liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-10 22:36:55 +08:00
Code Activity

Qlib data doc (#1207)

Browse Source 
* Explain data crawler structure

* Add documentation for data and feature

* Update scripts/data_collector/yahoo/README.md

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>

* Remove some confusing wording

* Add third party data source

* Fix command typo

* Update commands

Co-authored-by: you-n-g <you-n-g@users.noreply.github.com>
This commit is contained in:
Di
2022-07-22 09:24:58 +08:00
committed by GitHub
parent 8199822ca0
commit 86f08e47e8
5 changed files with 97 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
qlib/contrib/data/handler.py
View File

@@ -259,79 +259,119 @@ class Alpha158(DataHandlerLP):
def use(x):
return x not in exclude and (include is None or x in include)
# Some factor ref: https://guorn.com/static/upload/file/3/134065454575605.pdf
if use("ROC"):
# https://www.investopedia.com/terms/r/rateofchange.asp
# Rate of change, the price change in the past d days, divided by latest close price to remove unit
fields += ["Ref($close, %d)/$close" % d for d in windows]
names += ["ROC%d" % d for d in windows]
if use("MA"):
# https://www.investopedia.com/ask/answers/071414/whats-difference-between-moving-average-and-weighted-moving-average.asp
# Simple Moving Average, the simple moving average in the past d days, divided by latest close price to remove unit
fields += ["Mean($close, %d)/$close" % d for d in windows]
names += ["MA%d" % d for d in windows]
if use("STD"):
# The standard diviation of close price for the past d days, divided by latest close price to remove unit
fields += ["Std($close, %d)/$close" % d for d in windows]
names += ["STD%d" % d for d in windows]
if use("BETA"):
# The rate of close price change in the past d days, divided by latest close price to remove unit
# For example, price increase 10 dollar per day in the past d days, then Slope will be 10.
fields += ["Slope($close, %d)/$close" % d for d in windows]
names += ["BETA%d" % d for d in windows]
if use("RSQR"):
# The R-sqaure value of linear regression for the past d days, represent the trend linearity for past d days.
fields += ["Rsquare($close, %d)" % d for d in windows]
names += ["RSQR%d" % d for d in windows]
if use("RESI"):
# The redisdual for linear regression for the past d days, represent the trend linearity for past d days.
fields += ["Resi($close, %d)/$close" % d for d in windows]
names += ["RESI%d" % d for d in windows]
if use("MAX"):
# The max price for past d days, divided by latest close price to remove unit
fields += ["Max($high, %d)/$close" % d for d in windows]
names += ["MAX%d" % d for d in windows]
if use("LOW"):
# The low price for past d days, divided by latest close price to remove unit
fields += ["Min($low, %d)/$close" % d for d in windows]
names += ["MIN%d" % d for d in windows]
if use("QTLU"):
# The 80% quantile of past d day's close price, divided by latest close price to remove unit
# Used with MIN and MAX
fields += ["Quantile($close, %d, 0.8)/$close" % d for d in windows]
names += ["QTLU%d" % d for d in windows]
if use("QTLD"):
# The 20% quantile of past d day's close price, divided by latest close price to remove unit
fields += ["Quantile($close, %d, 0.2)/$close" % d for d in windows]
names += ["QTLD%d" % d for d in windows]
if use("RANK"):
# Get the percentile of current close price in past d day's close price.
# Represent the current price level comparing to past N days, add additional information to moving average.
fields += ["Rank($close, %d)" % d for d in windows]
names += ["RANK%d" % d for d in windows]
if use("RSV"):
# Represent the price position between upper and lower resistent price for past d days.
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"):
# The number of days between current date and previous highest price date.
# Part of Aroon Indicator https://www.investopedia.com/terms/a/aroon.asp
# The indicator measures the time between highs and the time between lows over a time period.
# The idea is that strong uptrends will regularly see new highs, and strong downtrends will regularly see new lows.
fields += ["IdxMax($high, %d)/%d" % (d, d) for d in windows]
names += ["IMAX%d" % d for d in windows]
if use("IMIN"):
# The number of days between current date and previous lowest price date.
# Part of Aroon Indicator https://www.investopedia.com/terms/a/aroon.asp
# The indicator measures the time between highs and the time between lows over a time period.
# The idea is that strong uptrends will regularly see new highs, and strong downtrends will regularly see new lows.
fields += ["IdxMin($low, %d)/%d" % (d, d) for d in windows]
names += ["IMIN%d" % d for d in windows]
if use("IMXD"):
# The time period between previous lowest-price date occur after highest price date.
# Large value suggest downward momemtum.
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"):
# The correlation between absolute close price and log scaled trading volume
fields += ["Corr($close, Log($volume+1), %d)" % d for d in windows]
names += ["CORR%d" % d for d in windows]
if use("CORD"):
# The correlation between price change ratio and volume change ratio
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"):
# The percentage of days in past d days that price go up.
fields += ["Mean($close>Ref($close, 1), %d)" % d for d in windows]
names += ["CNTP%d" % d for d in windows]
if use("CNTN"):
# The percentage of days in past d days that price go down.
fields += ["Mean($close<Ref($close, 1), %d)" % d for d in windows]
names += ["CNTN%d" % d for d in windows]
if use("CNTD"):
# The diff between past up day and past down day
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"):
# The total gain / the absolute total price changed
# Similar to RSI indicator. https://www.investopedia.com/terms/r/rsi.asp
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"):
# The total lose / the absolute total price changed
# Can be derived from SUMP by SUMN = 1 - SUMP
# Similar to RSI indicator. https://www.investopedia.com/terms/r/rsi.asp
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"):
# The diff ratio between total gain and total lose
# Similar to RSI indicator. https://www.investopedia.com/terms/r/rsi.asp
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)
@@ -339,12 +379,15 @@ class Alpha158(DataHandlerLP):
]
names += ["SUMD%d" % d for d in windows]
if use("VMA"):
# Simple Volume Moving average: https://www.barchart.com/education/technical-indicators/volume_moving_average
fields += ["Mean($volume, %d)/($volume+1e-12)" % d for d in windows]
names += ["VMA%d" % d for d in windows]
if use("VSTD"):
# The standard deviation for volume in past d days.
fields += ["Std($volume, %d)/($volume+1e-12)" % d for d in windows]
names += ["VSTD%d" % d for d in windows]
if use("WVMA"):
# The volume weighted price change volatility
fields += [
"Std(Abs($close/Ref($close, 1)-1)*$volume, %d)/(Mean(Abs($close/Ref($close, 1)-1)*$volume, %d)+1e-12)"
% (d, d)
@@ -352,6 +395,7 @@ class Alpha158(DataHandlerLP):
]
names += ["WVMA%d" % d for d in windows]
if use("VSUMP"):
# The total volume increase / the absolute total volume changed
fields += [
"Sum(Greater($volume-Ref($volume, 1), 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)"
% (d, d)
@@ -359,6 +403,8 @@ class Alpha158(DataHandlerLP):
]
names += ["VSUMP%d" % d for d in windows]
if use("VSUMN"):
# The total volume increase / the absolute total volume changed
# Can be derived from VSUMP by VSUMN = 1 - VSUMP
fields += [
"Sum(Greater(Ref($volume, 1)-$volume, 0), %d)/(Sum(Abs($volume-Ref($volume, 1)), %d)+1e-12)"
% (d, d)
@@ -366,6 +412,8 @@ class Alpha158(DataHandlerLP):
]
names += ["VSUMN%d" % d for d in windows]
if use("VSUMD"):
# The diff ratio between total volume increase and total volume decrease
# RSI indicator for volume
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)