mirror of
https://github.com/microsoft/qlib.git
synced 2026-07-07 04:50:56 +08:00
adjust data and model interface
This commit is contained in:
Young
@@ -25,10 +25,12 @@ class ALPHA360(DataHandlerLP):
|
||||
},
|
||||
"label": self.get_label_config()
|
||||
},
|
||||
"group_fields": True,
|
||||
}
|
||||
}
|
||||
infer_processors = ["ConfigSectionProcessor"] # ConfigSectionProcessor will normalize LABEL0
|
||||
infer_processors = [{
|
||||
"class": "ConfigSectionProcessor",
|
||||
"module_path": "qlib.contrib.data.processor"
|
||||
}] # ConfigSectionProcessor will normalize LABEL0
|
||||
super().__init__(instruments, start_time, end_time, data_loader=data_loader, infer_processors=infer_processors)
|
||||
|
||||
def get_label_config(self):
|
||||
@@ -83,7 +85,6 @@ class Alpha158(DataHandlerLP):
|
||||
"feature": self.get_feature_config(),
|
||||
"label": self.get_label_config()
|
||||
},
|
||||
"group_fields": True,
|
||||
}
|
||||
}
|
||||
super().__init__(instruments,
|
||||
@@ -94,7 +95,7 @@ class Alpha158(DataHandlerLP):
|
||||
learn_processors=learn_processors)
|
||||
|
||||
def get_feature_config(self):
|
||||
return {
|
||||
conf = {
|
||||
"kbar": {},
|
||||
"price": {
|
||||
"windows": [0],
|
||||
@@ -102,10 +103,186 @@ class Alpha158(DataHandlerLP):
|
||||
},
|
||||
"rolling": {},
|
||||
}
|
||||
return self.parse_config_to_fields(conf)
|
||||
|
||||
def get_label_config(self):
|
||||
return (["Ref($close, -2)/Ref($close, -1) - 1"], ["LABEL0"])
|
||||
|
||||
@staticmethod
|
||||
def parse_config_to_fields(config):
|
||||
"""create factors from config
|
||||
|
||||
config = {
|
||||
'kbar': {}, # whether to use some hard-code kbar features
|
||||
'price': { # whether to use raw price features
|
||||
'windows': [0, 1, 2, 3, 4], # use price at n days ago
|
||||
'feature': ['OPEN', 'HIGH', 'LOW'] # which price field to use
|
||||
},
|
||||
'volume': { # whether to use raw volume features
|
||||
'windows': [0, 1, 2, 3, 4], # use volume at n days ago
|
||||
},
|
||||
'rolling': { # whether to use rolling operator based features
|
||||
'windows': [5, 10, 20, 30, 60], # rolling windows size
|
||||
'include': ['ROC', 'MA', 'STD'], # rolling operator to use
|
||||
#if include is None we will use default operators
|
||||
'exclude': ['RANK'], # rolling operator not to use
|
||||
}
|
||||
}
|
||||
"""
|
||||
fields = []
|
||||
names = []
|
||||
if "kbar" in config:
|
||||
fields += [
|
||||
"($close-$open)/$open",
|
||||
"($high-$low)/$open",
|
||||
"($close-$open)/($high-$low+1e-12)",
|
||||
"($high-Greater($open, $close))/$open",
|
||||
"($high-Greater($open, $close))/($high-$low+1e-12)",
|
||||
"(Less($open, $close)-$low)/$open",
|
||||
"(Less($open, $close)-$low)/($high-$low+1e-12)",
|
||||
"(2*$close-$high-$low)/$open",
|
||||
"(2*$close-$high-$low)/($high-$low+1e-12)",
|
||||
]
|
||||
names += [
|
||||
"KMID",
|
||||
"KLEN",
|
||||
"KMID2",
|
||||
"KUP",
|
||||
"KUP2",
|
||||
"KLOW",
|
||||
"KLOW2",
|
||||
"KSFT",
|
||||
"KSFT2",
|
||||
]
|
||||
if "price" in config:
|
||||
windows = config["price"].get("windows", range(5))
|
||||
feature = config["price"].get("feature", ["OPEN", "HIGH", "LOW", "CLOSE", "VWAP"])
|
||||
for field in feature:
|
||||
field = field.lower()
|
||||
fields += ["Ref($%s, %d)/$close" % (field, d) if d != 0 else "$%s/$close" % field for d in windows]
|
||||
names += [field.upper() + str(d) for d in windows]
|
||||
if "volume" in config:
|
||||
windows = config["volume"].get("windows", range(5))
|
||||
fields += ["Ref($volume, %d)/$volume" % d if d != 0 else "$volume/$volume" for d in windows]
|
||||
names += ["VOLUME" + str(d) for d in windows]
|
||||
if "rolling" in config:
|
||||
windows = config["rolling"].get("windows", [5, 10, 20, 30, 60])
|
||||
include = config["rolling"].get("include", None)
|
||||
exclude = config["rolling"].get("exclude", [])
|
||||
# `exclude` in dataset config unnecessary filed
|
||||
# `include` in dataset config necessary field
|
||||
use = lambda x: x not in exclude and (include is None or x in include)
|
||||
if use("ROC"):
|
||||
fields += ["Ref($close, %d)/$close" % d for d in windows]
|
||||
names += ["ROC%d" % d for d in windows]
|
||||
if use("MA"):
|
||||
fields += ["Mean($close, %d)/$close" % d for d in windows]
|
||||
names += ["MA%d" % d for d in windows]
|
||||
if use("STD"):
|
||||
fields += ["Std($close, %d)/$close" % d for d in windows]
|
||||
names += ["STD%d" % d for d in windows]
|
||||
if use("BETA"):
|
||||
fields += ["Slope($close, %d)/$close" % d for d in windows]
|
||||
names += ["BETA%d" % d for d in windows]
|
||||
if use("RSQR"):
|
||||
fields += ["Rsquare($close, %d)" % d for d in windows]
|
||||
names += ["RSQR%d" % d for d in windows]
|
||||
if use("RESI"):
|
||||
fields += ["Resi($close, %d)/$close" % d for d in windows]
|
||||
names += ["RESI%d" % d for d in windows]
|
||||
if use("MAX"):
|
||||
fields += ["Max($high, %d)/$close" % d for d in windows]
|
||||
names += ["MAX%d" % d for d in windows]
|
||||
if use("LOW"):
|
||||
fields += ["Min($low, %d)/$close" % d for d in windows]
|
||||
names += ["MIN%d" % d for d in windows]
|
||||
if use("QTLU"):
|
||||
fields += ["Quantile($close, %d, 0.8)/$close" % d for d in windows]
|
||||
names += ["QTLU%d" % d for d in windows]
|
||||
if use("QTLD"):
|
||||
fields += ["Quantile($close, %d, 0.2)/$close" % d for d in windows]
|
||||
names += ["QTLD%d" % d for d in windows]
|
||||
if use("RANK"):
|
||||
fields += ["Rank($close, %d)" % d for d in windows]
|
||||
names += ["RANK%d" % d for d in windows]
|
||||
if use("RSV"):
|
||||
fields += ["($close-Min($low, %d))/(Max($high, %d)-Min($low, %d)+1e-12)" % (d, d, d) for d in windows]
|
||||
names += ["RSV%d" % d for d in windows]
|
||||
if use("IMAX"):
|
||||
fields += ["IdxMax($high, %d)/%d" % (d, d) for d in windows]
|
||||
names += ["IMAX%d" % d for d in windows]
|
||||
if use("IMIN"):
|
||||
fields += ["IdxMin($low, %d)/%d" % (d, d) for d in windows]
|
||||
names += ["IMIN%d" % d for d in windows]
|
||||
if use("IMXD"):
|
||||
fields += ["(IdxMax($high, %d)-IdxMin($low, %d))/%d" % (d, d, d) for d in windows]
|
||||
names += ["IMXD%d" % d for d in windows]
|
||||
if use("CORR"):
|
||||
fields += ["Corr($close, Log($volume+1), %d)" % d for d in windows]
|
||||
names += ["CORR%d" % d for d in windows]
|
||||
if use("CORD"):
|
||||
fields += ["Corr($close/Ref($close,1), Log($volume/Ref($volume, 1)+1), %d)" % d for d in windows]
|
||||
names += ["CORD%d" % d for d in windows]
|
||||
if use("CNTP"):
|
||||
fields += ["Mean($close>Ref($close, 1), %d)" % d for d in windows]
|
||||
names += ["CNTP%d" % d for d in windows]
|
||||
if use("CNTN"):
|
||||
fields += ["Mean($close<Ref($close, 1), %d)" % d for d in windows]
|
||||
names += ["CNTN%d" % d for d in windows]
|
||||
if use("CNTD"):
|
||||
fields += ["Mean($close>Ref($close, 1), %d)-Mean($close<Ref($close, 1), %d)" % (d, d) for d in windows]
|
||||
names += ["CNTD%d" % d for d in windows]
|
||||
if use("SUMP"):
|
||||
fields += [
|
||||
"Sum(Greater($close-Ref($close, 1), 0), %d)/(Sum(Abs($close-Ref($close, 1)), %d)+1e-12)" % (d, d)
|
||||
for d in windows
|
||||
]
|
||||
names += ["SUMP%d" % d for d in windows]
|
||||
if use("SUMN"):
|
||||
fields += [
|
||||
"Sum(Greater(Ref($close, 1)-$close, 0), %d)/(Sum(Abs($close-Ref($close, 1)), %d)+1e-12)" % (d, d)
|
||||
for d in windows
|
||||
]
|
||||
names += ["SUMN%d" % d for d in windows]
|
||||
if use("SUMD"):
|
||||
fields += [
|
||||
"(Sum(Greater($close-Ref($close, 1), 0), %d)-Sum(Greater(Ref($close, 1)-$close, 0), %d))"
|
||||
"/(Sum(Abs($close-Ref($close, 1)), %d)+1e-12)" % (d, d, d) for d in windows
|
||||
]
|
||||
names += ["SUMD%d" % d for d in windows]
|
||||
if use("VMA"):
|
||||
fields += ["Mean($volume, %d)/($volume+1e-12)" % d for d in windows]
|
||||
names += ["VMA%d" % d for d in windows]
|
||||
if use("VSTD"):
|
||||
fields += ["Std($volume, %d)/($volume+1e-12)" % d for d in windows]
|
||||
names += ["VSTD%d" % d for d in windows]
|
||||
if use("WVMA"):
|
||||
fields += [
|
||||
"Std(Abs($close/Ref($close, 1)-1)*$volume, %d)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, %d)+1e-12)" %
|
||||
(d, d) for d in windows
|
||||
]
|
||||
names += ["WVMA%d" % d for d in windows]
|
||||
if use("VSUMP"):
|
||||
fields += [
|
||||
"Sum(Greater($volume-Ref($volume, 1), 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d)
|
||||
for d in windows
|
||||
]
|
||||
names += ["VSUMP%d" % d for d in windows]
|
||||
if use("VSUMN"):
|
||||
fields += [
|
||||
"Sum(Greater(Ref($volume, 1)-$volume, 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d)
|
||||
for d in windows
|
||||
]
|
||||
names += ["VSUMN%d" % d for d in windows]
|
||||
if use("VSUMD"):
|
||||
fields += [
|
||||
"(Sum(Greater($volume-Ref($volume, 1), 0), %d)-Sum(Greater(Ref($volume, 1)-$volume, 0), %d))"
|
||||
"/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)" % (d, d, d) for d in windows
|
||||
]
|
||||
names += ["VSUMD%d" % d for d in windows]
|
||||
|
||||
return fields, names
|
||||
|
||||
|
||||
class Alpha158vwap(Alpha158):
|
||||
def get_label_config(self):
|
||||
|
||||
117
qlib/contrib/data/processor.py
Normal file
117
qlib/contrib/data/processor.py
Normal file
@@ -0,0 +1,117 @@
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import copy
|
||||
|
||||
from ...log import TimeInspector
|
||||
from ...utils.serial import Serializable
|
||||
from ...data.dataset.processor import Processor, get_group_columns
|
||||
|
||||
|
||||
class ConfigSectionProcessor(Processor):
|
||||
'''
|
||||
This processor is designed for Alpha158. And will be replaced by simple processors in the future
|
||||
'''
|
||||
def __init__(self, fields_group=None, **kwargs):
|
||||
super().__init__()
|
||||
# Options
|
||||
self.fillna_feature = kwargs.get("fillna_feature", True)
|
||||
self.fillna_label = kwargs.get("fillna_label", True)
|
||||
self.clip_feature_outlier = kwargs.get("clip_feature_outlier", False)
|
||||
self.shrink_feature_outlier = kwargs.get("shrink_feature_outlier", True)
|
||||
self.clip_label_outlier = kwargs.get("clip_label_outlier", False)
|
||||
|
||||
self.fields_group = None
|
||||
|
||||
def __call__(self, df):
|
||||
return self._transform(df)
|
||||
|
||||
def _transform(self, df):
|
||||
def _label_norm(x):
|
||||
x = x - x.mean() # copy
|
||||
x /= x.std()
|
||||
if self.clip_label_outlier:
|
||||
x.clip(-3, 3, inplace=True)
|
||||
if self.fillna_label:
|
||||
x.fillna(0, inplace=True)
|
||||
return x
|
||||
|
||||
def _feature_norm(x):
|
||||
x = x - x.median() # copy
|
||||
x /= x.abs().median() * 1.4826
|
||||
if self.clip_feature_outlier:
|
||||
x.clip(-3, 3, inplace=True)
|
||||
if self.shrink_feature_outlier:
|
||||
x.where(x <= 3, 3 + (x - 3).div(x.max() - 3) * 0.5, inplace=True)
|
||||
x.where(x >= -3, -3 - (x + 3).div(x.min() + 3) * 0.5, inplace=True)
|
||||
if self.fillna_feature:
|
||||
x.fillna(0, inplace=True)
|
||||
return x
|
||||
|
||||
TimeInspector.set_time_mark()
|
||||
|
||||
# Copy the focus part and change it to single level
|
||||
selected_cols = get_group_columns(df, self.fields_group)
|
||||
df_focus = df[selected_cols].copy()
|
||||
if len(df_focus.columns.levels) > 1:
|
||||
df_focus = df_focus.droplevel(level=0)
|
||||
|
||||
# Label
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^LABEL")]
|
||||
df_focus[cols] = df_focus[cols].groupby(level="datetime").apply(_label_norm)
|
||||
|
||||
# Features
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^KLEN|^KLOW|^KUP")]
|
||||
df_focus[cols] = df_focus[cols].apply(lambda x: x ** 0.25).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^KLOW2|^KUP2")]
|
||||
df_focus[cols] = df_focus[cols].apply(lambda x: x ** 0.5).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
_cols = [
|
||||
"KMID",
|
||||
"KSFT",
|
||||
"OPEN",
|
||||
"HIGH",
|
||||
"LOW",
|
||||
"CLOSE",
|
||||
"VWAP",
|
||||
"ROC",
|
||||
"MA",
|
||||
"BETA",
|
||||
"RESI",
|
||||
"QTLU",
|
||||
"QTLD",
|
||||
"RSV",
|
||||
"SUMP",
|
||||
"SUMN",
|
||||
"SUMD",
|
||||
"VSUMP",
|
||||
"VSUMN",
|
||||
"VSUMD",
|
||||
]
|
||||
pat = "|".join(["^" + x for x in _cols])
|
||||
cols = df_focus.columns[df_focus.columns.str.contains(pat) & (~df_focus.columns.isin(["HIGH0", "LOW0"]))]
|
||||
df_focus[cols] = df_focus[cols].groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^STD|^VOLUME|^VMA|^VSTD")]
|
||||
df_focus[cols] = df_focus[cols].apply(np.log).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^RSQR")]
|
||||
df_focus[cols] = df_focus[cols].fillna(0).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^MAX|^HIGH0")]
|
||||
df_focus[cols] = df_focus[cols].apply(lambda x: (x - 1) ** 0.5).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^MIN|^LOW0")]
|
||||
df_focus[cols] = df_focus[cols].apply(lambda x: (1 - x) ** 0.5).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^CORR|^CORD")]
|
||||
df_focus[cols] = df_focus[cols].apply(np.exp).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
cols = df_focus.columns[df_focus.columns.str.contains("^WVMA")]
|
||||
df_focus[cols] = df_focus[cols].apply(np.log1p).groupby(level="datetime").apply(_feature_norm)
|
||||
|
||||
df[selected_cols] = df_focus.values
|
||||
|
||||
TimeInspector.log_cost_time("Finished preprocessing data.")
|
||||
|
||||
return df
|
||||
Reference in New Issue
Block a user