def main(countsfile, outpath, countsfile2, strand_symmetry, force_overwrite,
dry_run, verbose):
args = locals()
table = LoadTable(countsfile, sep='\t')
if not dry_run:
log_file_path = os.path.join(util.abspath(outpath),
'spectra_analysis.log')
LOGGER.log_file_path = log_file_path
LOGGER.log_message(str(args), label='vars')
LOGGER.input_file(countsfile)
# if there's a strand symmetry argument then we don't need a second file
if strand_symmetry:
group_label = 'strand'
counts_table = util.spectra_table(table, group_label)
if not strand_symmetry:
group_label = 'group'
# be sure there's two files
counts_table2 = LoadTable(countsfile2, sep='\t')
LOGGER.input_file(countsfile2)
counts_table2 = counts_table2.with_new_column('group',
lambda x: '2', columns=counts_table2.header[0])
counts_table1 = table.with_new_column('group',
lambda x: '1', columns=table.header[0])
counts_table1 = util.spectra_table(counts_table1, group_label)
counts_table2 = util.spectra_table(counts_table2, group_label)
# now combine
header = ['group'] + counts_table2.header[:-1]
raw1 = counts_table1.tolist(header)
raw2 = counts_table2.tolist(header)
counts_table = LoadTable(header=header, rows=raw1 + raw2)
if verbose:
print(counts_table)
# spectra table has [count, start, end, group] order
# we reduce comparisons to a start base
results = []
saveable = {}
for start_base in counts_table.distinct_values('start'):
subtable = counts_table.filtered('start == "%s"' % start_base)
columns = [c for c in counts_table.header if c != 'start']
subtable = subtable.get_columns(columns)
total_re, dev, df, collated, formula = log_lin.spectra_difference(
subtable, group_label)
r = [list(x) for x in collated.to_records(index=False)]
if not strand_symmetry:
grp_labels = {'1': countsfile,
'2': countsfile2}
grp_index = list(collated.columns).index('group')
for row in r:
row[grp_index] = grp_labels[row[grp_index]]
p = chisqprob(dev, df)
if p < 1e-6:
prob = "%.2e" % p
else:
prob = "%.6f" % p
for row in r:
row.insert(0, start_base)
row.append(prob)
results += r
significance = ["RE=%.6f" % total_re, "Dev=%.2f" % dev, "df=%d" % df,
"p=%s" % p]
stats = " : ".join(significance)
print("Start base=%s %s" % (start_base, stats))
saveable[start_base] = dict(rel_entropy=total_re, deviance=dev,
df=df, prob=p,
formula=formula, stats=collated.to_json())
table = LoadTable(header=['start_base'] + list(collated.columns) +
['prob'],
rows=results, digits=5).sorted(columns='ret')
json_path = None
outpath = util.abspath(outpath)
if not dry_run:
util.makedirs(outpath)
json_path = os.path.join(outpath, 'spectra_analysis.json')
dump_json(saveable, json_path)
LOGGER.output_file(json_path)
table_path = os.path.join(outpath, 'spectra_summary.txt')
table.write(table_path, sep='\t')
LOGGER.output_file(table_path)
LOGGER.log_message(str(significance), label="significance")
def collate(base_path, output_path, exclude_paths, overwrite):
"""collates all classifier performance stats and writes
to a single tsv file"""
LOGGER.log_args()
outpath = os.path.join(output_path, "collated.tsv.gz")
logfile_path = os.path.join(output_path, "collated.log")
if os.path.exists(outpath) and not overwrite:
click.secho(f"Skipping. {outpath} exists. "
"Use overwrite to force.",
fg='green')
exit(0)
stat_fns = exec_command(f'find {base_path} -name' ' "*performance.json*"')
stat_fns = stat_fns.splitlines()
if not stat_fns:
msg = f'No files matching "*performance.json*" in {base_path}'
click.secho(msg, fg='red')
return
LOGGER.log_file_path = logfile_path
records = []
keys = set()
exclude_paths = [] if exclude_paths is None else exclude_paths.split(',')
num_skipped = 0
for fn in tqdm(stat_fns, ncols=80):
if skip_path(exclude_paths, fn):
num_skipped += 1
LOGGER.log_message(fn, label="SKIPPED FILE")
continue
LOGGER.input_file(fn)
data = load_json(fn)
labels = data['classification_report']['labels']
fscores = data['classification_report']['f-score']
row = {
"stat_path": fn,
"classifier_path": data["classifier_path"],
"auc": data["auc"],
"algorithm": data["classifier_label"],
"mean_precision": data["mean_precision"],
f"fscore({labels[0]})": fscores[0],
f"fscore({labels[1]})": fscores[1],
'balanced_accuracy': data['balanced_accuracy']
}
row.update(data["feature_params"])
keys.update(row.keys())
records.append(row)
columns = sorted(keys)
rows = list(map(lambda r: [r.get(c, None) for c in columns], records))
table = LoadTable(header=columns, rows=rows)
table = table.sorted(reverse="auc")
table = table.with_new_column(
"name",
lambda x: model_name_from_features(*x),
columns=["flank_size", "feature_dim", "usegc", "proximal"])
table = table.with_new_column("size",
sample_size_from_path,
columns="classifier_path")
table.write(outpath)
LOGGER.output_file(outpath)
# make summary statistics via grouping by factors
factors = [
"algorithm", "name", "flank_size", "feature_dim", "proximal", "usegc",
"size"
]
summary = summary_stat_table(table, factors=factors)
outpath = os.path.join(output_path, "summary_statistics.tsv.gz")
summary.write(outpath)
LOGGER.output_file(outpath)
if num_skipped:
click.secho("Skipped %d files that matched exclude_paths" %
num_skipped,
fg='red')