lychiyu/freqtrade_origin
1
0
Fork 0
mirror of https://github.com/freqtrade/freqtrade.git synced 2024-11-15 12:43:56 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
166789c746
freqtrade_origin/en/2019.6/hyperopt/index.html

1337 lines
44 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../backtesting/">
<link rel="next" href="../edge/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.0, mkdocs-material-9.5.30">
<title>Hyperopt - Freqtrade</title>
<link rel="stylesheet" href="../assets/stylesheets/main.3cba04c6.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce((e,_)=>(e<<5)-e+_.charCodeAt(0),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="blue-grey" data-md-color-accent="tear">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#hyperopt" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<div data-md-color-scheme="default" data-md-component="outdated" hidden>
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="Freqtrade" class="md-header__button md-logo" aria-label="Freqtrade" data-md-component="logo">
<img src="../images/logo.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3V6m0 5h18v2H3v-2m0 5h18v2H3v-2Z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Freqtrade
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Hyperopt
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.516 6.516 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5Z"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12 19 6.41Z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="Freqtrade" class="md-nav__button md-logo" aria-label="Freqtrade" data-md-component="logo">
<img src="../images/logo.png" alt="logo">
</a>
Freqtrade
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
About
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../docker/" class="md-nav__link">
<span class="md-ellipsis">
Installation Docker
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../configuration/" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../strategy-customization/" class="md-nav__link">
<span class="md-ellipsis">
Strategy Customization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../stoploss/" class="md-nav__link">
<span class="md-ellipsis">
Stoploss
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../bot-usage/" class="md-nav__link">
<span class="md-ellipsis">
Start the bot
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0">
<span class="md-ellipsis">
Control the bot
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Control the bot
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../telegram-usage/" class="md-nav__link">
<span class="md-ellipsis">
Telegram
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../webhook-config/" class="md-nav__link">
<span class="md-ellipsis">
Web Hook
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../rest-api/" class="md-nav__link">
<span class="md-ellipsis">
REST API
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../backtesting/" class="md-nav__link">
<span class="md-ellipsis">
Backtesting
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Hyperopt
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Hyperopt
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#prepare-hyperopting" class="md-nav__link">
<span class="md-ellipsis">
Prepare Hyperopting
</span>
</a>
<nav class="md-nav" aria-label="Prepare Hyperopting">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#checklist-on-all-tasks-possibilities-in-hyperopt" class="md-nav__link">
<span class="md-ellipsis">
Checklist on all tasks / possibilities in hyperopt
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#1-install-a-custom-hyperopt-file" class="md-nav__link">
<span class="md-ellipsis">
1. Install a Custom Hyperopt File
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2-configure-your-guards-and-triggers" class="md-nav__link">
<span class="md-ellipsis">
2. Configure your Guards and Triggers
</span>
</a>
<nav class="md-nav" aria-label="2. Configure your Guards and Triggers">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#sell-optimization" class="md-nav__link">
<span class="md-ellipsis">
Sell optimization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#using-ticker-interval-as-part-of-the-strategy" class="md-nav__link">
<span class="md-ellipsis">
Using ticker-interval as part of the Strategy
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#solving-a-mystery" class="md-nav__link">
<span class="md-ellipsis">
Solving a Mystery
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#execute-hyperopt" class="md-nav__link">
<span class="md-ellipsis">
Execute Hyperopt
</span>
</a>
<nav class="md-nav" aria-label="Execute Hyperopt">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#execute-hyperopt-with-different-ticker-data-source" class="md-nav__link">
<span class="md-ellipsis">
Execute Hyperopt with Different Ticker-Data Source
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-hyperopt-with-smaller-testset" class="md-nav__link">
<span class="md-ellipsis">
Running Hyperopt with Smaller Testset
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-hyperopt-with-smaller-search-space" class="md-nav__link">
<span class="md-ellipsis">
Running Hyperopt with Smaller Search Space
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#understand-the-hyperopt-result" class="md-nav__link">
<span class="md-ellipsis">
Understand the Hyperopt Result
</span>
</a>
<nav class="md-nav" aria-label="Understand the Hyperopt Result">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#understand-hyperopt-roi-results" class="md-nav__link">
<span class="md-ellipsis">
Understand Hyperopt ROI results
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#validate-backtest-result" class="md-nav__link">
<span class="md-ellipsis">
Validate backtest result
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#next-step" class="md-nav__link">
<span class="md-ellipsis">
Next Step
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../edge/" class="md-nav__link">
<span class="md-ellipsis">
Edge positioning
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../plotting/" class="md-nav__link">
<span class="md-ellipsis">
Plotting
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../deprecated/" class="md-nav__link">
<span class="md-ellipsis">
Deprecated features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../faq/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../data-analysis/" class="md-nav__link">
<span class="md-ellipsis">
Data Analysis
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../sql_cheatsheet/" class="md-nav__link">
<span class="md-ellipsis">
SQL Cheatsheet
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../sandbox-testing/" class="md-nav__link">
<span class="md-ellipsis">
Sandbox testing
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../developer/" class="md-nav__link">
<span class="md-ellipsis">
Contributors guide
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#prepare-hyperopting" class="md-nav__link">
<span class="md-ellipsis">
Prepare Hyperopting
</span>
</a>
<nav class="md-nav" aria-label="Prepare Hyperopting">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#checklist-on-all-tasks-possibilities-in-hyperopt" class="md-nav__link">
<span class="md-ellipsis">
Checklist on all tasks / possibilities in hyperopt
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#1-install-a-custom-hyperopt-file" class="md-nav__link">
<span class="md-ellipsis">
1. Install a Custom Hyperopt File
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#2-configure-your-guards-and-triggers" class="md-nav__link">
<span class="md-ellipsis">
2. Configure your Guards and Triggers
</span>
</a>
<nav class="md-nav" aria-label="2. Configure your Guards and Triggers">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#sell-optimization" class="md-nav__link">
<span class="md-ellipsis">
Sell optimization
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#using-ticker-interval-as-part-of-the-strategy" class="md-nav__link">
<span class="md-ellipsis">
Using ticker-interval as part of the Strategy
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#solving-a-mystery" class="md-nav__link">
<span class="md-ellipsis">
Solving a Mystery
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#execute-hyperopt" class="md-nav__link">
<span class="md-ellipsis">
Execute Hyperopt
</span>
</a>
<nav class="md-nav" aria-label="Execute Hyperopt">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#execute-hyperopt-with-different-ticker-data-source" class="md-nav__link">
<span class="md-ellipsis">
Execute Hyperopt with Different Ticker-Data Source
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-hyperopt-with-smaller-testset" class="md-nav__link">
<span class="md-ellipsis">
Running Hyperopt with Smaller Testset
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-hyperopt-with-smaller-search-space" class="md-nav__link">
<span class="md-ellipsis">
Running Hyperopt with Smaller Search Space
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#understand-the-hyperopt-result" class="md-nav__link">
<span class="md-ellipsis">
Understand the Hyperopt Result
</span>
</a>
<nav class="md-nav" aria-label="Understand the Hyperopt Result">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#understand-hyperopt-roi-results" class="md-nav__link">
<span class="md-ellipsis">
Understand Hyperopt ROI results
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#validate-backtest-result" class="md-nav__link">
<span class="md-ellipsis">
Validate backtest result
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#next-step" class="md-nav__link">
<span class="md-ellipsis">
Next Step
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="hyperopt">Hyperopt<a class="headerlink" href="#hyperopt" title="Permanent link">&para;</a></h1>
<p>This page explains how to tune your strategy by finding the optimal
parameters, a process called hyperparameter optimization. The bot uses several
algorithms included in the <code>scikit-optimize</code> package to accomplish this. The
search will burn all your CPU cores, make your laptop sound like a fighter jet
and still take a long time.</p>
<div class="admonition bug">
<p class="admonition-title">Bug</p>
<p>Hyperopt will crash when used with only 1 CPU Core as found out in <a href="https://github.com/freqtrade/freqtrade/issues/1133">Issue #1133</a></p>
</div>
<h2 id="prepare-hyperopting">Prepare Hyperopting<a class="headerlink" href="#prepare-hyperopting" title="Permanent link">&para;</a></h2>
<p>Before we start digging into Hyperopt, we recommend you to take a look at
an example hyperopt file located into <a href="https://github.com/freqtrade/freqtrade/blob/develop/user_data/hyperopts/sample_hyperopt.py">user_data/hyperopts/</a></p>
<p>Configuring hyperopt is similar to writing your own strategy, and many tasks will be similar and a lot of code can be copied across from the strategy.</p>
<h3 id="checklist-on-all-tasks-possibilities-in-hyperopt">Checklist on all tasks / possibilities in hyperopt<a class="headerlink" href="#checklist-on-all-tasks-possibilities-in-hyperopt" title="Permanent link">&para;</a></h3>
<p>Depending on the space you want to optimize, only some of the below are required.</p>
<ul>
<li>fill <code>populate_indicators</code> - probably a copy from your strategy</li>
<li>fill <code>buy_strategy_generator</code> - for buy signal optimization</li>
<li>fill <code>indicator_space</code> - for buy signal optimzation</li>
<li>fill <code>sell_strategy_generator</code> - for sell signal optimization</li>
<li>fill <code>sell_indicator_space</code> - for sell signal optimzation</li>
<li>fill <code>roi_space</code> - for ROI optimization</li>
<li>fill <code>generate_roi_table</code> - for ROI optimization (if you need more than 3 entries)</li>
<li>fill <code>stoploss_space</code> - stoploss optimization</li>
<li>Optional but recommended</li>
<li>copy <code>populate_buy_trend</code> from your strategy - otherwise default-strategy will be used</li>
<li>copy <code>populate_sell_trend</code> from your strategy - otherwise default-strategy will be used</li>
</ul>
<h3 id="1-install-a-custom-hyperopt-file">1. Install a Custom Hyperopt File<a class="headerlink" href="#1-install-a-custom-hyperopt-file" title="Permanent link">&para;</a></h3>
<p>Put your hyperopt file into the folder<code>user_data/hyperopts</code>.</p>
<p>Let assume you want a hyperopt file <code>awesome_hyperopt.py</code>:<br />
Copy the file <code>user_data/hyperopts/sample_hyperopt.py</code> into <code>user_data/hyperopts/awesome_hyperopt.py</code></p>
<h3 id="2-configure-your-guards-and-triggers">2. Configure your Guards and Triggers<a class="headerlink" href="#2-configure-your-guards-and-triggers" title="Permanent link">&para;</a></h3>
<p>There are two places you need to change in your hyperopt file to add a new buy hyperopt for testing:</p>
<ul>
<li>Inside <code>indicator_space()</code> - the parameters hyperopt shall be optimizing.</li>
<li>Inside <code>populate_buy_trend()</code> - applying the parameters.</li>
</ul>
<p>There you have two different types of indicators: 1. <code>guards</code> and 2. <code>triggers</code>.</p>
<ol>
<li>Guards are conditions like "never buy if ADX &lt; 10", or never buy if current price is over EMA10.</li>
<li>Triggers are ones that actually trigger buy in specific moment, like "buy when EMA5 crosses over EMA10" or "buy when close price touches lower bollinger band".</li>
</ol>
<p>Hyperoptimization will, for each eval round, pick one trigger and possibly
multiple guards. The constructed strategy will be something like
"<em>buy exactly when close price touches lower bollinger band, BUT only if
ADX &gt; 10</em>".</p>
<p>If you have updated the buy strategy, ie. changed the contents of
<code>populate_buy_trend()</code> method you have to update the <code>guards</code> and
<code>triggers</code> hyperopts must use.</p>
<h4 id="sell-optimization">Sell optimization<a class="headerlink" href="#sell-optimization" title="Permanent link">&para;</a></h4>
<p>Similar to the buy-signal above, sell-signals can also be optimized.
Place the corresponding settings into the following methods</p>
<ul>
<li>Inside <code>sell_indicator_space()</code> - the parameters hyperopt shall be optimizing.</li>
<li>Inside <code>populate_sell_trend()</code> - applying the parameters.</li>
</ul>
<p>The configuration and rules are the same than for buy signals.
To avoid naming collisions in the search-space, please prefix all sell-spaces with <code>sell-</code>.</p>
<h4 id="using-ticker-interval-as-part-of-the-strategy">Using ticker-interval as part of the Strategy<a class="headerlink" href="#using-ticker-interval-as-part-of-the-strategy" title="Permanent link">&para;</a></h4>
<p>The Strategy exposes the ticker-interval as <code>self.ticker_interval</code>. The same value is available as class-attribute <code>HyperoptName.ticker_interval</code>.
In the case of the linked sample-value this would be <code>SampleHyperOpts.ticker_interval</code>.</p>
<h2 id="solving-a-mystery">Solving a Mystery<a class="headerlink" href="#solving-a-mystery" title="Permanent link">&para;</a></h2>
<p>Let's say you are curious: should you use MACD crossings or lower Bollinger
Bands to trigger your buys. And you also wonder should you use RSI or ADX to
help with those buy decisions. If you decide to use RSI or ADX, which values
should I use for them? So let's use hyperparameter optimization to solve this
mystery.</p>
<p>We will start by defining a search space:</p>
<div class="highlight"><pre><span></span><code> <span class="k">def</span> <span class="nf">indicator_space</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="n">Dimension</span><span class="p">]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
<span class="sd"> Define your Hyperopt space for searching strategy parameters</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="p">[</span>
<span class="n">Integer</span><span class="p">(</span><span class="mi">20</span><span class="p">,</span> <span class="mi">40</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;adx-value&#39;</span><span class="p">),</span>
<span class="n">Integer</span><span class="p">(</span><span class="mi">20</span><span class="p">,</span> <span class="mi">40</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;rsi-value&#39;</span><span class="p">),</span>
<span class="n">Categorical</span><span class="p">([</span><span class="kc">True</span><span class="p">,</span> <span class="kc">False</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;adx-enabled&#39;</span><span class="p">),</span>
<span class="n">Categorical</span><span class="p">([</span><span class="kc">True</span><span class="p">,</span> <span class="kc">False</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;rsi-enabled&#39;</span><span class="p">),</span>
<span class="n">Categorical</span><span class="p">([</span><span class="s1">&#39;bb_lower&#39;</span><span class="p">,</span> <span class="s1">&#39;macd_cross_signal&#39;</span><span class="p">],</span> <span class="n">name</span><span class="o">=</span><span class="s1">&#39;trigger&#39;</span><span class="p">)</span>
<span class="p">]</span>
</code></pre></div>
<p>Above definition says: I have five parameters I want you to randomly combine
to find the best combination. Two of them are integer values (<code>adx-value</code>
and <code>rsi-value</code>) and I want you test in the range of values 20 to 40.
Then we have three category variables. First two are either <code>True</code> or <code>False</code>.
We use these to either enable or disable the ADX and RSI guards. The last
one we call <code>trigger</code> and use it to decide which buy trigger we want to use.</p>
<p>So let's write the buy strategy using these values:</p>
<div class="highlight"><pre><span></span><code> <span class="k">def</span> <span class="nf">populate_buy_trend</span><span class="p">(</span><span class="n">dataframe</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="n">conditions</span> <span class="o">=</span> <span class="p">[]</span>
<span class="c1"># GUARDS AND TRENDS</span>
<span class="k">if</span> <span class="s1">&#39;adx-enabled&#39;</span> <span class="ow">in</span> <span class="n">params</span> <span class="ow">and</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;adx-enabled&#39;</span><span class="p">]:</span>
<span class="n">conditions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;adx&#39;</span><span class="p">]</span> <span class="o">&gt;</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;adx-value&#39;</span><span class="p">])</span>
<span class="k">if</span> <span class="s1">&#39;rsi-enabled&#39;</span> <span class="ow">in</span> <span class="n">params</span> <span class="ow">and</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;rsi-enabled&#39;</span><span class="p">]:</span>
<span class="n">conditions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;rsi&#39;</span><span class="p">]</span> <span class="o">&lt;</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;rsi-value&#39;</span><span class="p">])</span>
<span class="c1"># TRIGGERS</span>
<span class="k">if</span> <span class="s1">&#39;trigger&#39;</span> <span class="ow">in</span> <span class="n">params</span><span class="p">:</span>
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;trigger&#39;</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;bb_lower&#39;</span><span class="p">:</span>
<span class="n">conditions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;close&#39;</span><span class="p">]</span> <span class="o">&lt;</span> <span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;bb_lowerband&#39;</span><span class="p">])</span>
<span class="k">if</span> <span class="n">params</span><span class="p">[</span><span class="s1">&#39;trigger&#39;</span><span class="p">]</span> <span class="o">==</span> <span class="s1">&#39;macd_cross_signal&#39;</span><span class="p">:</span>
<span class="n">conditions</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">qtpylib</span><span class="o">.</span><span class="n">crossed_above</span><span class="p">(</span>
<span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;macd&#39;</span><span class="p">],</span> <span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;macdsignal&#39;</span><span class="p">]</span>
<span class="p">))</span>
<span class="k">if</span> <span class="n">conditions</span><span class="p">:</span>
<span class="n">dataframe</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span>
<span class="n">reduce</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">,</span> <span class="n">y</span><span class="p">:</span> <span class="n">x</span> <span class="o">&amp;</span> <span class="n">y</span><span class="p">,</span> <span class="n">conditions</span><span class="p">),</span>
<span class="s1">&#39;buy&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">dataframe</span>
<span class="k">return</span> <span class="n">populate_buy_trend</span>
</code></pre></div>
<p>Hyperopting will now call this <code>populate_buy_trend</code> as many times you ask it (<code>epochs</code>)
with different value combinations. It will then use the given historical data and make
buys based on the buy signals generated with the above function and based on the results
it will end with telling you which paramter combination produced the best profits.</p>
<p>The search for best parameters starts with a few random combinations and then uses a
regressor algorithm (currently ExtraTreesRegressor) to quickly find a parameter combination
that minimizes the value of the objective function <code>calculate_loss</code> in <code>hyperopt.py</code>.</p>
<p>The above setup expects to find ADX, RSI and Bollinger Bands in the populated indicators.
When you want to test an indicator that isn't used by the bot currently, remember to
add it to the <code>populate_indicators()</code> method in <code>hyperopt.py</code>.</p>
<h2 id="execute-hyperopt">Execute Hyperopt<a class="headerlink" href="#execute-hyperopt" title="Permanent link">&para;</a></h2>
<p>Once you have updated your hyperopt configuration you can run it.
Because hyperopt tries a lot of combinations to find the best parameters it will take time you will have the result (more than 30 mins).</p>
<p>We strongly recommend to use <code>screen</code> or <code>tmux</code> to prevent any connection loss.</p>
<div class="highlight"><pre><span></span><code>python3<span class="w"> </span>freqtrade<span class="w"> </span>-c<span class="w"> </span>config.json<span class="w"> </span>hyperopt<span class="w"> </span>--customhyperopt<span class="w"> </span>&lt;hyperoptname&gt;<span class="w"> </span>-e<span class="w"> </span><span class="m">5000</span><span class="w"> </span>--spaces<span class="w"> </span>all
</code></pre></div>
<p>Use <code>&lt;hyperoptname&gt;</code> as the name of the custom hyperopt used.</p>
<p>The <code>-e</code> flag will set how many evaluations hyperopt will do. We recommend
running at least several thousand evaluations.</p>
<p>The <code>--spaces all</code> flag determines that all possible parameters should be optimized. Possibilities are listed below.</p>
<div class="admonition warning">
<p class="admonition-title">Warning</p>
<p>When switching parameters or changing configuration options, the file <code>user_data/hyperopt_results.pickle</code> should be removed. It's used to be able to continue interrupted calculations, but does not detect changes to settings or the hyperopt file.</p>
</div>
<h3 id="execute-hyperopt-with-different-ticker-data-source">Execute Hyperopt with Different Ticker-Data Source<a class="headerlink" href="#execute-hyperopt-with-different-ticker-data-source" title="Permanent link">&para;</a></h3>
<p>If you would like to hyperopt parameters using an alternate ticker data that
you have on-disk, use the <code>--datadir PATH</code> option. Default hyperopt will
use data from directory <code>user_data/data</code>.</p>
<h3 id="running-hyperopt-with-smaller-testset">Running Hyperopt with Smaller Testset<a class="headerlink" href="#running-hyperopt-with-smaller-testset" title="Permanent link">&para;</a></h3>
<p>Use the <code>--timerange</code> argument to change how much of the testset
you want to use. The last N ticks/timeframes will be used.
Example:</p>
<div class="highlight"><pre><span></span><code>python3<span class="w"> </span>freqtrade<span class="w"> </span>hyperopt<span class="w"> </span>--timerange<span class="w"> </span>-200
</code></pre></div>
<h3 id="running-hyperopt-with-smaller-search-space">Running Hyperopt with Smaller Search Space<a class="headerlink" href="#running-hyperopt-with-smaller-search-space" title="Permanent link">&para;</a></h3>
<p>Use the <code>--spaces</code> argument to limit the search space used by hyperopt.
Letting Hyperopt optimize everything is a huuuuge search space. Often it
might make more sense to start by just searching for initial buy algorithm.
Or maybe you just want to optimize your stoploss or roi table for that awesome
new buy strategy you have.</p>
<p>Legal values are:</p>
<ul>
<li><code>all</code>: optimize everything</li>
<li><code>buy</code>: just search for a new buy strategy</li>
<li><code>sell</code>: just search for a new sell strategy</li>
<li><code>roi</code>: just optimize the minimal profit table for your strategy</li>
<li><code>stoploss</code>: search for the best stoploss value</li>
<li>space-separated list of any of the above values for example <code>--spaces roi stoploss</code></li>
</ul>
<h2 id="understand-the-hyperopt-result">Understand the Hyperopt Result<a class="headerlink" href="#understand-the-hyperopt-result" title="Permanent link">&para;</a></h2>
<p>Once Hyperopt is completed you can use the result to create a new strategy.
Given the following result from hyperopt:</p>
<div class="highlight"><pre><span></span><code>Best result:
135 trades. Avg profit 0.57%. Total profit 0.03871918 BTC (0.7722Σ%). Avg duration 180.4 mins.
with values:
{ &#39;adx-value&#39;: 44,
&#39;rsi-value&#39;: 29,
&#39;adx-enabled&#39;: False,
&#39;rsi-enabled&#39;: True,
&#39;trigger&#39;: &#39;bb_lower&#39;}
</code></pre></div>
<p>You should understand this result like:</p>
<ul>
<li>The buy trigger that worked best was <code>bb_lower</code>.</li>
<li>You should not use ADX because <code>adx-enabled: False</code>)</li>
<li>You should <strong>consider</strong> using the RSI indicator (<code>rsi-enabled: True</code> and the best value is <code>29.0</code> (<code>rsi-value: 29.0</code>)</li>
</ul>
<p>You have to look inside your strategy file into <code>buy_strategy_generator()</code>
method, what those values match to.</p>
<p>So for example you had <code>rsi-value: 29.0</code> so we would look at <code>rsi</code>-block, that translates to the following code block:</p>
<div class="highlight"><pre><span></span><code>(dataframe[&#39;rsi&#39;] &lt; 29.0)
</code></pre></div>
<p>Translating your whole hyperopt result as the new buy-signal
would then look like:</p>
<div class="highlight"><pre><span></span><code><span class="k">def</span> <span class="nf">populate_buy_trend</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dataframe</span><span class="p">:</span> <span class="n">DataFrame</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">DataFrame</span><span class="p">:</span>
<span class="n">dataframe</span><span class="o">.</span><span class="n">loc</span><span class="p">[</span>
<span class="p">(</span>
<span class="p">(</span><span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;rsi&#39;</span><span class="p">]</span> <span class="o">&lt;</span> <span class="mf">29.0</span><span class="p">)</span> <span class="o">&amp;</span> <span class="c1"># rsi-value</span>
<span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;close&#39;</span><span class="p">]</span> <span class="o">&lt;</span> <span class="n">dataframe</span><span class="p">[</span><span class="s1">&#39;bb_lowerband&#39;</span><span class="p">]</span> <span class="c1"># trigger</span>
<span class="p">),</span>
<span class="s1">&#39;buy&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="mi">1</span>
<span class="k">return</span> <span class="n">dataframe</span>
</code></pre></div>
<h3 id="understand-hyperopt-roi-results">Understand Hyperopt ROI results<a class="headerlink" href="#understand-hyperopt-roi-results" title="Permanent link">&para;</a></h3>
<p>If you are optimizing ROI, you're result will look as follows and include a ROI table.</p>
<div class="highlight"><pre><span></span><code>Best result:
135 trades. Avg profit 0.57%. Total profit 0.03871918 BTC (0.7722Σ%). Avg duration 180.4 mins.
with values:
{ &#39;adx-value&#39;: 44,
&#39;rsi-value&#39;: 29,
&#39;adx-enabled&#39;: false,
&#39;rsi-enabled&#39;: True,
&#39;trigger&#39;: &#39;bb_lower&#39;,
&#39;roi_t1&#39;: 40,
&#39;roi_t2&#39;: 57,
&#39;roi_t3&#39;: 21,
&#39;roi_p1&#39;: 0.03634636907306948,
&#39;roi_p2&#39;: 0.055237357937802885,
&#39;roi_p3&#39;: 0.015163796015548354,
&#39;stoploss&#39;: -0.37996664668703606
}
ROI table:
{ 0: 0.10674752302642071,
21: 0.09158372701087236,
78: 0.03634636907306948,
118: 0}
</code></pre></div>
<p>This would translate to the following ROI table:</p>
<div class="highlight"><pre><span></span><code> <span class="n">minimal_roi</span> <span class="o">=</span> <span class="p">{</span>
<span class="s2">&quot;118&quot;</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span>
<span class="s2">&quot;78&quot;</span><span class="p">:</span> <span class="mf">0.0363463</span><span class="p">,</span>
<span class="s2">&quot;21&quot;</span><span class="p">:</span> <span class="mf">0.0915</span><span class="p">,</span>
<span class="s2">&quot;0&quot;</span><span class="p">:</span> <span class="mf">0.106</span>
<span class="p">}</span>
</code></pre></div>
<h3 id="validate-backtest-result">Validate backtest result<a class="headerlink" href="#validate-backtest-result" title="Permanent link">&para;</a></h3>
<p>Once the optimized strategy has been implemented into your strategy, you should backtest this strategy to make sure everything is working as expected.
To archive the same results (number of trades, ...) than during hyperopt, please use the command line flags <code>--disable-max-market-positions</code> and <code>--enable-position-stacking</code> for backtesting.</p>
<p>This configuration is the default in hyperopt for performance reasons.</p>
<p>You can overwrite position stacking in the configuration by explicitly setting <code>"position_stacking"=false</code> or by changing the relevant line in your hyperopt file <a href="https://github.com/freqtrade/freqtrade/blob/develop/freqtrade/optimize/hyperopt.py#L191">here</a>.</p>
<p>Enabling the market-position for hyperopt is currently not possible.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Dry/live runs will <strong>NOT</strong> use position stacking - therefore it does make sense to also validate the strategy without this as it's closer to reality.</p>
</div>
<h2 id="next-step">Next Step<a class="headerlink" href="#next-step" title="Permanent link">&para;</a></h2>
<p>Now you have a perfect bot and want to control it from Telegram. Your
next step is to learn the <a href="../telegram-usage/">Telegram usage</a>.</p>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": [], "search": "../assets/javascripts/workers/search.b8dbb3d2.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": {"provider": "mike"}}</script>
<script src="../assets/javascripts/bundle.fe8b6f2b.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink