def build_kmer_distribution(datafile, kmer_patterns, sampling_proportion, num_processes, builddir, reverse_complement, pattern_window_length, input_driver_config):
if os.path.exists(get_save_filename(datafile, builddir)):
print("build_kmer_distribution- skipping %s as already done"%datafile)
distob = Distribution.load(get_save_filename(datafile, builddir))
distob.summary()
else:
filetype = get_file_type(datafile)
distob = Distribution([datafile], num_processes)
distob.interval_locator_parameters = (None,)
distob.interval_locator_funcs = (bin_discrete_value,)
distob.assignments_files = ("kmer_binning.txt",)
distob.file_to_stream_func = seq_from_sequence_file
distob.file_to_stream_func_xargs = [filetype,sampling_proportion]
distob.weight_value_provider_func = kmer_count_from_sequence
distob.weight_value_provider_func_xargs = [reverse_complement, pattern_window_length, 1] + kmer_patterns
if filetype == ".cnt":
print "DEBUG setting methods for count file"
distob.file_to_stream_func = tag_count_from_tag_count_file
distob.file_to_stream_func_xargs = [input_driver_config,sampling_proportion]
distob.weight_value_provider_func = kmer_count_from_tag_count
#distdata = build(distob, use="singlethread")
distdata = build(distob, proc_pool_size=num_processes)
distob.save(get_save_filename(datafile, builddir))
print "Distribution %s has %d points distributed over %d intervals, stored in %d parts"%(get_save_filename(datafile, builddir), distob.point_weight, len(distdata), len(distob.part_dict))
return get_save_filename(datafile, builddir)
def build_tax_distribution(datafile):
distob = Distribution([datafile], 1)
distob.file_to_stream_func = my_top_hit_provider
#distob.DEBUG = True
distob.file_to_stream_func_xargs = [0,7,6] # i.e. pick out first field, then kingdom, comnames
distob.interval_locator_funcs = [bin_discrete_value, bin_discrete_value]
distdata = build(distob,"singlethread")
distob.save("%s.pickle"%datafile)
return distdata
