Each table row shows performance measurements for this PyPy 3 program with a particular command-line input value N.
N | CPU secs | Elapsed secs | Memory KB | Code B | ≈ CPU Load |
---|---|---|---|---|---|
10,000 | 0.38 | 0.34 | 2,348 | 801 | 11% 3% 0% 97% 6% 6% 3% 9% |
Read the ↓ make, command line, and program output logs to see how this program was run.
Read k-nucleotide benchmark to see what this program should do.
# The Computer Language Benchmarks Game # http://benchmarksgame.alioth.debian.org/ # # submitted by Ian Osgood # modified by Sokolov Yura # modified by bearophile # modified by jacek2v: few changes in algorytm, added multiprocessing, used str.count (nucleo newer overlapping) from sys import stdin from collections import defaultdict from multiprocessing import Process, Pool, cpu_count def gen_freq(seq, frame): frequences = defaultdict(int) ns = len(seq) + 1 - frame for ii in range(ns): frequences[seq[ii:ii + frame]] += 1 return ns, frequences def sort_seq(seq, length): n, frequences = gen_freq(seq, length) #l = sorted(frequences.items(), reverse=True, key=lambda (seq,freq): (freq,seq)) l = sorted(list(frequences.items()), reverse=True, key=lambda seq_freq: (seq_freq[1],seq_freq[0])) return [(st, 100.0*fr/n) for st, fr in l] def find_seq(seq, nucleo): count = seq.count(nucleo) return nucleo, count def load(): for line in stdin: if line[0:3] == ">TH": break seq = [] for line in stdin: if line[0] in ">;": break seq.append( line[:-1] ) return seq def main(): nucleos = "GGT GGTA GGTATT GGTATTTTAATT GGTATTTTAATTTATAGT" sequence = "".join(load()).upper() plres = [] pl = Pool(processes=cpu_count() + 1) for nl in 1,2: plres.append(pl.apply_async(sort_seq, (sequence, nl, ))) for se in nucleos.split(): plres.append(pl.apply_async(find_seq, (sequence, se, ))) pl.close() pl.join() for ii in 0,1: print('\n'.join("%s %.3f" % (st, fr) for st,fr in plres[ii].get())) print('') for ii in range(2, len(nucleos.split()) + 2): print("%d\t%s" % (plres[ii].get()[1], plres[ii].get()[0])) main()
Fri, 09 Sep 2022 06:02:56 GMT COMMAND LINE: /usr/bin/pypy3 knucleotide.pypy3-2.pypy3 0 < knucleotide-input10000.txt PROGRAM OUTPUT: A 30.284 T 29.796 C 20.312 G 19.608 AA 9.212 AT 8.950 TT 8.948 TA 8.936 CA 6.166 CT 6.100 AC 6.086 TC 6.042 AG 6.036 GA 5.968 TG 5.868 GT 5.798 CC 4.140 GC 4.044 CG 3.906 GG 3.798 562 GGT 152 GGTA 15 GGTATT 0 GGTATTTTAATT 0 GGTATTTTAATTTATAGT