#with gzip.open('test.txt.gz', 'wb') as f:
# for i in range(10):
# f.write('111222333444555666777888999000'*100)
bstat = RunningStats()
sstat = RunningStats()
def test():
big = build_x()
bstat.push(len(big))
sio = StringIO()
f = gzip.GzipFile("", "wb", 9, sio)
f.write(big)
f.close()
sstat.push(len(sio.getvalue()))
sio.close()
for i in range(1005):
test()
print("%.4g %.3g +-%.3g %.4g" %
(bstat.min(), bstat.mean(), 2 * bstat.stdev(), bstat.max()))
print("%.4g %.3g +-%.3g %.4g" %
(sstat.min(), sstat.mean(), 2 * sstat.stdev(), sstat.max()))
shuffledCrcs.add(calcCrc(shufSeq))
seq1shufftrans = Seq(shufSeq, generic_dna).translate()
shuffledTransCrcs.add(calcCrc(seq1shufftrans))
print("Shuffled distinct: %d" % (len(shuffledCrcs)))
print("Shuffled trans distinct: %d" % len(shuffledTransCrcs))
#for s in range(len(shuffles)):
# shuf = cds.getShuffledSeq(s)
# if( len(cds.sequence()) != cds.length() ):
# print("WARNING: incorrect shuffled sequence length detected for record (taxid=%d, protId=%s, seqId=%d); real-length=%d, recorded-length=%d." % (taxId, protId, shuffles[s], len(shuff.sequence()), cds.length()))
# warningsCount += 1
if (rl()):
print("processed %d records (%.2g%%)" %
(recordsCount, float(recordsCount) / total * 100))
print(statsLength.count())
print("%.3g %.3g +-%.3g %.3g" % (statsLength.min(), statsLength.mean(),
2 * statsLength.stdev(), statsLength.max()))
print(statsShuffles.count())
print("%.3g %.3g +-%.3g %.3g" % (statsShuffles.min(), statsShuffles.mean(), 2 *
statsShuffles.stdev(), statsShuffles.max()))
print("Done - Processed %d records, found %d warnings" %
(recordsCount, warningsCount))
if (warningsCount > 0):
print("%d warnings found!" % (warningsCount, ))
i = 0
for i in range(totalSequncesToTry):
seq = randseq(sequenceLength)
stats = RunningStats()
for start in range(len(seq) - windowWidth + 1):
fragment = seq[start:(start + windowWidth)]
assert (len(fragment) == windowWidth)
# Calculate the RNA folding energy. This is the computation-heavy part.
strct, energy = RNA.fold(fragment)
assert (energy <= 0.0)
stats.push(energy)
if (stats.mean() > -3.2 and stats.min() > (-6.32 - 0.50)):
weakFasta.append(
SeqRecord(
Seq(seq, alphabet=generic_dna),
id=("rand%d" % i),
description=(
"Random synthetic sequence, mean MFE=%.4g, MFA>=%.4g" %
(stats.mean(), stats.min()))))
elif (stats.mean() < -8.03 and stats.max() < (-6.32 + 0.50)):
strongFasta.append(
SeqRecord(
Seq(seq, alphabet=generic_dna),
id=("rand%d" % i),
description=(
"Random synthetic sequence, mean MFE=%.4g, MFA<=%.4g" %
(stats.mean(), stats.max()))))
