{% extends "layout.html" %}
{% set title = 'skrub: Prepping tables for machine learning' %}

{%- block extrahead %}
    {{ super() }}
    {# Add here landing-page specific stuff that goes in the header (eg css) #}
{%- endblock extrahead %}

{% block docs_navbar %}
    {{ super() }}

    {# We add the full-width banner below the navbar, as the div there is
still full-width (unlike the article) #}
    <div class="container-fluid sk-landing-bg">
    <div class="container sk-landing-container">
	<div class="row">
	<div class="col-md-6 mb-3 mb-md-0">
	    <h1 class="sk-landing-header text-white text-monospace">skrub</h1>
	    <h4 class="sk-landing-subheader text-white font-italic mb-3"><i>Prepping tables for machine learning</i></h4>
      <a class="btn sk-btn-orange mb-1" href="{{ pathto('auto_examples/00_getting_started') }}" role="button">Getting started</code></a>
      <a class="btn sk-btn-orange mb-1" href="{{ pathto('CHANGES') }}" role="button">Recent changes</a>
	</div>
	<div class="col-md-6 d-flex">
	    <ul class="sk-landing-header-body">
	    <li>Built for scikit-learn, Python</li>
	    <li>Robust to dirty data</li>
	    <li>Easy learning on pandas and polars dataframes</li>
	    </ul>
	</div>
	</div>
    </div>
    </div>
{% endblock docs_navbar %}

{% block docs_main %}
<div class="container-fluid schema-container">
    <img src="_static/skrub_pipeline.svg">
</div>

<article class="bd-article" role="main">
<div class="bd-content">
<div class="landing-container">

<div class="container-fluid">
  <div class="row justify-content-md-center">
    <div class="col-lg-4">
      <div class="sd-card sd-shadow-sm card-landing">
        <div class="card-body">
          <h4 class="card-title"><a href="{{ pathto('assembling') }}">Assembling</a></h4>
    <p><a class="reference internal" href="generated/skrub.fuzzy_join.html"
title="skrub.fuzzy_join"><code class="xref py py-func docutils literal
notranslate"><span class="pre">fuzzy_join()</span></code></a>: Joining
tables on non-normalized categories with approximate matching. <a
class="reference internal" href="{{ pathto('auto_examples/04_fuzzy_joining') }}"><span class="std std-ref">Example</span></a></p>
<p><a class="reference internal"
href="generated/skrub.Joiner.html"
title="skrub.Joiner"><code class="xref py py-class docutils
literal notranslate"><span class="pre">Joiner</span></code></a>,
<a class="reference internal"
href="generated/skrub.AggJoiner.html"
title="skrub.AggJoiner"><code class="xref py py-class docutils
literal notranslate"><span class="pre">AggJoiner</span></code></a>: transformers for joining multiple tables together. <a class="reference internal" href="{{ pathto('auto_examples/04_fuzzy_joining') }}"><span class="std std-ref">Example</span></a></p>
    </div>
  </div>
</div>
<div class="col-lg-4">
  <div class="sd-card sd-shadow-sm card-landing">
    <div class="card-body">
      <h4 class="card-title"><a href="{{ pathto('encoding') }}">Encoding</a></h4><p><a class="reference
internal"
href="generated/skrub.TableVectorizer.html#skrub.TableVectorizer"
title="skrub.TableVectorizer"><code class="xref py py-class docutils
literal notranslate"><span class="pre">TableVectorizer</span></code></a>:
<strong>turn a pandas dataframe into a numerical array</strong> for
machine learning. <a class="reference internal" href="auto_examples/01_encodings.html#example-table-vectorizer"><span class="std std-ref">Example</span></a></p>
<p><a class="reference internal"
href="generated/skrub.GapEncoder.html#skrub.GapEncoder"
title="skrub.GapEncoder"><code class="xref py py-class docutils literal
notranslate"><span class="pre">GapEncoder</span></code></a>:
OneHotEncoder but robust to typos or non-normalized categories. <a
class="reference internal" href="auto_examples/02_feature_interpretation_with_gapencoder.html#example-gap-encoder"><span class="std std-ref">Example</span></a></p>
    </div>
  </div>
</div>
<div class="col-lg-4">
  <div class="sd-card sd-shadow-sm card-landing">
    <div class="card-body">
      <h4 class="card-title"><a href="{{ pathto('cleaning') }}">Cleaning</a></h4><p><a class="reference
internal" href="generated/skrub.deduplicate.html#skrub.deduplicate"
title="skrub.deduplicate"><code class="xref py py-func docutils literal
notranslate"><span class="pre">deduplicate()</span></code></a>: merge
categories of similar morphology (spelling). <a class="reference internal" href="auto_examples/05_deduplication.html"><span class="std std-ref">Example</span></a></p>
        </div>
      </div>
    </div>
  </div>
</div>
</article>

<div class="container-fluid" style="max-width: 58rem;">
    <div class="sd-card sd-shadow-sm card-landing" style="border: 1px solid var(--pst-color-border, #d1d5da);">
    <div class="card-body">
        <div style="display: flex; justify-content: center; padding-bottom: 0.5rem;">
    <h4 class="card-title">Less data wrangling, more machine learning</h4>
        </div>
      <div>
          <p>
            <a class="reference
              internal"
              href="generated/skrub.tabular_learner.html#skrub.tabular_learner"
              title="skrub.tabular_learner"><code class="xref py py-class docutils
              literal notranslate"><span class="pre">tabular_learner</span></code></a>:
              easily create tabular-learning pipelines that wrangle complex dataframes.
          </p>
      </div>
      <details>
	<summary>Given, a complex dataframe
	<code class="docutils literal notranslate"><span
class="pre">df</span></code>: <i>(expand for full code)</i></summary>
      <div class="doctest highlight-default notranslate">
        <div class="highlight">
          <pre style="overflow-x: auto;">
<span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">skrub.datasets</span> <span class="kn">import</span> <span class="n">fetch_employee_salaries</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">dataset</span> <span class="o">=</span> <span class="n">fetch_employee_salaries</span><span class="p">()</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">df</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">X</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">y</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">y</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">df</span></pre>
        </div>
      </div>
    </details>
<div class="output_subarea output_html rendered_html output_result">
<div>
<style scoped="">
    .dataframe tbody tr th:only-of-type {
        vertical-align: middle;
    }

    .dataframe tbody tr th {
        vertical-align: top;
    }

    .dataframe thead th {
        text-align: right;
    }
</style>
<table border="1" class="dataframe">
  <thead>
    <tr style="text-align: right;">
      <th></th>
      <th>gender</th>
      <th>department</th>
      <th>department_name</th>
      <th>division</th>
      <th>assignment_category</th>
      <th>employee_position_title</th>
      <th>date_first_hired</th>
      <th>year_first_hired</th>
    </tr>
  </thead>
  <tbody>
    <tr>
      <th>0</th>
      <td>F</td>
      <td>POL</td>
      <td>Department of Police</td>
      <td>MSB Information Mgmt and...</td>
      <td>Fulltime-Regular</td>
      <td>Office Services Coordinator</td>
      <td>09/22/1986</td>
      <td>1986</td>
    </tr>
    <tr>
      <th>1</th>
      <td>M</td>
      <td>POL</td>
      <td>Department of Police</td>
      <td>ISB Major Crimes...</td>
      <td>Fulltime-Regular</td>
      <td>Master Police Officer</td>
      <td>09/12/1988</td>
      <td>1988</td>
    </tr>
    <tr>
      <th>...</th>
      <td>...</td>
      <td>...</td>
      <td>...</td>
      <td>...</td>
      <td>...</td>
      <td>...</td>
      <td>...</td>
      <td>...</td>
    </tr>
    <tr>
      <th>9226</th>
      <td>M</td>
      <td>CCL</td>
      <td>County Council</td>
      <td>Council Central Staff</td>
      <td>Fulltime-Regular</td>
      <td>Manager II</td>
      <td>09/05/2006</td>
      <td>2006</td>
    </tr>
    <tr>
      <th>9227</th>
      <td>M</td>
      <td>DLC</td>
      <td>Department of Liquor Control</td>
      <td>Licensure, Regulation...</td>
      <td>Fulltime-Regular</td>
      <td>Alcohol/Tobacco Enforcement Specialist II</td>
      <td>01/30/2012</td>
      <td>2012</td>
    </tr>
  </tbody>
</table>
</div>
</div>
      <div class="doctest highlight-default notranslate">
        <div class="highlight">
          <pre style="overflow-x: auto;">
<span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">cross_val_score</span>
<span class="gp">&gt;&gt;&gt; </span><span class="kn">from</span> <span class="nn">skrub</span> <span class="kn">import</span> <span class="n">tabular_learner</span>
<span class="gp">&gt;&gt;&gt; </span><span class="n">cross_val_score</span><span class="p">(</span><span class="n">tabular_learner</span><span class="p">(</span><span class="s1">&#39;regressor&#39;</span><span class="p">),</span> </span><span class="n">df</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
<span class="go">array([0.89370447, 0.89279068, 0.92282557, 0.92319094, 0.92162666])</span></pre>
        </div>
      </div>
    </div>
  </div>
</div>


{# So far, no article footer. Maybe this is brutal #}
</div>
</div>
{% endblock docs_main %}

{%- block footer %}
{%- endblock footer %}