You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
627 lines
20 KiB
627 lines
20 KiB
|
|
<!DOCTYPE HTML>
|
|
<html lang="" >
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
|
|
<title>调参 · GitBook</title>
|
|
<meta http-equiv="X-UA-Compatible" content="IE=edge" />
|
|
<meta name="description" content="">
|
|
<meta name="generator" content="GitBook 3.2.3">
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../gitbook/style.css">
|
|
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../gitbook/gitbook-plugin-katex/katex.min.css">
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../gitbook/gitbook-plugin-highlight/website.css">
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../gitbook/gitbook-plugin-search/search.css">
|
|
|
|
|
|
|
|
<link rel="stylesheet" href="../gitbook/gitbook-plugin-fontsettings/website.css">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<meta name="HandheldFriendly" content="true"/>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no">
|
|
<meta name="apple-mobile-web-app-capable" content="yes">
|
|
<meta name="apple-mobile-web-app-status-bar-style" content="black">
|
|
<link rel="apple-touch-icon-precomposed" sizes="152x152" href="../gitbook/images/apple-touch-icon-precomposed-152.png">
|
|
<link rel="shortcut icon" href="../gitbook/images/favicon.ico" type="image/x-icon">
|
|
|
|
|
|
|
|
<link rel="prev" href="fit and predict.html" />
|
|
|
|
|
|
</head>
|
|
<body>
|
|
|
|
<div class="book">
|
|
<div class="book-summary">
|
|
|
|
|
|
<div id="book-search-input" role="search">
|
|
<input type="text" placeholder="Type to search" />
|
|
</div>
|
|
|
|
|
|
<nav role="navigation">
|
|
|
|
|
|
|
|
<ul class="summary">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="chapter " data-level="1.1" data-path="../">
|
|
|
|
<a href="../">
|
|
|
|
|
|
简介
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.2" data-path="../machine_learning.html">
|
|
|
|
<a href="../machine_learning.html">
|
|
|
|
|
|
机器学习概述
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3" data-path="../algorithm.html">
|
|
|
|
<a href="../algorithm.html">
|
|
|
|
|
|
常见机器学习算法
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<ul class="articles">
|
|
|
|
|
|
<li class="chapter " data-level="1.3.1" data-path="../kNN.html">
|
|
|
|
<a href="../kNN.html">
|
|
|
|
|
|
近朱者赤近墨者黑-kNN
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.2" data-path="../linear_regression.html">
|
|
|
|
<a href="../linear_regression.html">
|
|
|
|
|
|
最简单的回归算法-线性回归
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.3" data-path="../logistic_regression.html">
|
|
|
|
<a href="../logistic_regression.html">
|
|
|
|
|
|
使用回归的思想进行分类-逻辑回归
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.4" data-path="../decision_tree.html">
|
|
|
|
<a href="../decision_tree.html">
|
|
|
|
|
|
最接近人类思维的算法-决策树
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.5" data-path="../random_forest.html">
|
|
|
|
<a href="../random_forest.html">
|
|
|
|
|
|
群众的力量是伟大的-随机森林
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.6" data-path="../kMeans.html">
|
|
|
|
<a href="../kMeans.html">
|
|
|
|
|
|
物以类聚人以群分-kMeans
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.3.7" data-path="../AGNES.html">
|
|
|
|
<a href="../AGNES.html">
|
|
|
|
|
|
以距离为尺-AGNES
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.4" data-path="../metrics.html">
|
|
|
|
<a href="../metrics.html">
|
|
|
|
|
|
模型评估指标
|
|
|
|
</a>
|
|
|
|
|
|
|
|
<ul class="articles">
|
|
|
|
|
|
<li class="chapter " data-level="1.4.1" data-path="../classification_metrics.html">
|
|
|
|
<a href="../classification_metrics.html">
|
|
|
|
|
|
分类性能评估指标
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.4.2" data-path="../regression_metrics.html">
|
|
|
|
<a href="../regression_metrics.html">
|
|
|
|
|
|
回归性能评估指标
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.4.3" data-path="../cluster_metrics.html">
|
|
|
|
<a href="../cluster_metrics.html">
|
|
|
|
|
|
聚类性能评估指标
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.5" data-path="../sklearn.html">
|
|
|
|
<a href="../sklearn.html">
|
|
|
|
|
|
使用sklearn进行机器学习
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6" >
|
|
|
|
<span>
|
|
|
|
|
|
综合实战案例
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<ul class="articles">
|
|
|
|
|
|
<li class="chapter " data-level="1.6.1" >
|
|
|
|
<span>
|
|
|
|
|
|
泰坦尼克生还预测
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<ul class="articles">
|
|
|
|
|
|
<li class="chapter " data-level="1.6.1.1" data-path="introduction.html">
|
|
|
|
<a href="introduction.html">
|
|
|
|
|
|
简介
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.1.2" data-path="EDA.html">
|
|
|
|
<a href="EDA.html">
|
|
|
|
|
|
探索性数据分析(EDA)
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.1.3" data-path="feature engerning.html">
|
|
|
|
<a href="feature engerning.html">
|
|
|
|
|
|
特征工程
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.1.4" data-path="fit and predict.html">
|
|
|
|
<a href="fit and predict.html">
|
|
|
|
|
|
构建模型进行预测
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter active" data-level="1.6.1.5" data-path="tuning.html">
|
|
|
|
<a href="tuning.html">
|
|
|
|
|
|
调参
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.2" >
|
|
|
|
<span>
|
|
|
|
|
|
使用强化学习玩乒乓球游戏
|
|
|
|
</span>
|
|
|
|
|
|
|
|
<ul class="articles">
|
|
|
|
|
|
<li class="chapter " data-level="1.6.2.1" data-path="../pingpong/what is reinforce learning.html">
|
|
|
|
<a href="../pingpong/what is reinforce learning.html">
|
|
|
|
|
|
什么是强化学习
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.2.2" data-path="../pingpong/Policy Gradient.html">
|
|
|
|
<a href="../pingpong/Policy Gradient.html">
|
|
|
|
|
|
Policy Gradient原理
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.6.2.3" data-path="../pingpong/coding.html">
|
|
|
|
<a href="../pingpong/coding.html">
|
|
|
|
|
|
使用Policy Gradient玩乒乓球游戏
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
<li class="chapter " data-level="1.7" data-path="../recommand.html">
|
|
|
|
<a href="../recommand.html">
|
|
|
|
|
|
实训推荐
|
|
|
|
</a>
|
|
|
|
|
|
|
|
</li>
|
|
|
|
|
|
|
|
|
|
<li class="divider"></li>
|
|
|
|
<li>
|
|
<a href="https://www.gitbook.com" target="blank" class="gitbook-link">
|
|
Published with GitBook
|
|
</a>
|
|
</li>
|
|
</ul>
|
|
|
|
|
|
</nav>
|
|
|
|
|
|
</div>
|
|
|
|
<div class="book-body">
|
|
|
|
<div class="body-inner">
|
|
|
|
|
|
|
|
<div class="book-header" role="navigation">
|
|
|
|
|
|
<!-- Title -->
|
|
<h1>
|
|
<i class="fa fa-circle-o-notch fa-spin"></i>
|
|
<a href=".." >调参</a>
|
|
</h1>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
<div class="page-wrapper" tabindex="-1" role="main">
|
|
<div class="page-inner">
|
|
|
|
<div id="book-search-results">
|
|
<div class="search-noresults">
|
|
|
|
<section class="normal markdown-section">
|
|
|
|
<h1 id="调参">调参</h1>
|
|
<p>很多机器学习算法有很多可以调整的参数(即超参数)，例如我们用的随机森林需要我们指定森林中有多少棵决策树，没棵决策树的最大深度等。这些超参数都或多或少的会影响这模型的性能。那么怎样才能找到合适的超参数，来让我们的模型性能达到比较好的效果呢？可以使用网格搜索!</p>
|
|
<p>网格搜索的意思其实就是遍历所有我们想要尝试的参数组合，看看哪个参数组合的性能最高，那么这组参数组合就是模型的最佳参数。</p>
|
|
<p>sklearn 为我们提供了网格搜索的接口，我们能很方便的进行网格搜索。</p>
|
|
<pre><code class="lang-python"><span class="hljs-keyword">from</span> sklearn.model_selection <span class="hljs-keyword">import</span> GridSearchCV
|
|
|
|
<span class="hljs-comment"># 想要调整的参数的字典，字典的key为参数名字，value为想要尝试参数值</span>
|
|
param_grid = {<span class="hljs-string">'n_estimators'</span>: [<span class="hljs-number">10</span>, <span class="hljs-number">20</span>, <span class="hljs-number">50</span>, <span class="hljs-number">100</span>, <span class="hljs-number">150</span>, <span class="hljs-number">200</span>],<span class="hljs-string">'max_depth'</span>: [<span class="hljs-number">5</span>, <span class="hljs-number">10</span>, <span class="hljs-number">15</span>, <span class="hljs-number">20</span>, <span class="hljs-number">25</span>, <span class="hljs-number">30</span>]}
|
|
|
|
<span class="hljs-comment"># 采用5折验证的方式进行网格搜索，分类器为随机森林</span>
|
|
grid_search = GridSearchCV(RandomForestClassifier(), param_grid, cv=<span class="hljs-number">5</span>)
|
|
grid_search.fit(X_train, Y_train)
|
|
|
|
<span class="hljs-comment"># 打印最佳参数组合</span>
|
|
print(grid_search.best_params_)
|
|
<span class="hljs-comment"># 打印最佳参数组合时模型的最佳性能</span>
|
|
print(grid_search.best_score_)
|
|
</code></pre>
|
|
<p><img src="../img/58.jpg" alt=""></p>
|
|
<p>可以看到经过调参之后，我们的随机森林模型的性能提高到了 0.8323 ，提升了接近 1% 的准确率。然后我们使用最佳参数构造随机森林，并对测试集测试会发现，测试集的准确率达到了 0.8525。</p>
|
|
<pre><code class="lang-python">Y_train = data[<span class="hljs-string">'Survived'</span>]
|
|
X_train = data.drop([<span class="hljs-string">'Survived'</span>], axis=<span class="hljs-number">1</span>)
|
|
|
|
Y_test = test_data[<span class="hljs-string">'Survived'</span>]
|
|
X_test = test_data.drop([<span class="hljs-string">'Survived'</span>], axis=<span class="hljs-number">1</span>)
|
|
|
|
clf = RandomForestClassifier(n_estimators=<span class="hljs-number">50</span>, max_depth=<span class="hljs-number">5</span>)
|
|
clf.fit(X_train, Y_train)
|
|
predict = clf.predict(X_test)
|
|
print(accuracy_score(Y_test, predict))
|
|
</code></pre>
|
|
|
|
|
|
</section>
|
|
|
|
</div>
|
|
<div class="search-results">
|
|
<div class="has-results">
|
|
|
|
<h1 class="search-results-title"><span class='search-results-count'></span> results matching "<span class='search-query'></span>"</h1>
|
|
<ul class="search-results-list"></ul>
|
|
|
|
</div>
|
|
<div class="no-results">
|
|
|
|
<h1 class="search-results-title">No results matching "<span class='search-query'></span>"</h1>
|
|
|
|
</div>
|
|
</div>
|
|
</div>
|
|
|
|
</div>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<a href="fit and predict.html" class="navigation navigation-prev navigation-unique" aria-label="Previous page: 构建模型进行预测">
|
|
<i class="fa fa-angle-left"></i>
|
|
</a>
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
<script>
|
|
var gitbook = gitbook || [];
|
|
gitbook.push(function() {
|
|
gitbook.page.hasChanged({"page":{"title":"调参","level":"1.6.1.5","depth":3,"next":{"title":"使用强化学习玩乒乓球游戏","level":"1.6.2","depth":2,"ref":"","articles":[{"title":"什么是强化学习","level":"1.6.2.1","depth":3,"path":"pingpong/what is reinforce learning.md","ref":"./pingpong/what is reinforce learning.md","articles":[]},{"title":"Policy Gradient原理","level":"1.6.2.2","depth":3,"path":"pingpong/Policy Gradient.md","ref":"./pingpong/Policy Gradient.md","articles":[]},{"title":"使用Policy Gradient玩乒乓球游戏","level":"1.6.2.3","depth":3,"path":"pingpong/coding.md","ref":"./pingpong/coding.md","articles":[]}]},"previous":{"title":"构建模型进行预测","level":"1.6.1.4","depth":3,"path":"titanic/fit and predict.md","ref":"./titanic/fit and predict.md","articles":[]},"dir":"ltr"},"config":{"gitbook":"*","theme":"default","variables":{},"plugins":["katex"],"pluginsConfig":{"katex":{},"highlight":{},"search":{},"lunr":{"maxIndexSize":1000000,"ignoreSpecialCharacters":false},"sharing":{"facebook":true,"twitter":true,"google":false,"weibo":false,"instapaper":false,"vk":false,"all":["facebook","google","twitter","weibo","instapaper"]},"fontsettings":{"theme":"white","family":"sans","size":2},"theme-default":{"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"},"showLevel":false}},"structure":{"langs":"LANGS.md","readme":"README.md","glossary":"GLOSSARY.md","summary":"SUMMARY.md"},"pdf":{"pageNumbers":true,"fontSize":12,"fontFamily":"Arial","paperSize":"a4","chapterMark":"pagebreak","pageBreaksBefore":"/","margin":{"right":62,"left":62,"top":56,"bottom":56}},"styles":{"website":"styles/website.css","pdf":"styles/pdf.css","epub":"styles/epub.css","mobi":"styles/mobi.css","ebook":"styles/ebook.css","print":"styles/print.css"}},"file":{"path":"titanic/tuning.md","mtime":"2019-07-05T01:25:15.418Z","type":"markdown"},"gitbook":{"version":"3.2.3","time":"2019-07-06T07:31:21.537Z"},"basePath":"..","book":{"language":""}});
|
|
});
|
|
</script>
|
|
</div>
|
|
|
|
|
|
<script src="../gitbook/gitbook.js"></script>
|
|
<script src="../gitbook/theme.js"></script>
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-search/search-engine.js"></script>
|
|
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-search/search.js"></script>
|
|
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-lunr/lunr.min.js"></script>
|
|
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-lunr/search-lunr.js"></script>
|
|
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-sharing/buttons.js"></script>
|
|
|
|
|
|
|
|
<script src="../gitbook/gitbook-plugin-fontsettings/fontsettings.js"></script>
|
|
|
|
|
|
|
|
</body>
|
|
</html>
|
|
|