Created
July 31, 2018 20:14
-
-
Save standage/d977864dcac74ee663ad677f1d3f9575 to your computer and use it in GitHub Desktop.
Simple kevlar utility for reservoir sampling of partitioned reads. The sampling function might be of general interest.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import argparse | |
import kevlar | |
import random | |
import sys | |
def resv_samp(objstream, n=100, stopafter=None, filterfunc=None): | |
sample = list() | |
for counter, obj in enumerate(objstream): | |
if filterfunc: | |
discard = filterfunc(obj) | |
if discard: | |
continue | |
if len(sample) < n: | |
sample.append(obj) | |
continue | |
guess = random.randint(1, counter) | |
if guess <= n: | |
sample[guess-1] = obj | |
if stopafter and counter > stopafter: | |
break | |
return sample | |
parser = argparse.ArgumentParser() | |
parser.add_argument('partreads') | |
parser.add_argument('outfile') | |
args = parser.parse_args() | |
reader = kevlar.parse_augmented_fastx(kevlar.open(args.partreads, 'r')) | |
preader = kevlar.parse_partitioned_reads(reader) | |
outstream = kevlar.open(args.outfile, 'w') | |
for partition in resv_samp(preader, filterfunc=lambda p: len(p) > 1000): | |
for read in partition: | |
kevlar.print_augmented_fastx(read, outstream) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment