1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-06-06 05:51:17 +08:00
Files
qlib/examples/workflow_by_code.py
2020-11-16 15:49:50 +08:00

133 lines
3.8 KiB
Python

# 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.gbdt import LGBModel
from qlib.contrib.data.handler import Alpha158
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, init_instance_by_config
from qlib.workflow import R
from qlib.workflow.record_temp import SignalRecord, PortAnaRecord
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_cn(target_dir=provider_uri)
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": "LGBModel",
"module_path": "qlib.contrib.model.gbdt",
"kwargs": {
"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,
},
},
"dataset": {
"class": "DatasetH",
"module_path": "qlib.data.dataset",
"kwargs": {
"handler": {
"class": "Alpha158",
"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", "PortAnaRecord"],
}
port_analysis_config = {
"strategy": {
"topk": 50,
"n_drop": 5,
},
"backtest": {
"verbose": False,
"limit_threshold": 0.095,
"account": 100000000,
"benchmark": BENCHMARK,
"deal_price": "close",
"open_cost": 0.0005,
"close_cost": 0.0015,
"min_cost": 5,
},
}
# model initiaiton
model = init_instance_by_config(task["model"])
dataset = init_instance_by_config(task["dataset"])
# start exp
with R.start("workflow"):
model.fit(dataset)
# prediction
recorder = R.get_recorder()
sr = SignalRecord(model, dataset, recorder)
sr.generate()
# backtest
par = PortAnaRecord(recorder, port_analysis_config)
par.generate()