sequence = f.readline().strip()
pred_mask = f.readline().strip()
assert len(sequence) == len(pred_mask)
sequence = f.readline().strip()
pred_mask = f.readline().strip()
assert len(sequence) == len(pred_mask)
- assert set(pred_mask) == {"0", "1", "2"}, f"{set(pred_mask)}"
+ assert set(pred_mask).issubset({"0", "1", "2"}), f"{set(pred_mask)}"
pairs.append((sequence, pred_mask))
symbols = ["#"] + list(set("".join([x[0] for x in pairs])) - set(["#"]))
pairs.append((sequence, pred_mask))
symbols = ["#"] + list(set("".join([x[0] for x in pairs])) - set(["#"]))
self.char2id = dict([(c, n) for n, c in enumerate(symbols)])
self.id2char = dict([(n, c) for c, n in self.char2id.items()])
self.char2id = dict([(c, n) for n, c in enumerate(symbols)])
self.id2char = dict([(n, c) for c, n in self.char2id.items()])