def test_AsyncTsvBatchWriter_array(dl_batch, pred_batch_array, tmpdir):
tmpfile = str(tmpdir.mkdir("example").join("out.tsv"))
writer = AsyncBatchWriter(TsvBatchWriter(tmpfile))
batch = prepare_batch(dl_batch, pred_batch_array)
writer.batch_write(batch)
writer.batch_write(batch)
writer.close()
df = pd.read_csv(tmpfile, sep="\t")
assert set(list(df.columns)) == {
'metadata/ranges/id', 'metadata/ranges/strand', 'metadata/ranges/chr',
'metadata/ranges/start', 'metadata/ranges/end', 'metadata/gene_id',
'preds/0', 'preds/1', 'preds/2'
}
assert list(df['metadata/ranges/id']) == [0, 1, 2, 0, 1, 2]
def test_MultipleBatchWriter(dl_batch, pred_batch_array, tmpdir):
tmpdir = tmpdir.mkdir("example")
h5_tmpfile = str(tmpdir.join("out.h5"))
tsv_tmpfile = str(tmpdir.join("out.tsv"))
batch = prepare_batch(dl_batch, pred_batch_array)
writer = MultipleBatchWriter(
[TsvBatchWriter(tsv_tmpfile),
HDF5BatchWriter(h5_tmpfile)])
writer.batch_write(batch)
writer.batch_write(batch)
writer.close()
assert os.path.exists(h5_tmpfile)
assert os.path.exists(tsv_tmpfile)
df = pd.read_csv(tsv_tmpfile, sep="\t")
assert set(list(df.columns)) == {
'metadata/ranges/id', 'metadata/ranges/strand', 'metadata/ranges/chr',
'metadata/ranges/start', 'metadata/ranges/end', 'metadata/gene_id',
'preds/0', 'preds/1', 'preds/2'
}
assert list(df['metadata/ranges/id']) == [0, 1, 2, 0, 1, 2]