def write_tsv(records: Iterator[DialogRecord], path: Union[str, Path]): seqs = ((str(x), ' '.join(map(str, y))) for x, y in records) lines = (f'{x}\t{y}\n' for x, y in seqs) log.info(f"Storing data at {path}") with IO.writer(path) as f: for line in lines: f.write(line)
def store_model(self, step: int, model, train_score: float, val_score: float, keep: int): """ saves model to a given path :param step: step number of training :param model: model object itself :param train_score: score of model on training split :param val_score: score of model on validation split :param keep: number of good models to keep, bad models will be deleted :return: """ # TODO: improve this by skipping the model save if the model is not good enough to be saved if self.read_only: log.warning("Ignoring the store request; experiment is readonly") return name = f'model_{step:05d}_{train_score:.6f}_{val_score:.6f}.pkl' path = self.model_dir / name log.info(f"Saving... step={step} to {path}") torch.save(model, str(path)) for bad_model in self.list_models(sort='total_score', desc=False)[keep:]: log.info(f"Deleting bad model {bad_model} . Keep={keep}") os.remove(str(bad_model)) with IO.writer(os.path.join(self.model_dir, 'scores.tsv'), append=True) as f: cols = [ str(step), datetime.now().isoformat(), name, f'{train_score:g}', f'{val_score:g}' ] f.write('\t'.join(cols) + '\n')
def write_lines(path: Union[str, Path], lines): count = 0 with IO.writer(path) as out: for line in lines: count += 1 out.write(line.strip()) out.write("\n") log.info(f"Wrote {count} lines to {path}")
def write_dialogs(dialogs: Iterator[Dialog], out: Path, dialog_sep='\n'): count = 0 with IO.writer(out) as outh: for dialog in dialogs: count += 1 for utter in dialog.chat: if utter.uid: outh.write(f'{utter.uid}\t') if utter.weight: outh.write(f'{utter.weight:g}\t') text = " ".join(map(str, utter.text)) outh.write(f'{utter.char}\t{text}\n') outh.write(dialog_sep) log.info(f"Wrote {count} recs to {out}")
def store_config(self): with IO.writer(self._config_file) as fp: return yaml.dump(self.config, fp, default_flow_style=False)