def train():
"""train model
Returns
-------
pred_score: pandas.DataFrame
predict scores
performance: dict
model performance
"""
# get data
x_train, y_train, x_validate, y_validate, x_test, y_test = QLibDataHandlerClose(
**DATA_HANDLER_CONFIG).get_split_data(**TRAINER_CONFIG)
# train
model = LGBModel(**MODEL_CONFIG)
model.fit(x_train, y_train, x_validate, y_validate)
_pred = model.predict(x_test)
_pred = pd.DataFrame(_pred, index=x_test.index, columns=y_test.columns)
pred_score = pd.DataFrame(index=_pred.index)
pred_score["score"] = _pred.iloc(axis=1)[0]
# get performance
model_score = model.score(x_test, y_test)
# Remove rows from x, y and w, which contain Nan in any columns in y_test.
x_test, y_test, __ = drop_nan_by_y_index(x_test, y_test)
pred_test = model.predict(x_test)
model_pearsonr = pearsonr(np.ravel(pred_test), np.ravel(y_test.values))[0]
return pred_score, {
"model_score": model_score,
"model_pearsonr": model_pearsonr
}
).get_split_data(**TRAINER_CONFIG)
MODEL_CONFIG = {
"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,
}
# use default model
# custom Model, refer to: TODO: Model API url
model = LGBModel(**MODEL_CONFIG)
model.fit(x_train, y_train, x_validate, y_validate)
_pred = model.predict(x_test)
_pred = pd.DataFrame(_pred, index=x_test.index, columns=y_test.columns)
# backtest requires pred_score
pred_score = pd.DataFrame(index=_pred.index)
pred_score["score"] = _pred.iloc(axis=1)[0]
# save pred_score to file
pred_score_path = Path("~/tmp/qlib/pred_score.pkl").expanduser()
pred_score_path.parent.mkdir(exist_ok=True, parents=True)
pred_score.to_pickle(pred_score_path)
###################################
# backtest