liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-06-06 05:51:17 +08:00
Code Activity

Bug fix for Rank and WMA operators (#1228)

Browse Source 
* bug fix: 1) 100 should be used to scale down percentileofscore return to 0-1, not length of array; 2) for (linear) weighted MA(n), weight should be n, n-1, ..., 1 instead of n-1, ..., 0

* use native pandas fucntion for rank

* remove useless import

* require pandas 1.4+

* rank for py37+pandas 1.3.5 compatibility

* lint improvement

* lint black fix

* use hasattr instead of version to check whether rolling.rank is implemented
This commit is contained in:
qianyun210603
2022-11-13 19:03:23 +08:00
committed by GitHub
parent ff2154c618
commit 4001a5d157
1 changed files with 9 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
qlib/data/ops.py
View File

@@ -34,8 +34,6 @@ np.seterr(invalid="ignore")
#################### Element-Wise Operator #################### #################### Element-Wise Operator ####################
class ElemOperator(ExpressionOps): class ElemOperator(ExpressionOps):
"""Element-wise Operator """Element-wise Operator
@@ -216,9 +214,7 @@ class Not(NpElemOperator):
Parameters Parameters
---------- ----------
feature_left : Expression feature : Expression
feature instance
feature_right : Expression
feature instance feature instance
Returns Returns
@@ -241,8 +237,6 @@ class PairOperator(ExpressionOps):
feature instance or numeric value feature instance or numeric value
feature_right : Expression feature_right : Expression
feature instance or numeric value feature instance or numeric value
func : str
operator function
Returns Returns
---------- ----------
@@ -1155,9 +1149,13 @@ class Rank(Rolling):
def __init__(self, feature, N): def __init__(self, feature, N):
super(Rank, self).__init__(feature, N, "rank") super(Rank, self).__init__(feature, N, "rank")
# for compatiblity of python 3.7, which doesn't support pandas 1.4.0+ which implements Rolling.rank
def _load_internal(self, instrument, start_index, end_index, *args): def _load_internal(self, instrument, start_index, end_index, *args):
series = self.feature.load(instrument, start_index, end_index, *args) series = self.feature.load(instrument, start_index, end_index, *args)
# TODO: implement in Cython
rolling_or_expending = series.expanding(min_periods=1) if self.N == 0 else series.rolling(self.N, min_periods=1)
if hasattr(rolling_or_expending, "rank"):
return rolling_or_expending.rank(pct=True)
def rank(x): def rank(x):
if np.isnan(x[-1]): if np.isnan(x[-1]):
@@ -1165,13 +1163,9 @@ class Rank(Rolling):
x1 = x[~np.isnan(x)] x1 = x[~np.isnan(x)]
if x1.shape[0] == 0: if x1.shape[0] == 0:
return np.nan return np.nan
return percentileofscore(x1, x1[-1]) / len(x1) return percentileofscore(x1, x1[-1]) / 100
if self.N == 0: return rolling_or_expending.apply(rank, raw=True)
series = series.expanding(min_periods=1).apply(rank, raw=True)
else:
series = series.rolling(self.N, min_periods=1).apply(rank, raw=True)
return series
class Count(Rolling): class Count(Rolling):
@@ -1341,7 +1335,7 @@ class WMA(Rolling):
# TODO: implement in Cython # TODO: implement in Cython
def weighted_mean(x): def weighted_mean(x):
w = np.arange(len(x)) w = np.arange(len(x)) + 1
w = w / w.sum() w = w / w.sum()
return np.nanmean(w * x) return np.nanmean(w * x)