def train_with_sigana():
"""train model followed by SigAnaRecord
Returns
-------
pred_score: pandas.DataFrame
predict scores
performance: dict
model performance
"""
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
# start exp
with R.start(experiment_name="workflow_with_sigana"):
R.log_params(**flatten_dict(task))
model.fit(dataset)
# predict and calculate ic and ric
recorder = R.get_recorder()
sar = SigAnaRecord(recorder, model=model, dataset=dataset)
sar.generate()
ic = sar.load(sar.get_path("ic.pkl"))
ric = sar.load(sar.get_path("ric.pkl"))
pred_score = sar.load("pred.pkl")
smr = SignalMseRecord(recorder)
smr.generate()
uri_path = R.get_uri()
return pred_score, {"ic": ic, "ric": ric}, uri_path
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(sr.get_path("pred.pkl"))
# predict and 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"))
uri_path = R.get_uri()
return pred_score, {"ic": ic, "ric": ric}, uri_path
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)
# To test get_local_dir
print(recorder.get_local_dir())
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,
},
},
}
# 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(CSI300_GBDT_TASK))
model.fit(dataset)
R.save_objects(**{"params.pkl": model})
# prediction
recorder = R.get_recorder()
sr = SignalRecord(model, dataset, recorder)
sr.generate()
# Signal Analysis
sar = SigAnaRecord(recorder)
sar.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, "day")
par.generate()