fit28.rb

require 'statsample'



def fit(l, y, lx)

	a = {}

	(lx + [y]).each { |x| a[x] = l.map { |b| b[x] }.to_vector() }

	ds = a.to_dataset()

	r = Statsample::Regression.multiple(ds, y)
#	$stderr.puts(r.summary)

	return r.coeffs.merge({'c' => r.constant})

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
	
end

def read(fn)
	
	l = File.open('data.txt').readlines
	l1 = l.shift.split
	return l.map \
	{
		|x|
		Hash[[l1, x.split.map { |y| y.to_f }].transpose]
	}
	
end



def f2(n)

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

end

def adv(x)

	n1 = n = x['n']
	l = [n]
	while (n >= n1 && n != 1)
		
		n = f2(n)
		l << n
	end
	

	x['l'] = l
	x['ls'] = l.size
	
	x['ns'] = x['n'].to_s(2).length
	x['h'] = x['ls'].to_f / x['ns']
	x['h2'] = (x['h'] * 50).to_i
	
	return x
	
end

def stat2(l, t)
	return Hash[[['a', 'sd', 'mx' , 'mn'], 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)
	
	l1 = ns.split(/1+/)
	l1.shift
	asdm0 = stat2(l1.map { |x| x.length }, nl)
	
	return {'nl' => nl, 'h2' => x['h2'], 'd' => d(ns), 'dh' => d(nsh), 'dl' => d(nsl)}.merge(asdm1)
end


def predict1(x, z)
	x.merge!(data(x))
	return x if (z.nil?)
	
	t = z['c']
	
	(z.keys - ['c']).each { |k| t += z[k] * x[k] }
	x['h2_p'] = t
	x['ls_p'] = t / $g * x['nl']
	
	
	x['h2_e'] = x['h2_p'] - x['h2']
	x['ls_e'] = x['ls_p'] - x['ls']
	
	puts([x['h2_e'], x['ls_e'], x['nl'], x['ls'], x['ls_p']].join("\t")) if (rand(40) == 0)
	$stdout.flush
	
	return x
end

def next2(z, v)
	
	l = [z]
	p = z['p'] + 1
	
	l << predict1(adv({'n'=>z['n'] + 2**p, 'p'=>p}), v)
	
	l << z.merge({'p'=>p})
	return l
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, l.min.to_f
end

def opt(c)
	
	l1 = []
	l2 = []
	l3 = []
	
	v = nil
	l1 << next2({'n'=>1, 'p'=>0}, v)

	puts('# ' + Time.now.to_s)
	t = Time.now.to_i

	c.times \
	{
		|i|
		$stderr.puts([i, sprintf('%.1fm', (Time.now.to_i - t) / 60.0), Time.now.to_s].join("\t")) if (i % 100 == 0)
		
		by = {0 => 'ls_e', 1 => 'ls'}[i % 2]
		
		if (i % 2 == 0) then
			l1 = l1.sort_by { |x| x[1]['ls'] }.reverse
			z = l1.delete_at(rand([l1.size, 200].min))
			l1.pop if (l1.size > 2000)
		else
			z = l2.delete_at(rand(l2.size))
			l2.pop if (l2.size > 10000)
		end
		
		l3 << z
		
		l1 << next2(z[1], v)
		l2 << next2(z[2], v)
		
		l3.shift if (l3.size > 400)
		v = fit(l3.map { |x| x[1] }, 'h2', ['a', 'sd', 'mn', 'mx', 'd', 'dh', 'dl']) if ((i + 1) % 400 == 0)
	}

end



	
$g = 50

l = opt(100000)