def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if len(args) != 0:
parser.error("Positional argument detected. make sure all" +
' parameters are identified.' +
'\ne.g.: include the \"-m\" in \"-m MINIMUM_LENGTH\"')
input_dir = opts.input_path
output_dir = opts.output_path
example_filepath = opts.example_path
if not os.path.exists(output_dir):
os.makedirs(output_dir)
file_names = os.listdir(input_dir)
file_names = [fname for fname in file_names if not fname.startswith('.')]
if example_filepath is None:
# table row is base_name, seqs_per_sam, iters, ext
file_name_table = map(parse_rarefaction_fname, file_names)
# sort on seqs/sam
sorted_fname_table = sorted(
file_name_table,
key=operator.itemgetter(1))
# now map back to file name
example_fname = file_names[
file_name_table.index(sorted_fname_table[0])]
example_filepath = os.path.join(input_dir, example_fname)
f = open(example_filepath, 'U')
all_metrics, all_samples, example_data = parse_matrix(f)
num_cols = len(all_samples)
f.close()
# make the table 1 row at a time
# we're building a rarefaction by sample mtx from
# a sample by metric matrix
# each metric is one output file
for metric in all_metrics:
metric_file_data = []
for fname in file_names:
# f_ here refers to the input file currently being processed
# to distinguish from the output file we're building
f = open(os.path.join(input_dir, fname), 'U')
f_metrics, f_samples, f_data = parse_matrix(f)
f.close()
metric_file_data.append(
make_output_row(f_metrics, metric, f_samples,
f_data, fname, num_cols, all_samples))
write_output_file(metric_file_data, output_dir, metric, all_samples)
def main():
option_parser, opts, args = parse_command_line_parameters(**script_info)
if len(args) != 0:
parser.error("Positional argument detected. make sure all" +
' parameters are identified.' +
'\ne.g.: include the \"-m\" in \"-m MINIMUM_LENGTH\"')
input_dir = opts.input_path
output_dir = opts.output_path
example_filepath = opts.example_path
if not os.path.exists(output_dir):
os.makedirs(output_dir)
file_names = os.listdir(input_dir)
file_names = [fname for fname in file_names if not fname.startswith('.')]
if example_filepath is None:
# table row is base_name, seqs_per_sam, iters, ext
file_name_table = map(parse_rarefaction_fname, file_names)
# sort on seqs/sam
sorted_fname_table = sorted(
file_name_table,
key=operator.itemgetter(1))
# now map back to file name
example_fname = file_names[
file_name_table.index(sorted_fname_table[0])]
example_filepath = os.path.join(input_dir, example_fname)
f = open(example_filepath, 'U')
all_metrics, all_samples, example_data = parse_matrix(f)
num_cols = len(all_samples)
f.close()
# make the table 1 row at a time
# we're building a rarefaction by sample mtx from
# a sample by metric matrix
# each metric is one output file
for metric in all_metrics:
metric_file_data = []
for fname in file_names:
# f_ here refers to the input file currently being processed
# to distinguish from the output file we're building
f = open(os.path.join(input_dir, fname), 'U')
f_metrics, f_samples, f_data = parse_matrix(f)
f.close()
metric_file_data.append(
make_output_row(f_metrics, metric, f_samples,
f_data, fname, num_cols, all_samples))
write_output_file(metric_file_data, output_dir, metric, all_samples)