liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-10 06:20:57 +08:00
Code Activity

fix some small bug

Browse Source
This commit is contained in:
Young
2020-11-14 08:23:19 +00:00
parent ea5f14ce12
commit 7a79028a72
6 changed files with 40 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
qlib/data/data.py
View File

@@ -664,9 +664,11 @@ class LocalExpressionProvider(ExpressionProvider):
lft_etd, rght_etd = expression.get_extended_window_size()
series = expression.load(instrument, max(0, start_index - lft_etd), end_index + rght_etd, freq)
# Ensure that each column type is consistent
# FIXME: The stock data is currently float. If there is other types of data, this part needs to be re-implemented.
# FIXME:
# 1) The stock data is currently float. If there is other types of data, this part needs to be re-implemented.
# 2) The the precision should be configurable
try:
series = series.astype(float)
series = series.astype(np.float32)
except ValueError:
pass
if not series.empty:

9
qlib/data/dataset/handler.py
View File

@@ -99,10 +99,11 @@ class DataHandler(Serializable):
self._data = self.data_loader.load(self.instruments, self.start_time, self.end_time)
# TODO: cache
CS_ALL = "__all"
CS_ALL = "__all" # return all columns with single-level index column
CS_RAW = "__raw" # return raw data with multi-level index column
def _fetch_df_by_col(self, df: pd.DataFrame, col_set: str) -> pd.DataFrame:
if not isinstance(df.columns, pd.MultiIndex):
if not isinstance(df.columns, pd.MultiIndex) or col_set == self.CS_RAW:
return df
elif col_set == self.CS_ALL:
return df.droplevel(axis=1, level=0)
@@ -111,7 +112,7 @@ class DataHandler(Serializable):
def fetch(
self,
selector: Union[pd.Timestamp, slice, str],
selector: Union[pd.Timestamp, slice, str] = slice(None, None),
level: Union[str, int] = "datetime",
col_set: Union[str, List[str]] = CS_ALL,
squeeze: bool = False,
@@ -371,7 +372,7 @@ class DataHandlerLP(DataHandler):
def fetch(
self,
selector: Union[pd.Timestamp, slice, str],
selector: Union[pd.Timestamp, slice, str] = slice(None, None),
level: Union[str, int] = "datetime",
col_set=DataHandler.CS_ALL,
data_key: str = DK_I,

2
qlib/data/dataset/utils.py
View File

@@ -52,4 +52,4 @@ def fetch_df_by_index(
idx_slc = (selector, slice(None, None))
if get_level_index(df, level) == 1:
idx_slc = idx_slc[1], idx_slc[0]
return df.loc(axis=0)[idx_slc]
return df.loc[pd.IndexSlice[idx_slc], ] # This could be faster than df.loc(axis=0)[idx_slc]