liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-09 22:10:56 +08:00
Code Activity

Format with black

Browse Source
This commit is contained in:
Jactus
2020-11-02 11:09:24 +08:00
parent b077d848f4
commit 661b3bffcc
11 changed files with 157 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
qlib/data/data.py
View File

@@ -1032,12 +1032,12 @@ def register_all_wrappers():
"""register_all_wrappers"""
logger = get_module_logger("data")
module = get_module_by_module_path("qlib.data")
_calendar_provider = init_instance_by_config(C.calendar_provider, module)
if getattr(C, "calendar_cache", None) is not None:
_calendar_cache_config = {}
_calendar_cache_config.update(C.calendar_cache)
_calendar_cache_config['kwargs'].update(provider=_calendar_provider)
_calendar_cache_config["kwargs"].update(provider=_calendar_provider)
_calendar_provider = init_instance_by_config(_calendar_cache_config, module)
register_wrapper(Cal, _calendar_provider, "qlib.data")
logger.debug(f"registering Cal {C.calendar_provider}-{C.calenar_cache}")
@@ -1056,7 +1056,7 @@ def register_all_wrappers():
if getattr(C, "expression_cache", None) is not None:
_expression_cache_config = {}
_expression_cache_config.update(C.expression_cache)
_expression_cache_config['kwargs'].update(provider=_eprovider)
_expression_cache_config["kwargs"].update(provider=_eprovider)
_eprovider = init_instance_by_config(C.expression_cache, module)
register_wrapper(ExpressionD, _eprovider, "qlib.data")
logger.debug(f"registering ExpressioneD {C.expression_provider}-{C.expression_cache}")
@@ -1065,7 +1065,7 @@ def register_all_wrappers():
if getattr(C, "dataset_cache", None) is not None:
_dataset_cache_config = {}
_dataset_cache_config.update(C.dataset_cache)
_dataset_cache_config['kwargs'].update(provider=_dprovider)
_dataset_cache_config["kwargs"].update(provider=_dprovider)
_dprovider = init_instance_by_config(_dataset_cache_config, module)
register_wrapper(DatasetD, _dprovider, "qlib.data")
logger.debug(f"registering DataseteD {C.dataset_provider}-{C.dataset_cache}")

13
qlib/data/dataset/handler.py
View File

@@ -125,7 +125,7 @@ class DataHandler(Serializable):
selector: Union[pd.Timestamp, slice, str],
level: Union[str, int] = "datetime",
col_set: Union[str, List[str]] = CS_ALL,
squeeze: bool = False
squeeze: bool = False,
) -> pd.DataFrame:
"""
fetch data from underlying data source
@@ -184,17 +184,18 @@ class DataHandler(Serializable):
cur_date (pd.Timestamp or str): current date
periods (int): number of periods
"""
trading_dates = self._data.index.unique(level='datetime')
trading_dates = self._data.index.unique(level="datetime")
cur_loc = trading_dates.get_loc(cur_date)
pre_loc = cur_loc - periods + 1
if pre_loc < 0:
warnings.warn('`periods` is too large. the first date will be returned.')
warnings.warn("`periods` is too large. the first date will be returned.")
pre_loc = 0
ref_date = trading_dates[pre_loc]
return slice(ref_date, cur_date)
def get_range_iterator(self, periods: int, min_periods: Optional[int] = None,
**kwargs) -> Iterator[Tuple[pd.Timestamp, pd.DataFrame]]:
def get_range_iterator(
self, periods: int, min_periods: Optional[int] = None, **kwargs
) -> Iterator[Tuple[pd.Timestamp, pd.DataFrame]]:
"""
get a iterator of sliced data with given periods
@@ -203,7 +204,7 @@ class DataHandler(Serializable):
min_periods (int): minimum periods for sliced dataframe
kwargs (dict): will be passed to `self.fetch`
"""
trading_dates = self._data.index.unique(level='datetime')
trading_dates = self._data.index.unique(level="datetime")
if min_periods is None:
min_periods = periods
for cur_date in trading_dates[min_periods:]:

17
qlib/data/dataset/loader.py
View File

@@ -9,10 +9,12 @@ from typing import Tuple
from qlib.data import D
class DataLoader(abc.ABC):
'''
"""
DataLoader is designed for loading raw data from original data source.
'''
"""
@abc.abstractmethod
def load(self, instruments, start_time=None, end_time=None) -> pd.DataFrame:
"""
@@ -47,7 +49,8 @@ class DataLoader(abc.ABC):
class QlibDataLoader(DataLoader):
'''Same as QlibDataLoader. The fields can be define by config'''
"""Same as QlibDataLoader. The fields can be define by config"""
def __init__(self, config: Tuple[list, tuple, dict], filter_pipe=None):
"""
Parameters
@@ -64,7 +67,7 @@ class QlibDataLoader(DataLoader):
<fields_info> := ["expr", ...] | (["expr", ...], ["col_name", ...])
"""
self.is_group = isinstance(config, dict)
self.is_group = isinstance(config, dict)
if self.is_group:
self.fields = {grp: self._parse_fields_info(fields_info) for grp, fields_info in config.items()}
@@ -86,15 +89,17 @@ class QlibDataLoader(DataLoader):
if isinstance(instruments, str):
instruments = D.instruments(instruments, filter_pipe=self.filter_pipe)
elif self.filter_pipe is not None:
warnings.warn('`filter_pipe` is not None, but it will not be used with `instruments` as list')
warnings.warn("`filter_pipe` is not None, but it will not be used with `instruments` as list")
def _get_df(exprs, names):
df = D.features(instruments, exprs, start_time, end_time)
df.columns = names
return df
if self.is_group:
df = pd.concat({grp: _get_df(exprs, names) for grp, (exprs, names) in self.fields.items()}, axis=1)
else:
exprs, names = self.fields
df = _get_df(exprs, names)
df = df.swaplevel().sort_index() # NOTE: always return <datetime, instrument>
df = df.swaplevel().sort_index() # NOTE: always return <datetime, instrument>
return df

2
qlib/data/ops.py
View File

@@ -701,7 +701,7 @@ class Rolling(ExpressionOps):
if self.N == 0:
return np.inf
if 0 < self.N < 1:
return int(np.log(1e-6) / np.log(1 - self.N)) # (1 - N)**window == 1e-6
return int(np.log(1e-6) / np.log(1 - self.N)) # (1 - N)**window == 1e-6
return self.feature.get_longest_back_rolling() + self.N - 1
def get_extended_window_size(self):