distd.rb

def f2(n)

	n = (n * 3 + 1) / 2 while (n.odd?)
	n /= 2 while (n.even?)
	return n

end

def adv(x)

	x['n'] = x['nb'].to_i(2)
	n1 = n = x['n']
	l = [n]
	while (n != 1)
		
		n = f2(n)
		l << n
	end
	

	x['l'] = l
	x['ls'] = l.size
	
	x['ns'] = x['n'].to_s(2).length
	x['m'] = (0...l.size).max_by { |x| l[x] }

#	x['y'] = (l.max.to_s(2).length.to_f / x['ns'] * 100).to_i
	x['y'] = l.max.to_s(2).length
	
	$h[x['y']] = [] if (!$h.member?(x['y']))
	$h[x['y']] << x
	
#	out1(data(x), ['a', 'sd', 'd', 'dl', 'dh', 'mn', 'y']) if (rand(100) == 0)
	return x
	
end

def out1(a, l)
	if ($f.nil?) then
		$f = File.open('data.txt', 'w')
		$f.puts(l.join("\t"))
	end
	$f.puts(a.values_at(*l).join("\t"))
	$f.flush
	
end

def stat(l)
	l = [0] if (l.empty?)
        t = t2 = 0
        l.each \
        {
		|x|
		t += x
		t2 += x ** 2
        }
        c = l.size
        a = t.to_f / c
        z = t2.to_f / c - a ** 2
        sd = Math.sqrt(z < 0 ? 0 : z)

	return a, sd, l.max.to_f
end

def stat2(l, t, n)
	return Hash[[["a#{n}", "sd#{n}", "mx#{n}"], stat(l).map { |x| x / t }].transpose]
end

def d(s)
        c = s.split('').select { |x| x == '1' }.size
	d = c.to_f / s.length
        return d
        
end

def data(x)
	
	n = x['n']
	ns = n.to_s(2)
	nl = ns.length
	m = nl / 2
	
	nsh = ns[0..m]
	nsl = ns[m..-1]
	
	asdm1 = stat2(ns.split(/0+/).map { |x| x.length }, nl, 1)
	
	l1 = ns.split(/1+/)
	l1.shift
	asdm0 = stat2(l1.map { |x| x.length }, nl, 0)
	
	return {'y' => x['y'], 'd' => d(ns), 'dh' => d(nsh), 'dl' => d(nsl)}.merge(asdm0).merge(asdm1)
end

def out(fn, l)
	
	f = File.open("#{fn}.txt", 'w')
	f.puts(l[0].keys.join("\t"))
	l.each { |x| f.puts(x.values.join("\t")) }
	f.close
	$stdout.puts("#{l.size} pts")
end

def init(w, f)
	s = (0...w).map { rand(2).to_s }.join
	s[0, 1] = '1' if (f)
	return s
end

w = ARGV[0].nil? ? 50 : ARGV[0].to_i
$stdout.puts("#{w} width")

l = []
f = false

$h = {}
$c = 10

20.times { l << adv({'nb' => init(w, f)}) }
c = 50000

seen = {}

i = n = 0
while (n < c)

	i += 1
	l.sort_by! { |x| -x['y'] }

	t = l.size / 10
	case i % 3
		when 0
			x = l[rand(t)]
			s = x['nb']
			r = f ? (rand(s.length - 1) + 1) : rand(s.length)
			s[r, 1] = (s[r, 1].to_i  ^ 1).to_s
			
		when 1
			x = l[rand(t)]
			y = l[rand(t)]
			sx = x['nb']
			sy = y['nb']
			s = ''
			w.times \
			{
				|j|
				s[j, 1] = (rand(2) == 0) ? sx[j, 1] : sy[j, 1]
			}
			
		when 2
			x = l[rand(t)]
			y = l[rand(t)]
			sx = x['nb']
			sy = y['nb']
			s = ''
			r = rand(w + 1)
			w.times \
			{
				|j|
				s[j, 1] = (j < r) ? sx[j, 1] : sy[j, 1]
			}
	end
	
	next if (seen.member?(s))
	seen[s] = nil
	
	l.pop if (l.size > 500)
	l << adv({'nb' => s})
	n += 1
end

$stderr.puts("#{i - n} dups")

l = []

$h.sort.each \
{
	|k, v|
	p([k, v.size])
}

$h.sort.select { |k, v| v.size >= $c }.each \
{ 
	|k, v|
	$c.times { l << data(v.delete_at(rand(v.size))) }
}

out('data', l)