0.24	b
0.08	b
0.58	b
-0.67	b
-0.70	b
-1.59	b
0.22	b
-0.05	b
1.62	b
-1.05	b
2.11	b
-1.10	b
0.10	b
-0.81	b
-0.72	b
0.43	b
0.00	b
1.69	b
-0.69	b
0.05	b
-0.51	b
0.78	b
1.47	b
0.20	b
1.83	b
-0.23	b
-0.27	b
0.43	b
-0.47	b
0.83	b
0.41	b
1.60	b
-0.56	b
0.23	b
0.73	b
-1.08	b
0.44	b
1.22	b
1.91	b
1.01	b
1.49	b
-2.05	b
0.78	b
1.09	b
1.61	b
-0.29	b
-0.75	b
-0.58	b
-0.60	b
2.18	b
1.47	b
0.01	b
0.92	b
0.90	b
-0.55	b
-0.89	b
-0.68	b
0.23	b
-0.90	b
0.79	b
-1.28	b
0.02	b
-1.48	b
-0.05	b
-1.16	b
-0.89	b
2.11	b
-1.59	b
-1.09	b
-1.55	b
-0.17	b
0.21	b
-0.01	b
0.53	b
-0.30	b
0.96	b
0.56	b
0.59	b
0.16	b
-0.83	b
1.86	b
0.98	b
-0.29	b
2.47	b
1.12	b
3.14	b
0.06	b
-0.79	b
-0.28	b
0.21	b
-1.04	b
2.16	b
-0.50	b
1.48	b
-0.13	b
-0.69	b
-0.46	b
0.09	b
0.42	b
-0.97	b
-0.61	b
-0.91	b
0.70	b
-0.52	b
2.02	b
-1.24	b
0.69	b
0.60	b
0.33	b
-0.14	b
-0.48	b
1.70	b
-0.87	b
0.82	b
0.16	b
-0.20	b
0.60	b
0.72	b
-0.05	b
-0.39	b
-0.39	b
0.26	b
-0.71	b
1.07	b
-0.47	b
1.68	b
1.12	b
1.24	b
1.11	b
-0.85	b
0.36	b
0.71	b
0.03	b
-0.28	b
-1.59	b
-0.82	b
0.05	b
-0.60	b
-0.27	b
-0.51	b
1.67	b
-0.26	b
-1.17	b
0.15	b
1.17	b
-0.10	b
-0.92	b
1.01	b
-0.35	b
-2.56	b
0.51	b
-0.14	b
-0.21	b
1.06	b
-0.08	b
-0.87	b
0.90	b
-0.41	b
-1.65	b
0.81	b
-0.21	b
0.21	b
0.13	b
0.24	b
0.75	b
-1.89	b
0.30	b
0.98	c
0.40	c
0.56	c
0.43	c
0.01	c
0.59	c
0.28	c
0.13	c
0.31	c
0.20	c
0.18	c
0.29	c
0.46	c
0.09	c
0.26	c
0.08	c
1.00	c
0.81	c
0.78	c
0.09	c
0.87	c
0.87	c
0.50	c
0.65	c
0.24	c
0.59	c
0.55	c
0.92	c
0.38	c
0.08	c
0.14	c
0.62	c
0.14	c
0.01	c
0.55	c
0.70	c
0.88	c
0.02	c
0.70	c
0.41	c
0.38	c
0.71	c
0.56	c
0.38	c
0.57	c
0.03	c
0.44	c
0.25	c
0.68	c
0.84	c
0.37	c
0.66	c
0.66	c
0.29	c
0.59	c
0.81	c
0.98	c
0.52	c
0.30	c
0.54	c
0.04	c
0.55	c
0.94	c
0.07	c
1.00	c
0.27	c
0.34	c
0.19	c
0.22	c
0.52	c
0.81	c
0.01	c
0.73	c
0.74	c
0.16	c
0.66	c
0.05	c
0.95	c
0.54	c
0.21	c
0.99	c
0.11	c
0.44	c
0.49	c
0.26	c
0.25	c
0.00	c
0.04	c
0.05	c
0.68	c
0.40	c
0.12	c
0.85	c
0.50	c
0.47	c
0.33	c
0.95	c
0.50	c
0.08	c
0.99	c
0.51	c
0.14	c
0.39	c
0.13	c
1.00	c
0.75	c
0.79	c
0.57	c
0.72	c
0.50	c
0.55	c
0.37	c
0.45	c
0.64	c
0.91	c
0.92	c
0.91	c
0.63	c
0.49	c
0.74	c
0.50	c
0.50	c
0.50	c
0.01	c
0.09	c
0.10	c
0.21	c
0.38	c
0.22	c
0.72	c
0.87	c
0.48	c
0.43	c
0.90	c
0.29	c
0.95	c
0.53	c
0.27	c
0.89	c
0.22	c
0.11	c
0.55	c
0.31	c
0.17	c
0.86	c
0.12	c
0.37	c
0.87	c
0.40	c
0.46	c
0.10	c
0.92	c
0.72	c
0.83	c
0.48	c
0.68	c
0.27	c
0.78	c
0.45	c
0.24	c
0.74	c
0.29	c
0.86	c
0.83	c
0.79	c
0.02	c
0.97	c
0.85	c
0.03	c
0.24	c
0.52	c
0.10	c
0.25	c
0.04	c
0.01	c
0.87	c
0.04	c
0.77	c
0.21	c
0.48	c
0.73	c
0.20	c
0.06	c
0.27	c
0.01	c
0.06	c
0.17	c
0.88	c
0.92	c
0.53	c
0.90	c
0.02	c
0.88	c
0.68	c
0.52	c
0.88	c
0.80	c
0.72	c
0.59	c
0.49	c

hist.go

package main

import (
	"bufio"
	"fmt"
	"log"
	"os"
	"regexp"
	"sort"
	"strconv"

	arg "github.com/alexflint/go-arg"
	"github.com/gonum/plot"
	"github.com/gonum/plot/plotter"
	"github.com/gonum/plot/plotutil"
	"github.com/gonum/plot/vg"
)

type dargs struct {
	Col   int    `arg:"-c,required,help:1-based column number to use for histogram"`
	Group int    `arg:"-g,help:optional 1-based column number to use grouping"`
	Sep   string `arg:"-s,help:optional sep for columns default is '\t'"`
	Bins  int    `arg:"-b,help:optional number of bins."`
	Path  string `arg:"-p,help:optional path to save plot."`
}

func pcheck(e error) {
	if e != nil {
		panic(e)
	}
}

func MustAtof(s string) float64 {
	v, err := strconv.ParseFloat(s, 64)
	pcheck(err)
	return v
}

// Main is run from the dispatcher
func main() {

	args := dargs{Sep: "\t", Bins: 20, Path: "hist.png"}
	arg.MustParse(&args)
	args.Group--
	args.Col--
	run(args)
}

func read(args dargs) map[string][]float64 {
	sep := regexp.MustCompile(args.Sep)
	scanner := bufio.NewScanner(os.Stdin)
	scanner.Buffer(make([]byte, 0, 16384), 5e9)

	grouped := make(map[string][]float64)

	nErr := 0
	for scanner.Scan() {
		line := scanner.Text()
		toks := sep.Split(line, -1)
		v, err := strconv.ParseFloat(toks[args.Col], 64)
		if err != nil {
			if nErr < 5 {
				log.Println(err)
			}
			nErr++
			continue
		}
		var g string
		if args.Group > -1 {
			g = toks[args.Group]
		} else {
			g = "default"
		}
		if _, ok := grouped[g]; !ok {
			grouped[g] = make([]float64, 0, 256)
		}
		grouped[g] = append(grouped[g], v)

	}
	if err := scanner.Err(); err != nil {
		fmt.Fprintln(os.Stderr, "reading standard input:", err)
	}
	return grouped
}

func mapkeys(m map[string][]float64) []string {
	var ks []string
	for k := range m {
		ks = append(ks, k)
	}
	sort.Strings(ks)
	return ks
}

func run(args dargs) {
	grouped := read(args)
	keys := mapkeys(grouped)

	p, err := plot.New()
	if err != nil {
		panic(err)
	}
	p.Y.Label.Text = "Count"

	w := float64(30/len(grouped)) * float64(20) / float64(args.Bins)
	var bars []plot.Plotter

	for i, k := range keys {
		tmp, err := plotter.NewHist(plotter.Values(grouped[k]), args.Bins)
		pcheck(err)
		vals := make([]float64, len(tmp.Bins))
		for i, b := range tmp.Bins {
			vals[i] = b.Weight
		}

		bar, err := plotter.NewBarChart(plotter.Values(vals), vg.Points(w+0.01))
		pcheck(err)

		bar.LineStyle.Width = vg.Length(0.1)
		bar.Color = plotutil.Color(i)

		bar.Offset = vg.Points(float64(i) * w)
		p.Legend.Add(k, bar)
		//p.Add(bar)
		bars = append(bars, bar)
	}
	p.Add(bars...)
	log.Println(p.X.Min, p.X.Max)

	p.Legend.Top = true
	if err := p.Save(10*vg.Inch, 3*vg.Inch, args.Path); err != nil {
		panic(err)
	}
}