1
0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-09 14:00:55 +08:00

modify the default value of exists_skip in the GetData.qlib_data parameter to False

This commit is contained in:
zhupr
2021-05-28 14:57:06 +08:00
parent 98eacf8f88
commit ef11a9d95c
10 changed files with 17 additions and 10 deletions

View File

@@ -85,7 +85,7 @@ class HighfreqWorkflow:
# use yahoo_cn_1min data
QLIB_INIT_CONFIG = {**HIGH_FREQ_CONFIG, **self.SPEC_CONF}
provider_uri = QLIB_INIT_CONFIG.get("provider_uri")
GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, interval="1min", region=REG_CN, exists_skip=True)
qlib.init(**QLIB_INIT_CONFIG)
def _prepare_calender_cache(self):

View File

@@ -37,7 +37,7 @@ def objective(trial):
if __name__ == "__main__":
provider_uri = "~/.qlib/qlib_data/cn_data"
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region="cn")
dataset = init_instance_by_config(CSI300_DATASET_CONFIG)

View File

@@ -40,7 +40,7 @@ def objective(trial):
if __name__ == "__main__":
provider_uri = "~/.qlib/qlib_data/cn_data"
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
dataset = init_instance_by_config(DATASET_CONFIG)

View File

@@ -14,7 +14,7 @@ if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)

View File

@@ -23,7 +23,7 @@ class RollingDataWorkflow:
"""initialize qlib"""
# use yahoo_cn_1min data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
def _dump_pre_handler(self, path):

View File

@@ -37,7 +37,7 @@ exp_manager = {
},
}
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN, exp_manager=exp_manager)
# decorator to check the arguments

View File

@@ -14,7 +14,7 @@ if __name__ == "__main__":
# use default data
provider_uri = "~/.qlib/qlib_data/cn_data" # target_dir
GetData().qlib_data(target_dir=provider_uri, region=REG_CN)
GetData().qlib_data(target_dir=provider_uri, region=REG_CN, exists_skip=True)
qlib.init(provider_uri=provider_uri, region=REG_CN)
port_analysis_config = {

View File

@@ -19,5 +19,6 @@ class TestAutoData(unittest.TestCase):
interval="1d",
target_dir=cls.provider_uri,
delete_old=False,
exists_skip=True,
)
init(provider_uri=cls.provider_uri, region=REG_CN, **cls._setup_kwargs)

View File

@@ -113,7 +113,7 @@ class GetData:
interval="1d",
region="cn",
delete_old=True,
exists_skip=True,
exists_skip=False,
):
"""download cn qlib data from remote
@@ -132,7 +132,7 @@ class GetData:
delete_old: bool
delete an existing directory, by default True
exists_skip: bool
exists skip, by default True
exists skip, by default False
Examples
---------
@@ -145,6 +145,10 @@ class GetData:
"""
if exists_skip and exists_qlib_data(target_dir):
logger.warning(
f"Data already exists: {target_dir}, the data download will be skipped\n"
f"\tIf downloading is required: `exists_skip=False` or `change target_dir`"
)
return
qlib_version = ".".join(re.findall(r"(\d+)\.+", qlib.__version__))

View File

@@ -34,7 +34,9 @@ class TestGetData(unittest.TestCase):
def test_0_qlib_data(self):
GetData().qlib_data(name="qlib_data_simple", target_dir=QLIB_DIR, region="cn", interval="1d", delete_old=False)
GetData().qlib_data(
name="qlib_data_simple", target_dir=QLIB_DIR, region="cn", interval="1d", delete_old=False, exists_skip=True
)
df = D.features(D.instruments("csi300"), self.FIELDS)
self.assertListEqual(list(df.columns), self.FIELDS, "get qlib data failed")
self.assertFalse(df.dropna().empty, "get qlib data failed")