liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-16 09:11:00 +08:00
Code Activity

update workflow

Browse Source
This commit is contained in:
bxdd
2021-03-25 19:58:55 +08:00
parent a04c6bd6c9
commit 68246b3b6d
1 changed files with 18 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
examples/rolling_process_data/workflow.py
View File

@@ -2,6 +2,7 @@
# Licensed under the MIT License. # Licensed under the MIT License.
import qlib import qlib
import fire
import pickle import pickle
import pandas as pd import pandas as pd
@@ -12,7 +13,6 @@ from qlib.contrib.data.handler import Alpha158
from qlib.utils import exists_qlib_data, init_instance_by_config from qlib.utils import exists_qlib_data, init_instance_by_config
from qlib.tests.data import GetData from qlib.tests.data import GetData
class RollingDataWorkflow(object): class RollingDataWorkflow(object):
MARKET = "csi300" MARKET = "csi300"
@@ -52,12 +52,12 @@ class RollingDataWorkflow(object):
self._dump_pre_handler("pre_handler.py") self._dump_pre_handler("pre_handler.py")
pre_handler = self._load_pre_handler("pre_handler.py") pre_handler = self._load_pre_handler("pre_handler.py")
train_start_time = (2010, 1, 1) train_start_time = (2010,1,1)
train_end_time = (2012, 12, 31) train_end_time = (2012,12,31)
valid_start_time = (2013, 1, 1) valid_start_time = (2013,1,1)
valid_end_time = (2013, 12, 31) valid_end_time = (2013,12,31)
test_start_time = (2014, 1, 1) test_start_time = (2014,1,1)
test_end_time = (2014, 12, 31) test_end_time = (2014,12,31)
dataset_config = { dataset_config = {
"class": "DatasetH", "class": "DatasetH",
@@ -71,9 +71,9 @@ class RollingDataWorkflow(object):
"end_time": datetime(*test_end_time), "end_time": datetime(*test_end_time),
"fit_start_time": datetime(*train_start_time), "fit_start_time": datetime(*train_start_time),
"fit_end_time": datetime(*train_end_time), "fit_end_time": datetime(*train_end_time),
"data_loader_kwargs": { "data_loader_kwargs":{
"handler_config": pre_handler, "handler_config": pre_handler,
}, }
}, },
}, },
"segments": { "segments": {
@@ -95,65 +95,14 @@ class RollingDataWorkflow(object):
"end_time": datetime(test_end_time[0] + 1, *test_end_time[1:]), "end_time": datetime(test_end_time[0] + 1, *test_end_time[1:]),
}, },
segment_kwargs={ segment_kwargs={
"train": ( "train": (datetime(train_start_time[0] + 1, *train_start_time[1:]), datetime(train_end_time[0], *train_end_time[1:])),
datetime(train_start_time[0] + 1, *train_start_time[1:]), "valid": (datetime(valid_start_time[0] + 1, *valid_start_time[1:]), datetime(valid_end_time[0], *valid_end_time[1:])),
datetime(train_end_time[0], *train_end_time[1:]), "test": (datetime(test_start_time[0] + 1, *test_start_time[1:]), datetime(test_end_time[0], *test_end_time[1:])),
),
"valid": (
datetime(valid_start_time[0] + 1, *valid_start_time[1:]),
datetime(valid_end_time[0], *valid_end_time[1:]),
),
"test": (
datetime(test_start_time[0] + 1, *test_start_time[1:]),
datetime(test_end_time[0], *test_end_time[1:]),
),
}, },
) )
dtrain, dvalid, dtest = dataset.prepare(["train", "valid", "test"]) dtrain, dvalid, dtest = dataset.prepare(["train", "valid", "test"])
if __name__ == "__main__": if __name__ == "__main__":
fire.Fire(RollingDataWorkflow)
# 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}")
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,
}
task = {
"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"),
},
},
},
}
dataset = init_instance_by_config(task["dataset"])