def train_with_sigana(uri_path: str = None):
"""train model followed by SigAnaRecord
Returns
-------
pred_score: pandas.DataFrame
predict scores
performance: dict
model performance
"""
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
# start exp
with R.start(experiment_name="workflow_with_sigana", uri=uri_path):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
sr = SignalRecord(model, dataset, recorder)
sr.generate()
pred_score = sr.load("pred.pkl")
# predict and calculate ic and ric
sar = SigAnaRecord(recorder)
sar.generate()
ic = sar.load("ic.pkl")
ric = sar.load("ric.pkl")
uri_path = R.get_uri()
return pred_score, {"ic": ic, "ric": ric}, uri_path
def _train_model(self, model, dataset):
with R.start(experiment_name="train"):
R.log_params(**flatten_dict(self.task))
model.fit(dataset)
R.save_objects(**{"params.pkl": model})
# prediction
recorder = R.get_recorder()
sr = SignalRecord(model, dataset, recorder)
sr.generate()
def train(uri_path: str = None):
"""train model
Returns
-------
pred_score: pandas.DataFrame
predict scores
performance: dict
model performance
"""
# model initiaiton
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
# To test __repr__
print(dataset)
print(R)
# start exp
with R.start(experiment_name="workflow", uri=uri_path):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
R.save_objects(trained_model=model)
# prediction
recorder = R.get_recorder()
# To test __repr__
print(recorder)
# To test get_local_dir
print(recorder.get_local_dir())
rid = recorder.id
sr = SignalRecord(model, dataset, recorder)
sr.generate()
pred_score = sr.load("pred.pkl")
# calculate ic and ric
sar = SigAnaRecord(recorder)
sar.generate()
ic = sar.load("ic.pkl")
ric = sar.load("ric.pkl")
return pred_score, {"ic": ic, "ric": ric}, rid
def train_mse(uri_path: str = None):
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
with R.start(experiment_name="workflow", uri=uri_path):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
SignalRecord(recorder=recorder, model=model, dataset=dataset).generate()
sr = SignalMseRecord(recorder)
sr.generate()
uri = R.get_uri()
return uri
def train():
"""train model
Returns
-------
pred_score: pandas.DataFrame
predict scores
performance: dict
model performance
"""
# model initiaiton
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
# To test __repr__
print(dataset)
print(R)
# start exp
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
# prediction
recorder = R.get_recorder()
# To test __repr__
print(recorder)
rid = recorder.id
sr = SignalRecord(model, dataset, recorder)
sr.generate()
pred_score = sr.load()
# calculate ic and ric
sar = SigAnaRecord(recorder)
sar.generate()
ic = sar.load(sar.get_path("ic.pkl"))
ric = sar.load(sar.get_path("ric.pkl"))
return pred_score, {"ic": ic, "ric": ric}, rid
"close_cost": 0.0015,
"min_cost": 5,
"return_order": True,
},
}
# model initialization
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
# NOTE: This line is optional
# It demonstrates that the dataset can be used standalone.
example_df = dataset.prepare("train")
print(example_df.head())
# start exp
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
R.save_objects(**{"params.pkl": model})
# prediction
recorder = R.get_recorder()
sr = SignalRecord(model, dataset, recorder)
sr.generate()
# backtest. If users want to use backtest based on their own prediction,
# please refer to https://qlib.readthedocs.io/en/latest/component/recorder.html#record-template.
par = PortAnaRecord(recorder, port_analysis_config)
par.generate()
def get_update_data(self, dataset: Dataset) -> pd.DataFrame:
new_label = SignalRecord.generate_label(dataset)
cb_data = _replace_range(self.old_data.sort_index(), new_label)
return cb_data
def get_update_data(self, dataset: Dataset) -> pd.DataFrame:
new_label = SignalRecord.generate_label(dataset)
cb_data = pd.concat([self.old_data, new_label], axis=0)
cb_data = cb_data[~cb_data.index.duplicated(keep="last")].sort_index()
return cb_data
def main(xargs):
dataset_config = {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha360",
"module_path": "qlib.contrib.data.handler",
"kwargs": {
"start_time":
"2008-01-01",
"end_time":
"2020-08-01",
"fit_start_time":
"2008-01-01",
"fit_end_time":
"2014-12-31",
"instruments":
xargs.market,
"infer_processors": [
{
"class": "RobustZScoreNorm",
"kwargs": {
"fields_group": "feature",
"clip_outlier": True
}
},
{
"class": "Fillna",
"kwargs": {
"fields_group": "feature"
}
},
],
"learn_processors": [
{
"class": "DropnaLabel"
},
{
"class": "CSRankNorm",
"kwargs": {
"fields_group": "label"
}
},
],
"label": ["Ref($close, -2) / Ref($close, -1) - 1"],
},
},
"segments": {
"train": ("2008-01-01", "2014-12-31"),
"valid": ("2015-01-01", "2016-12-31"),
"test": ("2017-01-01", "2020-08-01"),
},
},
}
model_config = {
"class": "QuantTransformer",
"module_path": "trade_models",
"kwargs": {
"loss": "mse",
"GPU": "0",
"metric": "loss",
},
}
task = {"model": model_config, "dataset": dataset_config}
model = init_instance_by_config(model_config)
dataset = init_instance_by_config(dataset_config)
# start exp to train model
with R.start(experiment_name="train_tt_model"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
R.save_objects(trained_model=model)
# prediction
recorder = R.get_recorder()
print(recorder)
sr = SignalRecord(model, dataset, recorder)
sr.generate()
# backtest. If users want to use backtest based on their own prediction,
# please refer to https://qlib.readthedocs.io/en/latest/component/recorder.html#record-template.
par = PortAnaRecord(recorder, port_analysis_config)
par.generate()