performance measurements
Each table row shows performance measurements for this program with a particular command-line input value N.
| N | CPU secs | Elapsed secs | Memory KB | Code B | ≈ CPU Load |
|---|---|---|---|---|---|
| 10,000 | 4.89 | 2.15 | 3,448 | 593 | 34% 52% 20% 30% 23% 31% 21% 16% |
Read the ↓ make, command line, and program output logs to see how this program was run.
Read benchmark to see what this program should do.
notes
source code
# The Computer Language Benchmarks Game
# http://benchmarksgame.alioth.debian.org/
#
# submitted by Ian Osgood
# modified by Sokolov Yura
# modified by bearophile
# 2to3
from sys import stdin
def gen_freq(seq, frame, frequences):
ns = len(seq) + 1 - frame
frequences.clear()
for ii in range(ns):
nucleo = seq[ii:ii + frame]
if nucleo in frequences:
frequences[nucleo] += 1
else:
frequences[nucleo] = 1
return ns, frequences
def sort_seq(seq, length, frequences):
n, frequences = gen_freq(seq, length, frequences)
l = sorted(list(frequences.items()), reverse=True, key=lambda seq_freq: (seq_freq[1],seq_freq[0]))
print '\n'.join("%s %.3f" % (st, 100.0*fr/n) for st,fr in l)
print
def find_seq(seq, s, frequences):
n,t = gen_freq(seq, len(s), frequences)
print "%d\t%s" % (t.get(s, 0), s)
def main():
frequences = {}
for line in stdin:
if line[0:3] == ">TH":
break
seq = []
for line in stdin:
if line[0] in ">;":
break
seq.append( line[:-1] )
sequence = "".join(seq).upper()
for nl in 1,2:
sort_seq(sequence, nl, frequences)
for se in "GGT GGTA GGTATT GGTATTTTAATT GGTATTTTAATTTATAGT".split():
find_seq(sequence, se, frequences)
main()
make, command-line, and program output logs
Fri, 30 Oct 2020 19:31:49 GMT COMMAND LINE: /usr/bin/jython knucleotide.jython 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