primes = [
75000007, 75000017, 75000031, 75000047, 75000071, 75000083, 75000097,
75000103, 75000113, 75000143, 75000157, 75000169, 75000173, 75000179,
75000181, 75000187, 75000197, 75000227, 75000241
]
###
this_filename = filename
for n, prime in enumerate(primes):
ht = khmer.new_hashtable(15, prime)
next_filename = filename + '.round%d' % n
total_reads, n_consumed = ht.consume_fasta(this_filename)
x = khmer.filter_fasta_file(ht, this_filename, total_reads, next_filename,
5)
_, n_seq_kept = x
print '%d: ate %d k-mers of %d reads' % (n, n_consumed, total_reads)
print '%d: kept %d of %d (%.1f%%)' % (
n, n_seq_kept, total_reads, n_seq_kept / float(total_reads) * 100)
fp.write('%d %d %d\n' % (n, n_seq_kept, ht.n_occupied()))
fp.flush()
this_filename = next_filename
###
# vim: set ft=python ts=4 sts=4 sw=4 et tw=79:
#! /usr/bin/env python
import khmer
filename = '1m.fa'
ht_full = khmer.new_hashtable(15, 4**15)
print 'filtering 15-mers exactly:'
total_reads, n_consumed = ht_full.consume_fasta(filename)
print 'ate %d k-mers of %d reads' % (n_consumed, total_reads)
print 'filtering...'
if 0:
(total_reads_2,
n_seq_kept) = khmer.filter_fasta_file(ht_full, filename, total_reads,
filename + '.15.exact', 5)
print 'kept %d of %d (%.1f%%)' % (n_seq_kept, total_reads,
n_seq_kept / float(total_reads) * 100)
print 'counting!'
print '%d total k-mers' % (ht_full.n_occupied())
75000181,
75000187,
75000197,
75000227,
75000241]
###
this_filename = filename
for n, prime in enumerate(primes):
ht = khmer.new_hashtable(15, prime)
next_filename = filename + '.round%d' % n
total_reads, n_consumed = ht.consume_fasta(this_filename)
x = khmer.filter_fasta_file(ht, this_filename, total_reads, next_filename,
5)
_, n_seq_kept = x
print '%d: ate %d k-mers of %d reads' % (n, n_consumed, total_reads)
print '%d: kept %d of %d (%.1f%%)' % (
n, n_seq_kept, total_reads, n_seq_kept / float(total_reads) * 100)
fp.write('%d %d %d\n' % (n, n_seq_kept, ht.n_occupied()))
fp.flush()
this_filename = next_filename
###
# vim: set ft=python ts=4 sts=4 sw=4 et tw=79:
#! /usr/bin/env python
import khmer
filename = '1m.fa'
ht_full = khmer.new_hashtable(15, 4 ** 15)
print 'filtering 15-mers exactly:'
total_reads, n_consumed = ht_full.consume_fasta(filename)
print 'ate %d k-mers of %d reads' % (n_consumed, total_reads)
print 'filtering...'
if 0:
(total_reads_2, n_seq_kept) = khmer.filter_fasta_file(ht_full,
filename,
total_reads,
filename +
'.15.exact',
5)
print 'kept %d of %d (%.1f%%)' % (
n_seq_kept, total_reads, n_seq_kept / float(total_reads) * 100)
print 'counting!'
print '%d total k-mers' % (ht_full.n_occupied())
# vim: set ft=python ts=4 sts=4 sw=4 et tw=79:
