microsoft/qlib · error · ValueError

model is not fitted yet!

Error message

model is not fitted yet!

What it means

Raised by GRUModelTS.predict when called before a completed fit(). The `fitted` flag flips True only after training, best-parameter restore, and checkpoint save; predict refuses to run otherwise because the GRU weights are random.

Source

Thrown at qlib/contrib/model/pytorch_gru_ts.py:283

                stop_steps = 0
                best_epoch = step
                best_param = copy.deepcopy(self.GRU_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.GRU_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.GRU_model.eval()
        preds = []

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

            with torch.no_grad():
                pred = self.GRU_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 fit() before predict().
  2. For inference-only sessions, load the saved state dict into GRU_model and set model.fitted = True before predict.
  3. Fail the pipeline loudly on fit errors so predict is never reached.

Example fix

# before
model = GRUModelTS(**params)
model.predict(dataset)  # ValueError

# after
model = GRUModelTS(**params)
model.fit(dataset)
model.predict(dataset)
Defensive patterns

Strategy: validation

Validate before calling

assert model.fitted, "fit GRUModelTS (or restore its checkpoint) before predict"

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)
        model.predict(dataset)
    else:
        raise

Prevention

When it happens

Trigger: Calling predict(dataset) on a newly constructed GRUModelTS, or after fit() aborted (empty data, NaN collapse, early exception) leaving fitted False.

Common situations: Inference scripts that re-instantiate the model rather than loading the checkpoint; workflow backtest stage running after a silent training failure.

Related errors

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/098dbced400bb268. Report an issue: GitHub.