Forecast Model

The Forecast Model is designed to make the prediction score about stocks and can be used as an independent module.

Base Class

fit

The attribute names of the learned model should not start with ‘_’. So that the model could be dumped to disk.

The following code example shows how to retrieve x_train, y_train, and w_train from the dataset:

# get features and labels
df_train, df_valid = dataset.prepare(
    ["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
)
x_train, y_train = df_train["feature"], df_train["label"]
x_valid, y_valid = df_valid["feature"], df_valid["label"]

# get weights
try:
    wdf_train, wdf_valid = dataset.prepare(["train", "valid"], col_set=["weight"],
                                           data_key=DataHandlerLP.DK_L)
    w_train, w_valid = wdf_train["weight"], wdf_valid["weight"]
except KeyError as e:
    w_train = pd.DataFrame(np.ones_like(y_train.values), index=y_train.index)
    w_valid = pd.DataFrame(np.ones_like(y_valid.values), index=y_valid.index)

predict

finetune

Qlib also provides a base class qlib.model.base.ModelFT, which includes the method for finetuning the model.

Example

from qlib.contrib.model.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
from qlib.utils import init_instance_by_config, flatten_dict
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, PortAnaRecord

market = "csi300"
benchmark = "SH000300"

data_handler_config = {
    "start_time": "2008-01-01",
    "end_time": "2020-08-01",
    "fit_start_time": "2008-01-01",
    "fit_end_time": "2014-12-31",
    "instruments": market,
}

task = {
    "model": {
        "class": "LGBModel",
        "module_path": "qlib.contrib.model.gbdt",
        "kwargs": {
            "loss": "mse",
            "colsample_bytree": 0.8879,
            "learning_rate": 0.0421,
            "subsample": 0.8789,
            "lambda_l1": 205.6999,
            "lambda_l2": 580.9768,
            "max_depth": 8,
            "num_leaves": 210,
            "num_threads": 20,
        },
    },
    "dataset": {
        "class": "DatasetH",
        "module_path": "qlib.data.dataset",
        "kwargs": {
            "handler": {
                "class": "Alpha158",
                "module_path": "qlib.contrib.data.handler",
                "kwargs": data_handler_config,
            },
            "segments": {
                "train": ("2008-01-01", "2014-12-31"),
                "valid": ("2015-01-01", "2016-12-31"),
                "test": ("2017-01-01", "2020-08-01"),
            },
        },
    },
}

# model initiaiton
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])

# start exp
with R.start(experiment_name="workflow"):
    # train
    R.log_params(**flatten_dict(task))
    model.fit(dataset)

    # prediction
    recorder = R.get_recorder()
    sr = SignalRecord(model, dataset, recorder)
    sr.generate()

See also examples/train_backtest_analyze.ipynb