microsoft/qlib · error · ValueError

Empty training data from dataset, please check your dataset

Error message

Empty training data from dataset, please check your dataset config.

What it means

Raised at the start of GRUModel.fit when the prepared train segment is an empty DataFrame. Unlike pytorch_general_nn (which also requires valid), GRU tolerates a missing/empty valid segment (it defaults to None) but hard-fails on empty train data, because there is nothing to optimize.

Source

Thrown at qlib/contrib/model/pytorch_gru.py:229

        dataset: DatasetH,
        evals_result=dict(),
        save_path=None,
    ):
        # prepare training and validation data
        dfs = {
            k: dataset.prepare(
                k,
                col_set=["feature", "label"],
                data_key=DataHandlerLP.DK_L,
            )
            for k in ["train", "valid"]
            if k in dataset.segments
        }
        df_train, df_valid = dfs.get("train", pd.DataFrame()), dfs.get("valid", pd.DataFrame())

        # check if training data is empty
        if df_train.empty:
            raise ValueError("Empty training data from dataset, please check your dataset config.")

        df_train = df_train.dropna()
        x_train, y_train = df_train["feature"], df_train["label"]

        # check if validation data is provided
        if not df_valid.empty:
            df_valid = df_valid.dropna()
            x_valid, y_valid = df_valid["feature"], df_valid["label"]
        else:
            x_valid, y_valid = None, None

        save_path = get_or_create_path(save_path)
        stop_steps = 0
        train_loss = 0
        best_score = -np.inf
        best_epoch = 0
        evals_result["train"] = []
        evals_result["valid"] = []

View on GitHub (pinned to 79633dd950)

Solutions

1. Print dataset.prepare('train', col_set=['feature','label'], data_key=DataHandlerLP.DK_L).shape and confirm it is non-empty.
2. Adjust train segment dates to overlap the data calendar produced by dump_bin.
3. Check instrument filters and processors are not eliminating all rows.
4. Ensure the segment key is exactly "train" in the dataset config.

Example fix

# before
"segments": {"train": ("2025-01-01", "2025-12-31")}  # data ends 2022 -> empty

# after
"segments": {"train": ("2018-01-01", "2021-12-31")}

df_train = dataset.prepare("train", col_set=["feature", "label"], data_key=DataHandlerLP.DK_L)
assert not df_train.empty, "train segment is empty; check segment dates and data calendar"

When it happens

Trigger: fit(dataset) where dataset.prepare("train", col_set=["feature","label"], data_key=DK_L) returns zero rows: train date range outside the data calendar, segment misnamed, or all rows dropped. Note the check runs BEFORE dropna, so data that becomes empty only after dropna() produces a different failure downstream (empty tensor batches), not this error.

Common situations: Train segment dates not covered by the dumped binary data; segment key typo such as "Train"; a learn-type processor removing every row; using an instrument universe with no overlapping dates.

Related errors

• Empty data from dataset, please check your dataset config.
• Empty data from dataset, please check your dataset config.
• Empty data from dataset, please check your dataset config.
• Empty data from dataset, please check your dataset config.
• Empty data from dataset, please check your dataset config.

AI-assisted analysis of microsoft/qlib@79633dd950 (2026-08-15). Data as JSON: /api/errors/5bc4d26e34514ba4. Report an issue: GitHub.