The Q6600
Benchmarks Game

k-nucleotide Python 3 #8 program

source code

# The Computer Language Benchmarks Game
# https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
#
# submitted by Ian Osgood
# modified by Sokolov Yura
# modified by bearophile
# modified by xfm for parallelization
# modified by Justin Peel 

from sys import stdin
from collections import defaultdict
from multiprocessing import Pool

def gen_freq(frame) :
    global sequence
    frequences = defaultdict(int)
    if frame != 1:
        for ii in range(len(sequence)-frame+1) :
            frequences[sequence[ii:ii+frame]] += 1
    else:
        for nucleo in sequence:
            frequences[nucleo] += 1
    return frequences


def sort_seq(length):
    frequences = gen_freq(length)
    n= sum(frequences.values())

    l = sorted(list(frequences.items()), reverse=True, key=lambda seq_freq: (seq_freq[1],seq_freq[0]))

    return '\n'.join("%s %.3f" % (st, 100.0*fr/n) for st,fr in l)


def find_seq(s):
    t = gen_freq(len(s))
    return (s,t.get(s,0))

def prepare(f=stdin) :
    for line in f:
        if line[0] in ">;":
            if line[1:3] == "TH":
                break

    seq = []
    app = seq.append
    for line in f:
        if line[0] in ">;":
            break
        app( line )
    return "".join(seq).upper().replace('\n','')

def init(arg):
    global sequence
    sequence = arg

def main():
    global sequence
    sequence = prepare()
    p=Pool()

    
    res2 = p.map_async(find_seq,reversed("GGT GGTA GGTATT GGTATTTTAATT GGTATTTTAATTTATAGT".split()))
    res1 = p.map_async(sort_seq,(1,2))
    
    for s in res1.get() : print (s+'\n')
    res2 = reversed([r for r in res2.get()])
    print ("\n".join("{1:d}\t{0}".format(*s) for s in res2))

if __name__=='__main__' :
    main()
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
Python 3.8.0


Mon, 11 May 2020 01:48:09 GMT

MAKE:
mv knucleotide.python3-8.python3 knucleotide.python3-8.py
mypy .
There are no .py[i] files in directory '.'
make: [/home/dunham/8000-benchmarksgame/nanobench/makefiles/u64q.programs.Makefile:352: knucleotide.python3-8.python3_run] Error 2 (ignored)

3.50s to complete and log all make actions

COMMAND LINE:
/opt/src/Python-3.8.0/bin/python3 -OO knucleotide.python3-8.py 0 < knucleotide-input25000000.txt

PROGRAM OUTPUT:
A 30.295
T 30.151
C 19.800
G 19.754

AA 9.177
TA 9.132
AT 9.131
TT 9.091
CA 6.002
AC 6.001
AG 5.987
GA 5.984
CT 5.971
TC 5.971
GT 5.957
TG 5.956
CC 3.917
GC 3.911
CG 3.909
GG 3.902

1471758	GGT
446535	GGTA
47336	GGTATT
893	GGTATTTTAATT
893	GGTATTTTAATTTATAGT