blob: 4779e0f58cafd4760eeeab68caf7a999afd32f3c [file] [log] [blame]
<!DOCTYPE html>
<html lang="en" data-content_root="../../">
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>HTML Rendering in Jupyter &#8212; Apache Arrow DataFusion documentation</title>
<link href="../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet">
<link href="../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet">
<link rel="stylesheet"
href="../../_static/vendor/fontawesome/5.13.0/css/all.min.css">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2">
<link rel="preload" as="font" type="font/woff2" crossorigin
href="../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2">
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=8f2a1f02" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/pydata-sphinx-theme.css?v=1140d252" />
<link rel="stylesheet" type="text/css" href="../../_static/graphviz.css?v=4ae1632d" />
<link rel="stylesheet" type="text/css" href="../../_static/theme_overrides.css?v=dca7052a" />
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf">
<script src="../../_static/documentation_options.js?v=8a448e45"></script>
<script src="../../_static/doctools.js?v=9bcbadda"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Common Operations" href="../common-operations/index.html" />
<link rel="prev" title="DataFrames" href="index.html" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="docsearch:language" content="en">
<!-- Google Analytics -->
</head>
<body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80">
<div class="container-fluid" id="banner"></div>
<div class="container-xl">
<div class="row">
<!-- Only show if we have sidebars configured, else just a small margin -->
<div class="col-12 col-md-3 bd-sidebar">
<div class="sidebar-start-items">
<a class="navbar-brand" href="../../index.html">
<img src="../../_static/images/2x_bgwhite_original.png" class="logo" alt="logo">
</a>
<form class="bd-search d-flex align-items-center" action="../../search.html" method="get">
<i class="icon fas fa-search"></i>
<input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" >
</form>
<nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation">
<div class="bd-toc-item active">
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
LINKS
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion-python">
Github and Issue Tracker
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://docs.rs/datafusion/latest/datafusion/">
Rust's API Docs
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion/blob/main/CODE_OF_CONDUCT.md">
Code of conduct
</a>
</li>
<li class="toctree-l1">
<a class="reference external" href="https://github.com/apache/datafusion-python/tree/main/examples">
Examples
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
USER GUIDE
</span>
</p>
<ul class="current nav bd-sidenav">
<li class="toctree-l1">
<a class="reference internal" href="../introduction.html">
Introduction
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../basics.html">
Concepts
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../data-sources.html">
Data Sources
</a>
</li>
<li class="toctree-l1 current active has-children">
<a class="reference internal" href="index.html">
DataFrames
</a>
<input checked="" class="toctree-checkbox" id="toctree-checkbox-1" name="toctree-checkbox-1" type="checkbox"/>
<label for="toctree-checkbox-1">
<i class="fas fa-chevron-down">
</i>
</label>
<ul class="current">
<li class="toctree-l2 current active">
<a class="current reference internal" href="#">
HTML Rendering in Jupyter
</a>
</li>
</ul>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="../common-operations/index.html">
Common Operations
</a>
<input class="toctree-checkbox" id="toctree-checkbox-2" name="toctree-checkbox-2" type="checkbox"/>
<label for="toctree-checkbox-2">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/views.html">
Registering Views
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/basic-info.html">
Basic Operations
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/select-and-filter.html">
Column Selections
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/expressions.html">
Expressions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/joins.html">
Joins
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/functions.html">
Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/aggregations.html">
Aggregation
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/windows.html">
Window Functions
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../common-operations/udf-and-udfa.html">
User-Defined Functions
</a>
</li>
</ul>
</li>
<li class="toctree-l1 has-children">
<a class="reference internal" href="../io/index.html">
IO
</a>
<input class="toctree-checkbox" id="toctree-checkbox-3" name="toctree-checkbox-3" type="checkbox"/>
<label for="toctree-checkbox-3">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2">
<a class="reference internal" href="../io/arrow.html">
Arrow
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/avro.html">
Avro
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/csv.html">
CSV
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/json.html">
JSON
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/parquet.html">
Parquet
</a>
</li>
<li class="toctree-l2">
<a class="reference internal" href="../io/table_provider.html">
Custom Table Provider
</a>
</li>
</ul>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../configuration.html">
Configuration
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../sql.html">
SQL
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
CONTRIBUTOR GUIDE
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1">
<a class="reference internal" href="../../contributor-guide/introduction.html">
Introduction
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="../../contributor-guide/ffi.html">
Python Extensions
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
API
</span>
</p>
<ul class="nav bd-sidenav">
<li class="toctree-l1 has-children">
<a class="reference internal" href="../../autoapi/index.html">
API Reference
</a>
<input class="toctree-checkbox" id="toctree-checkbox-4" name="toctree-checkbox-4" type="checkbox"/>
<label for="toctree-checkbox-4">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l2 has-children">
<a class="reference internal" href="../../autoapi/datafusion/index.html">
datafusion
</a>
<input class="toctree-checkbox" id="toctree-checkbox-5" name="toctree-checkbox-5" type="checkbox"/>
<label for="toctree-checkbox-5">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/catalog/index.html">
datafusion.catalog
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/context/index.html">
datafusion.context
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/dataframe/index.html">
datafusion.dataframe
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/dataframe_formatter/index.html">
datafusion.dataframe_formatter
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/expr/index.html">
datafusion.expr
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/functions/index.html">
datafusion.functions
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/html_formatter/index.html">
datafusion.html_formatter
</a>
</li>
<li class="toctree-l3 has-children">
<a class="reference internal" href="../../autoapi/datafusion/input/index.html">
datafusion.input
</a>
<input class="toctree-checkbox" id="toctree-checkbox-6" name="toctree-checkbox-6" type="checkbox"/>
<label for="toctree-checkbox-6">
<i class="fas fa-chevron-down">
</i>
</label>
<ul>
<li class="toctree-l4">
<a class="reference internal" href="../../autoapi/datafusion/input/base/index.html">
datafusion.input.base
</a>
</li>
<li class="toctree-l4">
<a class="reference internal" href="../../autoapi/datafusion/input/location/index.html">
datafusion.input.location
</a>
</li>
</ul>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/io/index.html">
datafusion.io
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/object_store/index.html">
datafusion.object_store
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/plan/index.html">
datafusion.plan
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/record_batch/index.html">
datafusion.record_batch
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/substrait/index.html">
datafusion.substrait
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/unparser/index.html">
datafusion.unparser
</a>
</li>
<li class="toctree-l3">
<a class="reference internal" href="../../autoapi/datafusion/user_defined/index.html">
datafusion.user_defined
</a>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</div>
</nav>
</div>
<div class="sidebar-end-items">
</div>
</div>
<div class="d-none d-xl-block col-xl-2 bd-toc">
<div class="toc-item">
<div class="tocsection onthispage pt-5 pb-3">
<i class="fas fa-list"></i> On this page
</div>
<nav id="bd-toc-nav">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#basic-html-rendering">
Basic HTML Rendering
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#customizing-html-rendering">
Customizing HTML Rendering
</a>
<ul class="visible nav section-nav flex-column">
<li class="toc-h3 nav-item toc-entry">
<a class="reference internal nav-link" href="#configuring-the-html-formatter">
Configuring the HTML Formatter
</a>
</li>
</ul>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#custom-style-providers">
Custom Style Providers
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#performance-optimization-with-shared-styles">
Performance Optimization with Shared Styles
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#creating-a-custom-formatter">
Creating a Custom Formatter
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#managing-formatters">
Managing Formatters
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#contextual-formatting">
Contextual Formatting
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#memory-and-display-controls">
Memory and Display Controls
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#best-practices">
Best Practices
</a>
</li>
<li class="toc-h2 nav-item toc-entry">
<a class="reference internal nav-link" href="#additional-resources">
Additional Resources
</a>
</li>
</ul>
</nav>
</div>
<div class="toc-item">
</div>
</div>
<main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main">
<div>
<section id="html-rendering-in-jupyter">
<h1>HTML Rendering in Jupyter<a class="headerlink" href="#html-rendering-in-jupyter" title="Link to this heading"></a></h1>
<p>When working in Jupyter notebooks or other environments that support rich HTML display,
DataFusion DataFrames automatically render as nicely formatted HTML tables. This functionality
is provided by the <code class="docutils literal notranslate"><span class="pre">_repr_html_</span></code> method, which is automatically called by Jupyter to provide
a richer visualization than plain text output.</p>
<section id="basic-html-rendering">
<h2>Basic HTML Rendering<a class="headerlink" href="#basic-html-rendering" title="Link to this heading"></a></h2>
<p>In a Jupyter environment, simply displaying a DataFrame object will trigger HTML rendering:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="c1"># Will display as HTML table in Jupyter</span>
<span class="n">df</span>
<span class="c1"># Explicit display also uses HTML rendering</span>
<span class="n">display</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="customizing-html-rendering">
<h2>Customizing HTML Rendering<a class="headerlink" href="#customizing-html-rendering" title="Link to this heading"></a></h2>
<p>DataFusion provides extensive customization options for HTML table rendering through the
<code class="docutils literal notranslate"><span class="pre">datafusion.html_formatter</span></code> module.</p>
<section id="configuring-the-html-formatter">
<h3>Configuring the HTML Formatter<a class="headerlink" href="#configuring-the-html-formatter" title="Link to this heading"></a></h3>
<p>You can customize how DataFrames are rendered by configuring the formatter:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">configure_formatter</span>
<span class="c1"># Change the default styling</span>
<span class="n">configure_formatter</span><span class="p">(</span>
<span class="n">max_cell_length</span><span class="o">=</span><span class="mi">25</span><span class="p">,</span> <span class="c1"># Maximum characters in a cell before truncation</span>
<span class="n">max_width</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="c1"># Maximum width in pixels</span>
<span class="n">max_height</span><span class="o">=</span><span class="mi">300</span><span class="p">,</span> <span class="c1"># Maximum height in pixels</span>
<span class="n">max_memory_bytes</span><span class="o">=</span><span class="mi">2097152</span><span class="p">,</span> <span class="c1"># Maximum memory for rendering (2MB)</span>
<span class="n">min_rows_display</span><span class="o">=</span><span class="mi">20</span><span class="p">,</span> <span class="c1"># Minimum number of rows to display</span>
<span class="n">repr_rows</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="c1"># Number of rows to display in __repr__</span>
<span class="n">enable_cell_expansion</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span><span class="c1"># Allow expanding truncated cells</span>
<span class="n">custom_css</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># Additional custom CSS</span>
<span class="n">show_truncation_message</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="c1"># Show message when data is truncated</span>
<span class="n">style_provider</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># Custom styling provider</span>
<span class="n">use_shared_styles</span><span class="o">=</span><span class="kc">True</span> <span class="c1"># Share styles across tables</span>
<span class="p">)</span>
</pre></div>
</div>
<p>The formatter settings affect all DataFrames displayed after configuration.</p>
</section>
</section>
<section id="custom-style-providers">
<h2>Custom Style Providers<a class="headerlink" href="#custom-style-providers" title="Link to this heading"></a></h2>
<p>For advanced styling needs, you can create a custom style provider:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">StyleProvider</span><span class="p">,</span> <span class="n">configure_formatter</span>
<span class="k">class</span><span class="w"> </span><span class="nc">MyStyleProvider</span><span class="p">(</span><span class="n">StyleProvider</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_table_styles</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="p">{</span>
<span class="s2">&quot;table&quot;</span><span class="p">:</span> <span class="s2">&quot;border-collapse: collapse; width: 100%;&quot;</span><span class="p">,</span>
<span class="s2">&quot;th&quot;</span><span class="p">:</span> <span class="s2">&quot;background-color: #007bff; color: white; padding: 8px; text-align: left;&quot;</span><span class="p">,</span>
<span class="s2">&quot;td&quot;</span><span class="p">:</span> <span class="s2">&quot;border: 1px solid #ddd; padding: 8px;&quot;</span><span class="p">,</span>
<span class="s2">&quot;tr:nth-child(even)&quot;</span><span class="p">:</span> <span class="s2">&quot;background-color: #f2f2f2;&quot;</span><span class="p">,</span>
<span class="p">}</span>
<span class="k">def</span><span class="w"> </span><span class="nf">get_value_styles</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dtype</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Return custom styles for specific values&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">dtype</span> <span class="o">==</span> <span class="s2">&quot;float&quot;</span> <span class="ow">and</span> <span class="n">value</span> <span class="o">&lt;</span> <span class="mi">0</span><span class="p">:</span>
<span class="k">return</span> <span class="s2">&quot;color: red;&quot;</span>
<span class="k">return</span> <span class="kc">None</span>
<span class="c1"># Apply the custom style provider</span>
<span class="n">configure_formatter</span><span class="p">(</span><span class="n">style_provider</span><span class="o">=</span><span class="n">MyStyleProvider</span><span class="p">())</span>
</pre></div>
</div>
</section>
<section id="performance-optimization-with-shared-styles">
<h2>Performance Optimization with Shared Styles<a class="headerlink" href="#performance-optimization-with-shared-styles" title="Link to this heading"></a></h2>
<p>The <code class="docutils literal notranslate"><span class="pre">use_shared_styles</span></code> parameter (enabled by default) optimizes performance when displaying
multiple DataFrames in notebook environments:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">StyleProvider</span><span class="p">,</span> <span class="n">configure_formatter</span>
<span class="c1"># Default: Use shared styles (recommended for notebooks)</span>
<span class="n">configure_formatter</span><span class="p">(</span><span class="n">use_shared_styles</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="c1"># Disable shared styles (each DataFrame includes its own styles)</span>
<span class="n">configure_formatter</span><span class="p">(</span><span class="n">use_shared_styles</span><span class="o">=</span><span class="kc">False</span><span class="p">)</span>
</pre></div>
</div>
<p>When <code class="docutils literal notranslate"><span class="pre">use_shared_styles=True</span></code>:
- CSS styles and JavaScript are included only once per notebook session
- This reduces HTML output size and prevents style duplication
- Improves rendering performance with many DataFrames
- Applies consistent styling across all DataFrames</p>
</section>
<section id="creating-a-custom-formatter">
<h2>Creating a Custom Formatter<a class="headerlink" href="#creating-a-custom-formatter" title="Link to this heading"></a></h2>
<p>For complete control over rendering, you can implement a custom formatter:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">Formatter</span><span class="p">,</span> <span class="n">get_formatter</span>
<span class="k">class</span><span class="w"> </span><span class="nc">MyFormatter</span><span class="p">(</span><span class="n">Formatter</span><span class="p">):</span>
<span class="k">def</span><span class="w"> </span><span class="nf">format_html</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batches</span><span class="p">,</span> <span class="n">schema</span><span class="p">,</span> <span class="n">has_more</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">table_uuid</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="c1"># Create your custom HTML here</span>
<span class="n">html</span> <span class="o">=</span> <span class="s2">&quot;&lt;div class=&#39;my-custom-table&#39;&gt;&quot;</span>
<span class="c1"># ... formatting logic ...</span>
<span class="n">html</span> <span class="o">+=</span> <span class="s2">&quot;&lt;/div&gt;&quot;</span>
<span class="k">return</span> <span class="n">html</span>
<span class="c1"># Set as the global formatter</span>
<span class="n">configure_formatter</span><span class="p">(</span><span class="n">formatter_class</span><span class="o">=</span><span class="n">MyFormatter</span><span class="p">)</span>
<span class="c1"># Or use the formatter just for specific operations</span>
<span class="n">formatter</span> <span class="o">=</span> <span class="n">get_formatter</span><span class="p">()</span>
<span class="n">custom_html</span> <span class="o">=</span> <span class="n">formatter</span><span class="o">.</span><span class="n">format_html</span><span class="p">(</span><span class="n">batches</span><span class="p">,</span> <span class="n">schema</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="managing-formatters">
<h2>Managing Formatters<a class="headerlink" href="#managing-formatters" title="Link to this heading"></a></h2>
<p>Reset to default formatting:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">reset_formatter</span>
<span class="c1"># Reset to default settings</span>
<span class="n">reset_formatter</span><span class="p">()</span>
</pre></div>
</div>
<p>Get the current formatter settings:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">get_formatter</span>
<span class="n">formatter</span> <span class="o">=</span> <span class="n">get_formatter</span><span class="p">()</span>
<span class="nb">print</span><span class="p">(</span><span class="n">formatter</span><span class="o">.</span><span class="n">max_rows</span><span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="n">formatter</span><span class="o">.</span><span class="n">theme</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="contextual-formatting">
<h2>Contextual Formatting<a class="headerlink" href="#contextual-formatting" title="Link to this heading"></a></h2>
<p>You can also use a context manager to temporarily change formatting settings:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span><span class="w"> </span><span class="nn">datafusion.html_formatter</span><span class="w"> </span><span class="kn">import</span> <span class="n">formatting_context</span>
<span class="c1"># Default formatting</span>
<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
<span class="c1"># Temporarily use different formatting</span>
<span class="k">with</span> <span class="n">formatting_context</span><span class="p">(</span><span class="n">max_rows</span><span class="o">=</span><span class="mi">100</span><span class="p">,</span> <span class="n">theme</span><span class="o">=</span><span class="s2">&quot;dark&quot;</span><span class="p">):</span>
<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span> <span class="c1"># Will use the temporary settings</span>
<span class="c1"># Back to default formatting</span>
<span class="n">df</span><span class="o">.</span><span class="n">show</span><span class="p">()</span>
</pre></div>
</div>
</section>
<section id="memory-and-display-controls">
<h2>Memory and Display Controls<a class="headerlink" href="#memory-and-display-controls" title="Link to this heading"></a></h2>
<p>You can control how much data is displayed and how much memory is used for rendering:</p>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">configure_formatter</span><span class="p">(</span>
<span class="n">max_memory_bytes</span><span class="o">=</span><span class="mi">4</span> <span class="o">*</span> <span class="mi">1024</span> <span class="o">*</span> <span class="mi">1024</span><span class="p">,</span> <span class="c1"># 4MB maximum memory for display</span>
<span class="n">min_rows_display</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="c1"># Always show at least 50 rows</span>
<span class="n">repr_rows</span><span class="o">=</span><span class="mi">20</span> <span class="c1"># Show 20 rows in __repr__ output</span>
<span class="p">)</span>
</pre></div>
</div>
<p>These parameters help balance comprehensive data display against performance considerations.</p>
</section>
<section id="best-practices">
<h2>Best Practices<a class="headerlink" href="#best-practices" title="Link to this heading"></a></h2>
<ol class="arabic simple">
<li><p><strong>Global Configuration</strong>: Use <code class="docutils literal notranslate"><span class="pre">configure_formatter()</span></code> at the beginning of your notebook to set up consistent formatting for all DataFrames.</p></li>
<li><p><strong>Memory Management</strong>: Set appropriate <code class="docutils literal notranslate"><span class="pre">max_memory_bytes</span></code> limits to prevent performance issues with large datasets.</p></li>
<li><p><strong>Shared Styles</strong>: Keep <code class="docutils literal notranslate"><span class="pre">use_shared_styles=True</span></code> (default) for better performance in notebooks with multiple DataFrames.</p></li>
<li><p><strong>Reset When Needed</strong>: Call <code class="docutils literal notranslate"><span class="pre">reset_formatter()</span></code> when you want to start fresh with default settings.</p></li>
<li><p><strong>Cell Expansion</strong>: Use <code class="docutils literal notranslate"><span class="pre">enable_cell_expansion=True</span></code> when cells might contain longer content that users may want to see in full.</p></li>
</ol>
</section>
<section id="additional-resources">
<h2>Additional Resources<a class="headerlink" href="#additional-resources" title="Link to this heading"></a></h2>
<ul class="simple">
<li><p><a class="reference internal" href="index.html"><span class="doc">DataFrames</span></a> - Complete guide to using DataFrames</p></li>
<li><p><a class="reference internal" href="../io/index.html"><span class="doc">IO</span></a> - I/O Guide for reading data from various sources</p></li>
<li><p><a class="reference internal" href="../data-sources.html"><span class="doc">Data Sources</span></a> - Comprehensive data sources guide</p></li>
<li><p><a class="reference internal" href="../io/csv.html#io-csv"><span class="std std-ref">CSV</span></a> - CSV file reading</p></li>
<li><p><a class="reference internal" href="../io/parquet.html#io-parquet"><span class="std std-ref">Parquet</span></a> - Parquet file reading</p></li>
<li><p><a class="reference internal" href="../io/json.html#io-json"><span class="std std-ref">JSON</span></a> - JSON file reading</p></li>
<li><p><a class="reference internal" href="../io/avro.html#io-avro"><span class="std std-ref">Avro</span></a> - Avro file reading</p></li>
<li><p><a class="reference internal" href="../io/table_provider.html#io-custom-table-provider"><span class="std std-ref">Custom Table Provider</span></a> - Custom table providers</p></li>
<li><p><a class="reference external" href="https://arrow.apache.org/datafusion-python/api/index.html">API Reference</a> - Full API reference</p></li>
</ul>
</section>
</section>
</div>
<!-- Previous / next buttons -->
<div class='prev-next-area'>
<a class='left-prev' id="prev-link" href="index.html" title="previous page">
<i class="fas fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">DataFrames</p>
</div>
</a>
<a class='right-next' id="next-link" href="../common-operations/index.html" title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Common Operations</p>
</div>
<i class="fas fa-angle-right"></i>
</a>
</div>
</main>
</div>
</div>
<script src="../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script>
<!-- Based on pydata_sphinx_theme/footer.html -->
<footer class="footer mt-5 mt-md-0">
<div class="container">
<div class="footer-item">
<p class="copyright">
&copy; Copyright 2019-2024, Apache Software Foundation.<br>
</p>
</div>
<div class="footer-item">
<p class="sphinx-version">
Created using <a href="http://sphinx-doc.org/">Sphinx</a> 8.1.3.<br>
</p>
</div>
<div class="footer-item">
<p>Apache Arrow DataFusion, Arrow DataFusion, Apache, the Apache feather logo, and the Apache Arrow DataFusion project logo</p>
<p>are either registered trademarks or trademarks of The Apache Software Foundation in the United States and other countries.</p>
</div>
</div>
</footer>
</body>
</html>