liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 00:06:58 +08:00
Code Activity

Delete workflow code for testing baseline.

Browse Source
This commit is contained in:
lwwang1995
2020-11-27 22:31:50 +08:00
parent bebce24a7c
commit b89c191e6f
7 changed files with 0 additions and 1002 deletions
Download Patch File Download Diff File Expand all files Collapse all files

138
examples/workflow_by_code_alstm.py
View File

@@ -1,138 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
from qlib.utils import init_instance_by_config
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "ALSTM",
"module_path": "qlib.contrib.model.pytorch_alstm",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"num_layers": 2,
"dropout": 0.0,
"n_epochs": 200,
"lr": 1e-3,
"early_stop": 20,
"batch_size": 800,
"metric": "IC",
"loss": "mse",
"seed": 0,
"GPU": "0",
"rnn_type": "GRU",
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

140
examples/workflow_by_code_gats.py
View File

@@ -1,140 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
from qlib.utils import init_instance_by_config
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "GAT",
"module_path": "qlib.contrib.model.pytorch_gats",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"num_layers": 2,
"dropout": 0.7,
"n_epochs": 200,
"lr": 1e-4,
"early_stop": 20,
"metric": "loss",
"loss": "mse",
"base_model": "LSTM",
"with_pretrain": True,
"seed": 0,
"GPU": "0",
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

144
examples/workflow_by_code_gru.py
View File

@@ -1,144 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.pytorch_gru import GRU
from qlib.contrib.data.handler import ALPHA360_Denoise
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
# from qlib.model.learner import train_model
from qlib.utils import init_instance_by_config
import pickle
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "GRU",
"module_path": "qlib.contrib.model.pytorch_gru",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"num_layers": 2,
"dropout": 0.0,
"n_epochs": 200,
"lr": 1e-3,
"early_stop": 20,
"batch_size": 800,
"metric": "loss",
"loss": "mse",
"seed": 0,
"GPU": 0,
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
# model = train_model(task)
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

136
examples/workflow_by_code_hats.py
View File

@@ -1,136 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
from qlib.utils import init_instance_by_config
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "HATS",
"module_path": "qlib.contrib.model.pytorch_hats",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"num_layers": 2,
"dropout": 0.7,
"n_epochs": 200,
"lr": 1e-4,
"early_stop": 20,
"metric": "loss",
"loss": "mse",
"base_model": "LSTM",
"seed": 0,
"GPU": "2",
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset, save_path="benchmarks/HATS/model_hat.pkl")
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

144
examples/workflow_by_code_lstm.py
View File

@@ -1,144 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.pytorch_lstm import LSTM
from qlib.contrib.data.handler import ALPHA360_Denoise
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
# from qlib.model.learner import train_model
from qlib.utils import init_instance_by_config
import pickle
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "LSTM",
"module_path": "qlib.contrib.model.pytorch_lstm",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"num_layers": 2,
"dropout": 0.0,
"n_epochs": 200,
"lr": 1e-3,
"early_stop": 20,
"batch_size": 800,
"metric": "IC",
"loss": "mse",
"seed": 0,
"GPU": 0,
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
# model = train_model(task)
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

158
examples/workflow_by_code_sfm.py
View File

@@ -1,158 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.pytorch_gru import GRU
from qlib.contrib.data.handler import ALPHA360_Denoise
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
from qlib.utils import init_instance_by_config
import pickle
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "SFM",
"module_path": "qlib.contrib.model.pytorch_sfm",
"kwargs": {
"d_feat": 6,
"hidden_size": 64,
"output_dim": 32,
"freq_dim": 25,
"dropout_W": 0.5,
"dropout_U": 0.5,
"n_epochs": 15,
"lr": 1e-3,
"metric": "",
"batch_size": 1600,
"early_stop": 20,
"eval_steps": 5,
"loss": "mse",
"lr_decay": 0.96,
"lr_decay_steps": 100,
"optimizer": "adam",
"GPU": 3,
"seed": 710,
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
# model = train_model(task)
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)

142
examples/workflow_by_code_tabnet.py
View File

@@ -1,142 +0,0 @@
# Copyright (c) Microsoft Corporation.
# Licensed under the MIT License.
import sys
from pathlib import Path
import qlib
import pandas as pd
from qlib.config import REG_CN
from qlib.contrib.model.tabnet import TabNetModel
from qlib.contrib.data.handler import ALPHA360_Denoise
from qlib.contrib.strategy.strategy import TopkDropoutStrategy
from qlib.contrib.evaluate import (
backtest as normal_backtest,
risk_analysis,
)
from qlib.utils import exists_qlib_data
# from qlib.model.learner import train_model
from qlib.utils import init_instance_by_config
import pickle
if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
if not exists_qlib_data(provider_uri):
print(f"Qlib data is not found in {provider_uri}")
sys.path.append(str(Path(__file__).resolve().parent.parent.joinpath("scripts")))
from get_data import GetData
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
qlib.init(provider_uri=provider_uri, region=REG_CN)
MARKET = "csi300"
BENCHMARK = "SH000300"
###################################
# train model
###################################
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,
}
TRAINER_CONFIG = {
"train_start_time": "2008-01-01",
"train_end_time": "2014-12-31",
"validate_start_time": "2015-01-01",
"validate_end_time": "2016-12-31",
"test_start_time": "2017-01-01",
"test_end_time": "2020-08-01",
}
task = {
"model": {
"class": "TabNetModel",
"module_path": "qlib.contrib.model.tabnet",
"kwargs": {
"n_d": 8,
"n_a": 8,
"n_steps": 3,
"gamma": 1.3,
"n_independent": 2,
"n_shared": 2,
"seed": 0,
"momentum": 0.02,
"lambda_sparse": 1e-3,
"optimizer_params": {"lr": 2e-3},
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "ALPHA360_Denoise",
"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"),
},
},
}
# You shoud record the data in specific sequence
# "record": ['SignalRecord', 'SigAnaRecord', 'PortAnaRecord'],
}
# model = train_model(task)
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
model.fit(dataset)
pred_score = model.predict(dataset)
# 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
###################################
STRATEGY_CONFIG = {
"topk": 50,
"n_drop": 5,
}
BACKTEST_CONFIG = {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
}
# use default strategy
# custom Strategy, refer to: TODO: Strategy API url
strategy = TopkDropoutStrategy(**STRATEGY_CONFIG)
report_normal, positions_normal = normal_backtest(pred_score, strategy=strategy, **BACKTEST_CONFIG)
###################################
# analyze
# If need a more detailed analysis, refer to: examples/train_and_bakctest.ipynb
###################################
analysis = dict()
analysis["excess_return_without_cost"] = risk_analysis(report_normal["return"] - report_normal["bench"])
analysis["excess_return_with_cost"] = risk_analysis(
report_normal["return"] - report_normal["bench"] - report_normal["cost"]
)
analysis_df = pd.concat(analysis) # type: pd.DataFrame
print(analysis_df)