microsoft/qlib · error · ValueError

model is not fitted yet!

Error message

model is not fitted yet!

What it means

The TS LSTM predict() checks self.fitted at entry; the flag flips True only at the very end of a successful fit(). Predicting beforehand raises ValueError('model is not fitted yet!') — no test data is prepared and no model eval occurs.

Source

Thrown at qlib/contrib/model/pytorch_lstm_ts.py:278

                stop_steps = 0
                best_epoch = step
                best_param = copy.deepcopy(self.LSTM_model.state_dict())
            else:
                stop_steps += 1
                if stop_steps >= self.early_stop:
                    self.logger.info("early stop")
                    break

        self.logger.info("best score: %.6lf @ %d" % (best_score, best_epoch))
        self.LSTM_model.load_state_dict(best_param)
        torch.save(best_param, save_path)

        if self.use_gpu:
            torch.cuda.empty_cache()

    def predict(self, dataset):
        if not self.fitted:
            raise ValueError("model is not fitted yet!")

        dl_test = dataset.prepare("test", col_set=["feature", "label"], data_key=DataHandlerLP.DK_I)
        dl_test.config(fillna_type="ffill+bfill")
        test_loader = DataLoader(dl_test, batch_size=self.batch_size, num_workers=self.n_jobs)
        self.LSTM_model.eval()
        preds = []

        for data in test_loader:
            feature = data[:, :, 0:-1].to(self.device)

            with torch.no_grad():
                pred = self.LSTM_model(feature.float()).detach().cpu().numpy()

            preds.append(pred)

        return pd.Series(np.concatenate(preds), index=dl_test.get_index())

View on GitHub (pinned to 79633dd950)

Solutions

  1. Complete model.fit(dataset, evals_result) first; check for the 'best score: ... @ epoch' log line as confirmation.
  2. Fix any prior fit failure (its exception is the root cause; fitted remains False otherwise).
  3. Restoring a checkpoint: model.LSTM_model.load_state_dict(torch.load(save_path)); model.fitted = True; then call predict.

Example fix

# before
model = LSTMModel(...)
model.predict(dataset)  # ValueError: model is not fitted yet!

# after
model = LSTMModel(...)
model.fit(dataset, evals_result)
model.predict(dataset)
Defensive patterns

Strategy: validation

Validate before calling

if not model.fitted:
    raise RuntimeError("TS LSTM not fitted; run fit() first")
model.predict(dataset)

Type guard

def is_fitted(model) -> bool:
    return bool(getattr(model, "fitted", False))

Try / catch

try:
    model.predict(dataset)
except ValueError as e:
    if "not fitted" in str(e):
        model.fit(dataset, evals_result)
        model.predict(dataset)
    else:
        raise

Prevention

When it happens

Trigger: model.predict(dataset) where fit() never completed: never called, interrupted, or failed on empty data / NaNs / device errors before setting fitted.

Common situations: Pipeline scripts proceeding to backtest after a training step errored; resuming a session with a fresh model object; notebook cell ordering mistakes.

Related errors

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/6be3867dea3192f3. Report an issue: GitHub.