def __call__(self, ensemble_dict: dict) -> pd.DataFrame:
"""using sample:
from qlib.model.ens.ensemble import AverageEnsemble
pred_res['new_key_name'] = AverageEnsemble()(predict_dict)
Parameters
----------
ensemble_dict : dict
Dictionary you want to ensemble
Returns
-------
pd.DataFrame
The dictionary including ensenbling result
"""
# need to flatten the nested dict
ensemble_dict = flatten_dict(ensemble_dict, sep=FLATTEN_TUPLE)
values = list(ensemble_dict.values())
# NOTE: this may change the style underlying data!!!!
# from pd.DataFrame to pd.Series
results = pd.concat(values, axis=1)
results = results.groupby("datetime").apply(
lambda df: (df - df.mean()) / df.std())
results = results.mean(axis=1)
results = results.sort_index()
return results
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_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 __call__(self, ensemble_dict: dict) -> pd.DataFrame:
# need to flatten the nested dict
ensemble_dict = flatten_dict(ensemble_dict, sep=FLATTEN_TUPLE)
values = list(ensemble_dict.values())
results = pd.concat(values, axis=1)
results = results.groupby("datetime").apply(
lambda df: (df - df.mean()) / df.std())
results = results.mean(axis=1)
results = results.sort_index()
return results
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_mse():
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
sr = SignalMseRecord(recorder, model=model, dataset=dataset)
sr.generate()
uri = R.get_uri()
return uri
def train_multiseg():
model = init_instance_by_config(CSI300_GBDT_TASK["model"])
dataset = init_instance_by_config(CSI300_GBDT_TASK["dataset"])
with R.start(experiment_name="workflow"):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
model.fit(dataset)
recorder = R.get_recorder()
sr = MultiSegRecord(model, dataset, recorder)
sr.generate(dict(valid="valid", test="test"), True)
uri = R.get_uri()
return uri
def run_exp(task_config, dataset, experiment_name, recorder_name, uri):
model = init_instance_by_config(task_config["model"])
model_fit_kwargs = dict(dataset=dataset)
# Let's start the experiment.
with R.start(
experiment_name=experiment_name,
recorder_name=recorder_name,
uri=uri,
resume=True,
):
# Setup log
recorder_root_dir = R.get_recorder().get_local_dir()
log_file = os.path.join(recorder_root_dir,
"{:}.log".format(experiment_name))
set_log_basic_config(log_file)
logger = get_module_logger("q.run_exp")
logger.info("task_config::\n{:}".format(
pprint.pformat(task_config, indent=2)))
logger.info("[{:}] - [{:}]: {:}".format(experiment_name, recorder_name,
uri))
logger.info("dataset={:}".format(dataset))
# Train model
R.log_params(**flatten_dict(task_config))
if "save_path" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_path"] = os.path.join(
recorder_root_dir, "model.ckp")
elif "save_dir" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_dir"] = os.path.join(
recorder_root_dir, "model-ckps")
model.fit(**model_fit_kwargs)
# Get the recorder
recorder = R.get_recorder()
R.save_objects(**{"model.pkl": model})
# Generate records: prediction, backtest, and analysis
for record in task_config["record"]:
record = record.copy()
if record["class"] == "SignalRecord":
srconf = {
"model": model,
"dataset": dataset,
"recorder": recorder
}
record["kwargs"].update(srconf)
sr = init_instance_by_config(record)
sr.generate()
else:
rconf = {"recorder": recorder}
record["kwargs"].update(rconf)
ar = init_instance_by_config(record)
ar.generate()
def fake_experiment():
"""A fake experiment workflow to test uri
Returns
-------
pass_or_not_for_default_uri: bool
pass_or_not_for_current_uri: bool
temporary_exp_dir: str
"""
# start exp
default_uri = R.get_uri()
current_uri = "file:./temp-test-exp-mag"
with R.start(experiment_name="fake_workflow_for_expm", uri=current_uri):
R.log_params(**flatten_dict(CSI300_GBDT_TASK))
current_uri_to_check = R.get_uri()
default_uri_to_check = R.get_uri()
return default_uri == default_uri_to_check, current_uri == current_uri_to_check, current_uri
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 run_exp(task_config, dataset, experiment_name, recorder_name, uri):
# model initiaiton
print("")
print("[{:}] - [{:}]: {:}".format(experiment_name, recorder_name, uri))
print("dataset={:}".format(dataset))
model = init_instance_by_config(task_config["model"])
# start exp
with R.start(experiment_name=experiment_name,
recorder_name=recorder_name,
uri=uri):
log_file = R.get_recorder().root_uri / "{:}.log".format(
experiment_name)
set_log_basic_config(log_file)
# train model
R.log_params(**flatten_dict(task_config))
model.fit(dataset)
recorder = R.get_recorder()
R.save_objects(**{"model.pkl": model})
# generate records: prediction, backtest, and analysis
for record in task_config["record"]:
record = record.copy()
if record["class"] == "SignalRecord":
srconf = {
"model": model,
"dataset": dataset,
"recorder": recorder
}
record["kwargs"].update(srconf)
sr = init_instance_by_config(record)
sr.generate()
else:
rconf = {"recorder": recorder}
record["kwargs"].update(rconf)
ar = init_instance_by_config(record)
ar.generate()
def begin_task_train(task_config: dict,
experiment_name: str,
recorder_name: str = None) -> Recorder:
"""
Begin task training to start a recorder and save the task config.
Args:
task_config (dict): the config of a task
experiment_name (str): the name of experiment
recorder_name (str): the given name will be the recorder name. None for using rid.
Returns:
Recorder: the model recorder
"""
with R.start(experiment_name=experiment_name, recorder_name=recorder_name):
R.log_params(**flatten_dict(task_config))
R.save_objects(**{"task": task_config
}) # keep the original format and datatype
R.set_tags(**{"hostname": socket.gethostname()})
recorder: Recorder = R.get_recorder()
return recorder
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
def task_train(task_config: dict, experiment_name):
"""
task based training
Parameters
----------
task_config : dict
A dict describes a task setting.
"""
# model initiaiton
model = init_instance_by_config(task_config["model"])
dataset = init_instance_by_config(task_config["dataset"])
# start exp
with R.start(experiment_name=experiment_name):
# train model
R.log_params(**flatten_dict(task_config))
model.fit(dataset)
recorder = R.get_recorder()
R.save_objects(**{"params.pkl": model})
# generate records: prediction, backtest, and analysis
for record in task_config["record"]:
if record["class"] == SignalRecord.__name__:
srconf = {
"model": model,
"dataset": dataset,
"recorder": recorder
}
record["kwargs"].update(srconf)
sr = init_instance_by_config(record)
sr.generate()
else:
rconf = {"recorder": recorder}
record["kwargs"].update(rconf)
ar = init_instance_by_config(record)
ar.generate()
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()
"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()
"deal_price": "close",
"open_cost": 0.0005,
"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")
def run_exp(
task_config,
dataset,
experiment_name,
recorder_name,
uri,
model_obj_name="model.pkl",
):
model = init_instance_by_config(task_config["model"])
model_fit_kwargs = dict(dataset=dataset)
# Let's start the experiment.
with R.start(
experiment_name=experiment_name,
recorder_name=recorder_name,
uri=uri,
resume=True,
):
# Setup log
recorder_root_dir = R.get_recorder().get_local_dir()
log_file = os.path.join(recorder_root_dir,
"{:}.log".format(experiment_name))
set_log_basic_config(log_file)
logger = get_module_logger("q.run_exp")
logger.info("task_config::\n{:}".format(
pprint.pformat(task_config, indent=2)))
logger.info("[{:}] - [{:}]: {:}".format(experiment_name, recorder_name,
uri))
logger.info("dataset={:}".format(dataset))
# Train model
try:
if hasattr(model, "to"): # Recoverable model
ori_device = model.device
model = R.load_object(model_obj_name)
model.to(ori_device)
else:
model = R.load_object(model_obj_name)
logger.info(
"[Find existing object from {:}]".format(model_obj_name))
except OSError:
R.log_params(**flatten_dict(update_gpu(task_config, None)))
if "save_path" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_path"] = os.path.join(
recorder_root_dir, "model.ckp")
elif "save_dir" in inspect.getfullargspec(model.fit).args:
model_fit_kwargs["save_dir"] = os.path.join(
recorder_root_dir, "model-ckps")
model.fit(**model_fit_kwargs)
# remove model to CPU for saving
if hasattr(model, "to"):
old_device = model.device
model.to("cpu")
R.save_objects(**{model_obj_name: model})
model.to(old_device)
else:
R.save_objects(**{model_obj_name: model})
except Exception as e:
raise ValueError("Something wrong: {:}".format(e))
# Get the recorder
recorder = R.get_recorder()
# Generate records: prediction, backtest, and analysis
for record in task_config["record"]:
record = deepcopy(record)
if record["class"] == "MultiSegRecord":
record["kwargs"] = dict(model=model,
dataset=dataset,
recorder=recorder)
sr = init_instance_by_config(record)
sr.generate(**record["generate_kwargs"])
elif record["class"] == "SignalRecord":
srconf = {
"model": model,
"dataset": dataset,
"recorder": recorder
}
record["kwargs"].update(srconf)
sr = init_instance_by_config(record)
sr.generate()
else:
rconf = {"recorder": recorder}
record["kwargs"].update(rconf)
ar = init_instance_by_config(record)
ar.generate()
def _log_task_info(task_config: dict):
R.log_params(**flatten_dict(task_config))
R.save_objects(**{"task":
task_config}) # keep the original format and datatype
R.set_tags(**{"hostname": socket.gethostname()})
