def main(args):
oracle = Oracle(args)
samples_dict = oracle.initializeDataset(save=False, returnData=True)
scores = samples_dict["scores"]
samples_mat = samples_dict["samples"]
seq_letters = oracle.numbers2letters(samples_mat)
seq_ints = [
"".join([str(el) for el in seq if el > 0]) for seq in samples_mat
]
if isinstance(scores, dict):
scores.update({"letters": seq_letters, "indices": seq_ints})
df = pd.DataFrame(scores)
else:
df = pd.DataFrame({
"letters": seq_letters,
"indices": seq_ints,
"scores": scores
})
if args.output:
output_yml = Path(args.output).with_suffix(".yml")
with open(output_yml, "w") as f:
yaml.dump(numpy2python(namespace2dict(args)),
f,
default_flow_style=False)
if args.no_indices:
df.drop(columns="indices", inplace=True)
df.to_csv(args.output)
