liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-14 00:06:58 +08:00
Code Activity

update format

Browse Source
This commit is contained in:
Alex Wang
2021-03-22 15:37:54 +08:00
parent 1ad237f89f
commit 3bf6c7f95f
2 changed files with 24 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
qlib/contrib/eva/alpha.py
View File

@@ -7,8 +7,11 @@ import pandas as pd
from typing import Tuple from typing import Tuple
def calc_prec(pred: pd.Series, label: pd.Series, date_col="datetime", quantile: float = 0.2, dropna=False, is_alpha=False) -> Tuple[pd.Series, pd.Series]:
""" calculate the precision def calc_prec(
pred: pd.Series, label: pd.Series, date_col="datetime", quantile: float = 0.2, dropna=False, is_alpha=False
) -> Tuple[pd.Series, pd.Series]:
"""calculate the precision
pred : pred :
pred pred
label : label :
@@ -23,13 +26,12 @@ def calc_prec(pred: pd.Series, label: pd.Series, date_col="datetime", quantile:
""" """
if is_alpha: if is_alpha:
label = label - label.mean(level=0) label = label - label.mean(level=0)
if int(1/quantile) >= len(label.index.get_level_values(1).unique()): if int(1 / quantile) >= len(label.index.get_level_values(1).unique()):
raise ValueError("Need more instruments to calculate precision") raise ValueError("Need more instruments to calculate precision")
df = pd.DataFrame({"pred": pred, "label": label}) df = pd.DataFrame({"pred": pred, "label": label})
if dropna: if dropna:
df.dropna(inplace = True) df.dropna(inplace=True)
group = df.groupby(level=date_col) group = df.groupby(level=date_col)
@@ -45,7 +47,7 @@ def calc_prec(pred: pd.Series, label: pd.Series, date_col="datetime", quantile:
groups = short.groupby(date_col) groups = short.groupby(date_col)
s_ration = groups.apply(lambda x: x < 0) s_ration = groups.apply(lambda x: x < 0)
s_c = groups.count() s_c = groups.count()
return (ll_ration.groupby(date_col).sum()/ll_c), (s_ration.groupby(date_col).sum()/s_c) return (ll_ration.groupby(date_col).sum() / ll_c), (s_ration.groupby(date_col).sum() / s_c)
def calc_ic(pred: pd.Series, label: pd.Series, date_col="datetime", dropna=False) -> Tuple[pd.Series, pd.Series]: def calc_ic(pred: pd.Series, label: pd.Series, date_col="datetime", dropna=False) -> Tuple[pd.Series, pd.Series]:

12
qlib/workflow/record_temp.py
View File

@@ -160,6 +160,7 @@ class HFSignalRecord(SignalRecord):
""" """
This is the Signal Analysis Record class that generates the analysis results such as IC and IR. This class inherits the ``RecordTemp`` class. This is the Signal Analysis Record class that generates the analysis results such as IC and IR. This class inherits the ``RecordTemp`` class.
""" """
artifact_path = "hg_sig_analysis" artifact_path = "hg_sig_analysis"
def __init__(self, recorder, **kwargs): def __init__(self, recorder, **kwargs):
@@ -169,7 +170,7 @@ class HFSignalRecord(SignalRecord):
pred = self.load("pred.pkl") pred = self.load("pred.pkl")
raw_label = self.load("label.pkl") raw_label = self.load("label.pkl")
long_pre, short_pre = calc_prec(pred.iloc[:, 0], raw_label.iloc[:, 0], is_alpha = True) long_pre, short_pre = calc_prec(pred.iloc[:, 0], raw_label.iloc[:, 0], is_alpha=True)
ic, ric = calc_ic(pred.iloc[:, 0], raw_label.iloc[:, 0]) ic, ric = calc_ic(pred.iloc[:, 0], raw_label.iloc[:, 0])
metrics = { metrics = {
"IC": ic.mean(), "IC": ic.mean(),
@@ -177,7 +178,7 @@ class HFSignalRecord(SignalRecord):
"Rank IC": ric.mean(), "Rank IC": ric.mean(),
"Rank ICIR": ric.mean() / ric.std(), "Rank ICIR": ric.mean() / ric.std(),
"Long precision": long_pre.mean(), "Long precision": long_pre.mean(),
"Short precision": short_pre.mean() "Short precision": short_pre.mean(),
} }
objects = {"ic.pkl": ic, "ric.pkl": ric} objects = {"ic.pkl": ic, "ric.pkl": ric}
objects.update({"long_pre.pkl": long_pre, "short_pre.pkl": short_pre}) objects.update({"long_pre.pkl": long_pre, "short_pre.pkl": short_pre})
@@ -199,7 +200,12 @@ class HFSignalRecord(SignalRecord):
pprint(metrics) pprint(metrics)
def list(self): def list(self):
paths = [self.get_path("ic.pkl"), self.get_path("ric.pkl"), self.get_path("long_pre.pkl"), self.get_path("short_pre.pkl")] paths = [
self.get_path("ic.pkl"),
self.get_path("ric.pkl"),
self.get_path("long_pre.pkl"),
self.get_path("short_pre.pkl"),
]
paths.extend([self.get_path("long_short_r.pkl"), self.get_path("long_avg_r.pkl")]) paths.extend([self.get_path("long_short_r.pkl"), self.get_path("long_avg_r.pkl")])
return paths return paths