Google Git
Sign in
apache / incubator-teaclave-website / refs/heads/asf-site / . / api-docs / crates-enclave / src / rusty_machine / learning / naive_bayes.rs.html
blob: 77276529241d78e667f1b3df716ab46dcd59d4d8 [file] [log] [blame]
<!DOCTYPE html><html lang="en"><head><meta charset="utf-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><meta name="generator" content="rustdoc"><meta name="description" content="Source of the Rust file `/root/.cargo/git/checkouts/incubator-teaclave-crates-c8106113f74feefc/ede1f68/rusty-machine/src/learning/naive_bayes.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>naive_bayes.rs - source</title><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Regular.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../FiraSans-Medium.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Regular.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceSerif4-Bold.ttf.woff2"><link rel="preload" as="font" type="font/woff2" crossorigin href="../../../SourceCodePro-Semibold.ttf.woff2"><link rel="stylesheet" href="../../../normalize.css"><link rel="stylesheet" href="../../../rustdoc.css" id="mainThemeStyle"><link rel="stylesheet" href="../../../ayu.css" disabled><link rel="stylesheet" href="../../../dark.css" disabled><link rel="stylesheet" href="../../../light.css" id="themeStyle"><script id="default-settings" ></script><script src="../../../storage.js"></script><script defer src="../../../source-script.js"></script><script defer src="../../../source-files.js"></script><script defer src="../../../main.js"></script><noscript><link rel="stylesheet" href="../../../noscript.css"></noscript><link rel="alternate icon" type="image/png" href="../../../favicon-16x16.png"><link rel="alternate icon" type="image/png" href="../../../favicon-32x32.png"><link rel="icon" type="image/svg+xml" href="../../../favicon.svg"></head><body class="rustdoc source"><!--[if lte IE 11]><div class="warning">This old browser is unsupported and will most likely display funky things.</div><![endif]--><nav class="sidebar"><a class="sidebar-logo" href="../../../rusty_machine/index.html"><div class="logo-container"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></div></a></nav><main><div class="width-limiter"><nav class="sub"><a class="sub-logo-container" href="../../../rusty_machine/index.html"><img class="rust-logo" src="../../../rust-logo.svg" alt="logo"></a><form class="search-form"><div class="search-container"><span></span><input class="search-input" name="search" autocomplete="off" spellcheck="false" placeholder="Click or press ‘S’ to search, ‘?’ for more options…" type="search"><div id="help-button" title="help" tabindex="-1"><a href="../../../help.html">?</a></div><div id="settings-menu" tabindex="-1"><a href="../../../settings.html" title="settings"><img width="22" height="22" alt="Change settings" src="../../../wheel.svg"></a></div></div></form></nav><section id="main-content" class="content"><div class="example-wrap"><pre class="src-line-numbers"><span id="1">1</span>
<span id="2">2</span>
<span id="3">3</span>
<span id="4">4</span>
<span id="5">5</span>
<span id="6">6</span>
<span id="7">7</span>
<span id="8">8</span>
<span id="9">9</span>
<span id="10">10</span>
<span id="11">11</span>
<span id="12">12</span>
<span id="13">13</span>
<span id="14">14</span>
<span id="15">15</span>
<span id="16">16</span>
<span id="17">17</span>
<span id="18">18</span>
<span id="19">19</span>
<span id="20">20</span>
<span id="21">21</span>
<span id="22">22</span>
<span id="23">23</span>
<span id="24">24</span>
<span id="25">25</span>
<span id="26">26</span>
<span id="27">27</span>
<span id="28">28</span>
<span id="29">29</span>
<span id="30">30</span>
<span id="31">31</span>
<span id="32">32</span>
<span id="33">33</span>
<span id="34">34</span>
<span id="35">35</span>
<span id="36">36</span>
<span id="37">37</span>
<span id="38">38</span>
<span id="39">39</span>
<span id="40">40</span>
<span id="41">41</span>
<span id="42">42</span>
<span id="43">43</span>
<span id="44">44</span>
<span id="45">45</span>
<span id="46">46</span>
<span id="47">47</span>
<span id="48">48</span>
<span id="49">49</span>
<span id="50">50</span>
<span id="51">51</span>
<span id="52">52</span>
<span id="53">53</span>
<span id="54">54</span>
<span id="55">55</span>
<span id="56">56</span>
<span id="57">57</span>
<span id="58">58</span>
<span id="59">59</span>
<span id="60">60</span>
<span id="61">61</span>
<span id="62">62</span>
<span id="63">63</span>
<span id="64">64</span>
<span id="65">65</span>
<span id="66">66</span>
<span id="67">67</span>
<span id="68">68</span>
<span id="69">69</span>
<span id="70">70</span>
<span id="71">71</span>
<span id="72">72</span>
<span id="73">73</span>
<span id="74">74</span>
<span id="75">75</span>
<span id="76">76</span>
<span id="77">77</span>
<span id="78">78</span>
<span id="79">79</span>
<span id="80">80</span>
<span id="81">81</span>
<span id="82">82</span>
<span id="83">83</span>
<span id="84">84</span>
<span id="85">85</span>
<span id="86">86</span>
<span id="87">87</span>
<span id="88">88</span>
<span id="89">89</span>
<span id="90">90</span>
<span id="91">91</span>
<span id="92">92</span>
<span id="93">93</span>
<span id="94">94</span>
<span id="95">95</span>
<span id="96">96</span>
<span id="97">97</span>
<span id="98">98</span>
<span id="99">99</span>
<span id="100">100</span>
<span id="101">101</span>
<span id="102">102</span>
<span id="103">103</span>
<span id="104">104</span>
<span id="105">105</span>
<span id="106">106</span>
<span id="107">107</span>
<span id="108">108</span>
<span id="109">109</span>
<span id="110">110</span>
<span id="111">111</span>
<span id="112">112</span>
<span id="113">113</span>
<span id="114">114</span>
<span id="115">115</span>
<span id="116">116</span>
<span id="117">117</span>
<span id="118">118</span>
<span id="119">119</span>
<span id="120">120</span>
<span id="121">121</span>
<span id="122">122</span>
<span id="123">123</span>
<span id="124">124</span>
<span id="125">125</span>
<span id="126">126</span>
<span id="127">127</span>
<span id="128">128</span>
<span id="129">129</span>
<span id="130">130</span>
<span id="131">131</span>
<span id="132">132</span>
<span id="133">133</span>
<span id="134">134</span>
<span id="135">135</span>
<span id="136">136</span>
<span id="137">137</span>
<span id="138">138</span>
<span id="139">139</span>
<span id="140">140</span>
<span id="141">141</span>
<span id="142">142</span>
<span id="143">143</span>
<span id="144">144</span>
<span id="145">145</span>
<span id="146">146</span>
<span id="147">147</span>
<span id="148">148</span>
<span id="149">149</span>
<span id="150">150</span>
<span id="151">151</span>
<span id="152">152</span>
<span id="153">153</span>
<span id="154">154</span>
<span id="155">155</span>
<span id="156">156</span>
<span id="157">157</span>
<span id="158">158</span>
<span id="159">159</span>
<span id="160">160</span>
<span id="161">161</span>
<span id="162">162</span>
<span id="163">163</span>
<span id="164">164</span>
<span id="165">165</span>
<span id="166">166</span>
<span id="167">167</span>
<span id="168">168</span>
<span id="169">169</span>
<span id="170">170</span>
<span id="171">171</span>
<span id="172">172</span>
<span id="173">173</span>
<span id="174">174</span>
<span id="175">175</span>
<span id="176">176</span>
<span id="177">177</span>
<span id="178">178</span>
<span id="179">179</span>
<span id="180">180</span>
<span id="181">181</span>
<span id="182">182</span>
<span id="183">183</span>
<span id="184">184</span>
<span id="185">185</span>
<span id="186">186</span>
<span id="187">187</span>
<span id="188">188</span>
<span id="189">189</span>
<span id="190">190</span>
<span id="191">191</span>
<span id="192">192</span>
<span id="193">193</span>
<span id="194">194</span>
<span id="195">195</span>
<span id="196">196</span>
<span id="197">197</span>
<span id="198">198</span>
<span id="199">199</span>
<span id="200">200</span>
<span id="201">201</span>
<span id="202">202</span>
<span id="203">203</span>
<span id="204">204</span>
<span id="205">205</span>
<span id="206">206</span>
<span id="207">207</span>
<span id="208">208</span>
<span id="209">209</span>
<span id="210">210</span>
<span id="211">211</span>
<span id="212">212</span>
<span id="213">213</span>
<span id="214">214</span>
<span id="215">215</span>
<span id="216">216</span>
<span id="217">217</span>
<span id="218">218</span>
<span id="219">219</span>
<span id="220">220</span>
<span id="221">221</span>
<span id="222">222</span>
<span id="223">223</span>
<span id="224">224</span>
<span id="225">225</span>
<span id="226">226</span>
<span id="227">227</span>
<span id="228">228</span>
<span id="229">229</span>
<span id="230">230</span>
<span id="231">231</span>
<span id="232">232</span>
<span id="233">233</span>
<span id="234">234</span>
<span id="235">235</span>
<span id="236">236</span>
<span id="237">237</span>
<span id="238">238</span>
<span id="239">239</span>
<span id="240">240</span>
<span id="241">241</span>
<span id="242">242</span>
<span id="243">243</span>
<span id="244">244</span>
<span id="245">245</span>
<span id="246">246</span>
<span id="247">247</span>
<span id="248">248</span>
<span id="249">249</span>
<span id="250">250</span>
<span id="251">251</span>
<span id="252">252</span>
<span id="253">253</span>
<span id="254">254</span>
<span id="255">255</span>
<span id="256">256</span>
<span id="257">257</span>
<span id="258">258</span>
<span id="259">259</span>
<span id="260">260</span>
<span id="261">261</span>
<span id="262">262</span>
<span id="263">263</span>
<span id="264">264</span>
<span id="265">265</span>
<span id="266">266</span>
<span id="267">267</span>
<span id="268">268</span>
<span id="269">269</span>
<span id="270">270</span>
<span id="271">271</span>
<span id="272">272</span>
<span id="273">273</span>
<span id="274">274</span>
<span id="275">275</span>
<span id="276">276</span>
<span id="277">277</span>
<span id="278">278</span>
<span id="279">279</span>
<span id="280">280</span>
<span id="281">281</span>
<span id="282">282</span>
<span id="283">283</span>
<span id="284">284</span>
<span id="285">285</span>
<span id="286">286</span>
<span id="287">287</span>
<span id="288">288</span>
<span id="289">289</span>
<span id="290">290</span>
<span id="291">291</span>
<span id="292">292</span>
<span id="293">293</span>
<span id="294">294</span>
<span id="295">295</span>
<span id="296">296</span>
<span id="297">297</span>
<span id="298">298</span>
<span id="299">299</span>
<span id="300">300</span>
<span id="301">301</span>
<span id="302">302</span>
<span id="303">303</span>
<span id="304">304</span>
<span id="305">305</span>
<span id="306">306</span>
<span id="307">307</span>
<span id="308">308</span>
<span id="309">309</span>
<span id="310">310</span>
<span id="311">311</span>
<span id="312">312</span>
<span id="313">313</span>
<span id="314">314</span>
<span id="315">315</span>
<span id="316">316</span>
<span id="317">317</span>
<span id="318">318</span>
<span id="319">319</span>
<span id="320">320</span>
<span id="321">321</span>
<span id="322">322</span>
<span id="323">323</span>
<span id="324">324</span>
<span id="325">325</span>
<span id="326">326</span>
<span id="327">327</span>
<span id="328">328</span>
<span id="329">329</span>
<span id="330">330</span>
<span id="331">331</span>
<span id="332">332</span>
<span id="333">333</span>
<span id="334">334</span>
<span id="335">335</span>
<span id="336">336</span>
<span id="337">337</span>
<span id="338">338</span>
<span id="339">339</span>
<span id="340">340</span>
<span id="341">341</span>
<span id="342">342</span>
<span id="343">343</span>
<span id="344">344</span>
<span id="345">345</span>
<span id="346">346</span>
<span id="347">347</span>
<span id="348">348</span>
<span id="349">349</span>
<span id="350">350</span>
<span id="351">351</span>
<span id="352">352</span>
<span id="353">353</span>
<span id="354">354</span>
<span id="355">355</span>
<span id="356">356</span>
<span id="357">357</span>
<span id="358">358</span>
<span id="359">359</span>
<span id="360">360</span>
<span id="361">361</span>
<span id="362">362</span>
<span id="363">363</span>
<span id="364">364</span>
<span id="365">365</span>
<span id="366">366</span>
<span id="367">367</span>
<span id="368">368</span>
<span id="369">369</span>
<span id="370">370</span>
<span id="371">371</span>
<span id="372">372</span>
<span id="373">373</span>
<span id="374">374</span>
<span id="375">375</span>
<span id="376">376</span>
<span id="377">377</span>
<span id="378">378</span>
<span id="379">379</span>
<span id="380">380</span>
<span id="381">381</span>
<span id="382">382</span>
<span id="383">383</span>
<span id="384">384</span>
<span id="385">385</span>
<span id="386">386</span>
<span id="387">387</span>
<span id="388">388</span>
<span id="389">389</span>
<span id="390">390</span>
<span id="391">391</span>
<span id="392">392</span>
<span id="393">393</span>
<span id="394">394</span>
<span id="395">395</span>
<span id="396">396</span>
<span id="397">397</span>
<span id="398">398</span>
<span id="399">399</span>
<span id="400">400</span>
<span id="401">401</span>
<span id="402">402</span>
<span id="403">403</span>
<span id="404">404</span>
<span id="405">405</span>
<span id="406">406</span>
<span id="407">407</span>
<span id="408">408</span>
<span id="409">409</span>
<span id="410">410</span>
<span id="411">411</span>
<span id="412">412</span>
<span id="413">413</span>
<span id="414">414</span>
<span id="415">415</span>
<span id="416">416</span>
<span id="417">417</span>
<span id="418">418</span>
<span id="419">419</span>
<span id="420">420</span>
<span id="421">421</span>
<span id="422">422</span>
<span id="423">423</span>
<span id="424">424</span>
<span id="425">425</span>
<span id="426">426</span>
<span id="427">427</span>
<span id="428">428</span>
<span id="429">429</span>
<span id="430">430</span>
<span id="431">431</span>
<span id="432">432</span>
<span id="433">433</span>
<span id="434">434</span>
<span id="435">435</span>
<span id="436">436</span>
<span id="437">437</span>
<span id="438">438</span>
<span id="439">439</span>
<span id="440">440</span>
<span id="441">441</span>
<span id="442">442</span>
<span id="443">443</span>
<span id="444">444</span>
<span id="445">445</span>
<span id="446">446</span>
<span id="447">447</span>
<span id="448">448</span>
<span id="449">449</span>
<span id="450">450</span>
<span id="451">451</span>
<span id="452">452</span>
<span id="453">453</span>
<span id="454">454</span>
<span id="455">455</span>
<span id="456">456</span>
<span id="457">457</span>
<span id="458">458</span>
<span id="459">459</span>
<span id="460">460</span>
<span id="461">461</span>
<span id="462">462</span>
<span id="463">463</span>
<span id="464">464</span>
<span id="465">465</span>
<span id="466">466</span>
<span id="467">467</span>
<span id="468">468</span>
<span id="469">469</span>
<span id="470">470</span>
<span id="471">471</span>
<span id="472">472</span>
<span id="473">473</span>
<span id="474">474</span>
<span id="475">475</span>
<span id="476">476</span>
<span id="477">477</span>
<span id="478">478</span>
<span id="479">479</span>
<span id="480">480</span>
<span id="481">481</span>
<span id="482">482</span>
<span id="483">483</span>
<span id="484">484</span>
<span id="485">485</span>
<span id="486">486</span>
<span id="487">487</span>
<span id="488">488</span>
<span id="489">489</span>
<span id="490">490</span>
<span id="491">491</span>
<span id="492">492</span>
<span id="493">493</span>
<span id="494">494</span>
<span id="495">495</span>
<span id="496">496</span>
<span id="497">497</span>
<span id="498">498</span>
<span id="499">499</span>
<span id="500">500</span>
<span id="501">501</span>
<span id="502">502</span>
<span id="503">503</span>
<span id="504">504</span>
<span id="505">505</span>
</pre><pre class="rust"><code><span class="doccomment">//! Naive Bayes Classifiers
//!
//! The classifier supports Gaussian, Bernoulli and Multinomial distributions.
//!
//! A naive Bayes classifier works by treating the features of each input as independent
//! observations. Under this assumption we utilize Bayes&#39; rule to compute the
//! probability that each input belongs to a given class.
//!
//! # Examples
//!
//! ```
//! use rusty_machine::learning::naive_bayes::{NaiveBayes, Gaussian};
//! use rusty_machine::linalg::Matrix;
//! use rusty_machine::learning::SupModel;
//!
//! let inputs = Matrix::new(6, 2, vec![1.0, 1.1,
//! 1.1, 0.9,
//! 2.2, 2.3,
//! 2.5, 2.7,
//! 5.2, 4.3,
//! 6.2, 7.3]);
//!
//! let targets = Matrix::new(6,3, vec![1.0, 0.0, 0.0,
//! 1.0, 0.0, 0.0,
//! 0.0, 1.0, 0.0,
//! 0.0, 1.0, 0.0,
//! 0.0, 0.0, 1.0,
//! 0.0, 0.0, 1.0]);
//!
//! // Create a Gaussian Naive Bayes classifier.
//! let mut model = NaiveBayes::&lt;Gaussian&gt;::new();
//!
//! // Train the model.
//! model.train(&amp;inputs, &amp;targets).unwrap();
//!
//! // Predict the classes on the input data
//! let outputs = model.predict(&amp;inputs).unwrap();
//!
//! // Will output the target classes - otherwise our classifier is bad!
//! println!(&quot;Final outputs --\n{}&quot;, outputs);
//! ```
</span><span class="kw">use </span>linalg::{Matrix, Axes, BaseMatrix, BaseMatrixMut};
<span class="kw">use </span>learning::{LearningResult, SupModel};
<span class="kw">use </span>learning::error::{Error, ErrorKind};
<span class="kw">use </span>rulinalg::utils;
<span class="kw">use </span>std::f64::consts::PI;
<span class="doccomment">/// The Naive Bayes model.
</span><span class="attribute">#[derive(Debug, Default)]
</span><span class="kw">pub struct </span>NaiveBayes&lt;T: Distribution&gt; {
distr: <span class="prelude-ty">Option</span>&lt;T&gt;,
cluster_count: <span class="prelude-ty">Option</span>&lt;usize&gt;,
class_prior: <span class="prelude-ty">Option</span>&lt;Vec&lt;f64&gt;&gt;,
class_counts: Vec&lt;usize&gt;,
}
<span class="kw">impl</span>&lt;T: Distribution&gt; NaiveBayes&lt;T&gt; {
<span class="doccomment">/// Create a new NaiveBayes model from a given
/// distribution.
///
/// # Examples
///
/// ```
/// use rusty_machine::learning::naive_bayes::{NaiveBayes, Gaussian};
///
/// // Create a new Gaussian Naive Bayes model.
/// let _ = NaiveBayes::&lt;Gaussian&gt;::new();
/// ```
</span><span class="kw">pub fn </span>new() -&gt; NaiveBayes&lt;T&gt; {
NaiveBayes {
distr: <span class="prelude-val">None</span>,
cluster_count: <span class="prelude-val">None</span>,
class_prior: <span class="prelude-val">None</span>,
class_counts: Vec::new(),
}
}
<span class="doccomment">/// Get the cluster count for this model.
///
/// Returns an option which is `None` until the model has been trained.
</span><span class="kw">pub fn </span>cluster_count(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span>usize&gt; {
<span class="self">self</span>.cluster_count.as_ref()
}
<span class="doccomment">/// Get the class prior distribution for this model.
///
/// Returns an option which is `None` until the model has been trained.
</span><span class="kw">pub fn </span>class_prior(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span>Vec&lt;f64&gt;&gt; {
<span class="self">self</span>.class_prior.as_ref()
}
<span class="doccomment">/// Get the distribution for this model.
///
/// Returns an option which is `None` until the model has been trained.
</span><span class="kw">pub fn </span>distr(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="prelude-ty">Option</span>&lt;<span class="kw-2">&amp;</span>T&gt; {
<span class="self">self</span>.distr.as_ref()
}
}
<span class="doccomment">/// Train and predict from the Naive Bayes model.
///
/// The input matrix must be rows made up of features.
/// The target matrix should have indicator vectors in each row specifying
/// the input class. e.g. [[1,0,0],[0,0,1]] shows class 1 first, then class 3.
</span><span class="kw">impl</span>&lt;T: Distribution&gt; SupModel&lt;Matrix&lt;f64&gt;, Matrix&lt;f64&gt;&gt; <span class="kw">for </span>NaiveBayes&lt;T&gt; {
<span class="doccomment">/// Train the model using inputs and targets.
</span><span class="kw">fn </span>train(<span class="kw-2">&amp;mut </span><span class="self">self</span>, inputs: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, targets: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;) -&gt; LearningResult&lt;()&gt; {
<span class="self">self</span>.distr = <span class="prelude-val">Some</span>(T::from_model_params(targets.cols(), inputs.cols()));
<span class="self">self</span>.update_params(inputs, targets)
}
<span class="doccomment">/// Predict output from inputs.
</span><span class="kw">fn </span>predict(<span class="kw-2">&amp;</span><span class="self">self</span>, inputs: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;) -&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt; {
<span class="kw">let </span>log_probs = <span class="self">self</span>.get_log_probs(inputs)<span class="question-mark">?</span>;
<span class="kw">let </span>input_classes = NaiveBayes::&lt;T&gt;::get_classes(log_probs);
<span class="kw">if let </span><span class="prelude-val">Some</span>(cluster_count) = <span class="self">self</span>.cluster_count {
<span class="kw">let </span><span class="kw-2">mut </span>class_data = Vec::with_capacity(inputs.rows() * cluster_count);
<span class="kw">for </span>c <span class="kw">in </span>input_classes {
<span class="kw">let </span><span class="kw-2">mut </span>row = <span class="macro">vec!</span>[<span class="number">0f64</span>; cluster_count];
row[c] = <span class="number">1f64</span>;
class_data.append(<span class="kw-2">&amp;mut </span>row);
}
<span class="prelude-val">Ok</span>(Matrix::new(inputs.rows(), cluster_count, class_data))
} <span class="kw">else </span>{
<span class="prelude-val">Err</span>(Error::new(ErrorKind::UntrainedModel, <span class="string">&quot;The model has not been trained.&quot;</span>))
}
}
}
<span class="kw">impl</span>&lt;T: Distribution&gt; NaiveBayes&lt;T&gt; {
<span class="doccomment">/// Get the log-probabilities per class for each input.
</span><span class="kw">pub fn </span>get_log_probs(<span class="kw-2">&amp;</span><span class="self">self</span>, inputs: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;) -&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt; {
<span class="kw">if let </span>(<span class="kw-2">&amp;</span><span class="prelude-val">Some</span>(<span class="kw-2">ref </span>distr), <span class="kw-2">&amp;</span><span class="prelude-val">Some</span>(<span class="kw-2">ref </span>prior)) = (<span class="kw-2">&amp;</span><span class="self">self</span>.distr, <span class="kw-2">&amp;</span><span class="self">self</span>.class_prior) {
<span class="comment">// Get the joint log likelihood from the distribution
</span>distr.joint_log_lik(inputs, prior)
} <span class="kw">else </span>{
<span class="prelude-val">Err</span>(Error::new_untrained())
}
}
<span class="kw">fn </span>update_params(<span class="kw-2">&amp;mut </span><span class="self">self</span>, inputs: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, targets: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;) -&gt; LearningResult&lt;()&gt; {
<span class="kw">let </span>class_count = targets.cols();
<span class="kw">let </span>total_data = inputs.rows();
<span class="self">self</span>.class_counts = <span class="macro">vec!</span>[<span class="number">0</span>; class_count];
<span class="kw">let </span><span class="kw-2">mut </span>class_data = <span class="macro">vec!</span>[Vec::new(); class_count];
<span class="kw">for </span>(idx, row) <span class="kw">in </span>targets.row_iter().enumerate() {
<span class="comment">// Find the class of this input
</span><span class="kw">let </span>class = NaiveBayes::&lt;T&gt;::find_class(row.raw_slice())<span class="question-mark">?</span>;
<span class="comment">// Note the class of the input
</span>class_data[class].push(idx);
<span class="self">self</span>.class_counts[class] += <span class="number">1</span>;
}
<span class="kw">if let </span><span class="prelude-val">Some</span>(<span class="kw-2">ref mut </span>distr) = <span class="self">self</span>.distr {
<span class="kw">for </span>(idx, c) <span class="kw">in </span>class_data.into_iter().enumerate() {
<span class="comment">// If this class&#39; vector has not been populated, we can safely
// skip this iteration, since the user is clearly not interested
// in associating features with this class
</span><span class="kw">if </span>c.is_empty() {
<span class="kw">continue</span>;
}
<span class="comment">// Update the parameters within this class
</span>distr.update_params(<span class="kw-2">&amp;</span>inputs.select_rows(<span class="kw-2">&amp;</span>c), idx)<span class="question-mark">?</span>;
}
}
<span class="kw">let </span><span class="kw-2">mut </span>class_prior = Vec::with_capacity(class_count);
<span class="comment">// Compute the prior as the proportion in each class
</span>class_prior.extend(<span class="self">self</span>.class_counts.iter().map(|c| <span class="kw-2">*</span>c <span class="kw">as </span>f64 / total_data <span class="kw">as </span>f64));
<span class="self">self</span>.class_prior = <span class="prelude-val">Some</span>(class_prior);
<span class="self">self</span>.cluster_count = <span class="prelude-val">Some</span>(class_count);
<span class="prelude-val">Ok</span>(())
}
<span class="kw">fn </span>find_class(row: <span class="kw-2">&amp;</span>[f64]) -&gt; LearningResult&lt;usize&gt; {
<span class="comment">// Find the `1` entry in the row
</span><span class="kw">for </span>(idx, r) <span class="kw">in </span>row.into_iter().enumerate() {
<span class="kw">if </span><span class="kw-2">*</span>r == <span class="number">1f64 </span>{
<span class="kw">return </span><span class="prelude-val">Ok</span>(idx);
}
}
<span class="prelude-val">Err</span>(Error::new(ErrorKind::InvalidState,
<span class="string">&quot;No class found for entry in targets&quot;</span>))
}
<span class="kw">fn </span>get_classes(log_probs: Matrix&lt;f64&gt;) -&gt; Vec&lt;usize&gt; {
<span class="kw">let </span><span class="kw-2">mut </span>data_classes = Vec::with_capacity(log_probs.rows());
data_classes.extend(log_probs.row_iter().map(|row| {
<span class="comment">// Argmax each class log-probability per input
</span><span class="kw">let </span>(class, <span class="kw">_</span>) = utils::argmax(row.raw_slice());
class
}));
data_classes
}
}
<span class="doccomment">/// Naive Bayes Distribution.
</span><span class="kw">pub trait </span>Distribution {
<span class="doccomment">/// Initialize the distribution parameters.
</span><span class="kw">fn </span>from_model_params(class_count: usize, features: usize) -&gt; <span class="self">Self</span>;
<span class="doccomment">/// Updates the distribution parameters.
</span><span class="kw">fn </span>update_params(<span class="kw-2">&amp;mut </span><span class="self">self</span>, data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, class: usize) -&gt; LearningResult&lt;()&gt;;
<span class="doccomment">/// Compute the joint log likelihood of the data.
///
/// Returns a matrix with rows containing the probability that the input lies in each class.
</span><span class="kw">fn </span>joint_log_lik(<span class="kw-2">&amp;</span><span class="self">self</span>,
data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;,
class_prior: <span class="kw-2">&amp;</span>[f64])
-&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt;;
}
<span class="doccomment">/// The Gaussian Naive Bayes model distribution.
///
/// Defines:
///
/// p(x|C&lt;sub&gt;k&lt;/sub&gt;) = ∏&lt;sub&gt;i&lt;/sub&gt; N(x&lt;sub&gt;i&lt;/sub&gt; ;
/// μ&lt;sub&gt;k&lt;/sub&gt;, σ&lt;sup&gt;2&lt;/sup&gt;&lt;sub&gt;k&lt;/sub&gt;)
</span><span class="attribute">#[derive(Debug)]
</span><span class="kw">pub struct </span>Gaussian {
theta: Matrix&lt;f64&gt;,
sigma: Matrix&lt;f64&gt;,
}
<span class="kw">impl </span>Gaussian {
<span class="doccomment">/// Returns the distribution means.
///
/// This is a matrix of class by feature means.
</span><span class="kw">pub fn </span>theta(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>Matrix&lt;f64&gt; {
<span class="kw-2">&amp;</span><span class="self">self</span>.theta
}
<span class="doccomment">/// Returns the distribution variances.
///
/// This is a matrix of class by feature variances.
</span><span class="kw">pub fn </span>sigma(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>Matrix&lt;f64&gt; {
<span class="kw-2">&amp;</span><span class="self">self</span>.sigma
}
}
<span class="kw">impl </span>Distribution <span class="kw">for </span>Gaussian {
<span class="kw">fn </span>from_model_params(class_count: usize, features: usize) -&gt; Gaussian {
Gaussian {
theta: Matrix::zeros(class_count, features),
sigma: Matrix::zeros(class_count, features),
}
}
<span class="kw">fn </span>update_params(<span class="kw-2">&amp;mut </span><span class="self">self</span>, data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, class: usize) -&gt; LearningResult&lt;()&gt; {
<span class="comment">// Compute mean and sample variance
</span><span class="kw">let </span>mean = data.mean(Axes::Row).into_vec();
<span class="kw">let </span>var = data.variance(Axes::Row).map_err(|<span class="kw">_</span>| {
Error::new(ErrorKind::InvalidData,
<span class="string">&quot;Cannot compute variance for Gaussian distribution.&quot;</span>)
})<span class="question-mark">?
</span>.into_vec();
<span class="kw">let </span>features = data.cols();
<span class="kw">for </span>(idx, (m, v)) <span class="kw">in </span>mean.into_iter().zip(var.into_iter()).enumerate() {
<span class="self">self</span>.theta.mut_data()[class * features + idx] = m;
<span class="self">self</span>.sigma.mut_data()[class * features + idx] = v;
}
<span class="prelude-val">Ok</span>(())
}
<span class="kw">fn </span>joint_log_lik(<span class="kw-2">&amp;</span><span class="self">self</span>,
data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;,
class_prior: <span class="kw-2">&amp;</span>[f64])
-&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt; {
<span class="kw">let </span>class_count = class_prior.len();
<span class="kw">let </span><span class="kw-2">mut </span>log_lik = Vec::with_capacity(class_count);
<span class="kw">for </span>(i, item) <span class="kw">in </span>class_prior.into_iter().enumerate() {
<span class="kw">let </span>joint_i = item.ln();
<span class="kw">let </span>n_ij = -<span class="number">0.5 </span>* (<span class="self">self</span>.sigma.select_rows(<span class="kw-2">&amp;</span>[i]) * <span class="number">2.0 </span>* PI).apply(<span class="kw-2">&amp;</span>|x| x.ln()).sum();
<span class="comment">// NOTE: Here we are copying the row data which is inefficient
</span><span class="kw">let </span>r_ij = (data - <span class="self">self</span>.theta.select_rows(<span class="kw-2">&amp;</span><span class="macro">vec!</span>[i; data.rows()]))
.apply(<span class="kw-2">&amp;</span>|x| x * x)
.elediv(<span class="kw-2">&amp;</span><span class="self">self</span>.sigma.select_rows(<span class="kw-2">&amp;</span><span class="macro">vec!</span>[i; data.rows()]))
.sum_cols();
<span class="kw">let </span>res = (-r_ij * <span class="number">0.5</span>) + n_ij;
log_lik.append(<span class="kw-2">&amp;mut </span>(res + joint_i).into_vec());
}
<span class="prelude-val">Ok</span>(Matrix::new(class_count, data.rows(), log_lik).transpose())
}
}
<span class="doccomment">/// The Bernoulli Naive Bayes model distribution.
///
/// Defines:
///
/// p(x|C&lt;sub&gt;k&lt;/sub&gt;) = ∏&lt;sub&gt;i&lt;/sub&gt; p&lt;sub&gt;k&lt;/sub&gt;&lt;sup&gt;x&lt;sub&gt;i&lt;/sub&gt;&lt;/sup&gt;
/// (1-p)&lt;sub&gt;k&lt;/sub&gt;&lt;sup&gt;1-x&lt;sub&gt;i&lt;/sub&gt;&lt;/sup&gt;
</span><span class="attribute">#[derive(Debug)]
</span><span class="kw">pub struct </span>Bernoulli {
log_probs: Matrix&lt;f64&gt;,
pseudo_count: f64,
}
<span class="kw">impl </span>Bernoulli {
<span class="doccomment">/// The log probability matrix.
///
/// A matrix of class by feature model log-probabilities.
</span><span class="kw">pub fn </span>log_probs(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>Matrix&lt;f64&gt; {
<span class="kw-2">&amp;</span><span class="self">self</span>.log_probs
}
}
<span class="kw">impl </span>Distribution <span class="kw">for </span>Bernoulli {
<span class="kw">fn </span>from_model_params(class_count: usize, features: usize) -&gt; Bernoulli {
Bernoulli {
log_probs: Matrix::zeros(class_count, features),
pseudo_count: <span class="number">1f64</span>,
}
}
<span class="kw">fn </span>update_params(<span class="kw-2">&amp;mut </span><span class="self">self</span>, data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, class: usize) -&gt; LearningResult&lt;()&gt; {
<span class="kw">let </span>features = data.cols();
<span class="comment">// We add the pseudo count to the class count and feature count
</span><span class="kw">let </span>pseudo_cc = data.rows() <span class="kw">as </span>f64 + (<span class="number">2f64 </span>* <span class="self">self</span>.pseudo_count);
<span class="kw">let </span>pseudo_fc = data.sum_rows() + <span class="self">self</span>.pseudo_count;
<span class="kw">let </span>log_probs = (pseudo_fc.apply(<span class="kw-2">&amp;</span>|x| x.ln()) - pseudo_cc.ln()).into_vec();
<span class="kw">for </span>(i, item) <span class="kw">in </span>log_probs.iter().enumerate().take(features) {
<span class="self">self</span>.log_probs[[class, i]] = <span class="kw-2">*</span>item;
}
<span class="prelude-val">Ok</span>(())
}
<span class="kw">fn </span>joint_log_lik(<span class="kw-2">&amp;</span><span class="self">self</span>,
data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;,
class_prior: <span class="kw-2">&amp;</span>[f64])
-&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt; {
<span class="kw">let </span>class_count = class_prior.len();
<span class="kw">let </span>neg_prob = <span class="self">self</span>.log_probs.clone().apply(<span class="kw-2">&amp;</span>|x| (<span class="number">1f64 </span>- x.exp()).ln());
<span class="kw">let </span>res = data * (<span class="kw-2">&amp;</span><span class="self">self</span>.log_probs - <span class="kw-2">&amp;</span>neg_prob).transpose();
<span class="comment">// NOTE: Some messy stuff now to get the class row contribution.
// Really we want to add to each row the class log-priors and the
// neg_prob_sum contribution - the last term in
// x log(p) + (1-x)log(1-p) = x (log(p) - log(1-p)) + log(1-p)
</span><span class="kw">let </span><span class="kw-2">mut </span>per_class_row = Vec::with_capacity(class_count);
<span class="kw">let </span>neg_prob_sum = neg_prob.sum_cols();
<span class="kw">for </span>(idx, p) <span class="kw">in </span>class_prior.into_iter().enumerate() {
per_class_row.push(p.ln() + neg_prob_sum[idx]);
}
<span class="kw">let </span>class_row_mat = Matrix::new(<span class="number">1</span>, class_count, per_class_row);
<span class="prelude-val">Ok</span>(res + class_row_mat.select_rows(<span class="kw-2">&amp;</span><span class="macro">vec!</span>[<span class="number">0</span>; data.rows()]))
}
}
<span class="doccomment">/// The Multinomial Naive Bayes model distribution.
///
/// Defines:
///
/// p(x|C&lt;sub&gt;k&lt;/sub&gt;) ∝ ∏&lt;sub&gt;i&lt;/sub&gt; p&lt;sub&gt;k&lt;/sub&gt;&lt;sup&gt;x&lt;sub&gt;i&lt;/sub&gt;&lt;/sup&gt;
</span><span class="attribute">#[derive(Debug)]
</span><span class="kw">pub struct </span>Multinomial {
log_probs: Matrix&lt;f64&gt;,
pseudo_count: f64,
}
<span class="kw">impl </span>Multinomial {
<span class="doccomment">/// The log probability matrix.
///
/// A matrix of class by feature model log-probabilities.
</span><span class="kw">pub fn </span>log_probs(<span class="kw-2">&amp;</span><span class="self">self</span>) -&gt; <span class="kw-2">&amp;</span>Matrix&lt;f64&gt; {
<span class="kw-2">&amp;</span><span class="self">self</span>.log_probs
}
}
<span class="kw">impl </span>Distribution <span class="kw">for </span>Multinomial {
<span class="kw">fn </span>from_model_params(class_count: usize, features: usize) -&gt; Multinomial {
Multinomial {
log_probs: Matrix::zeros(class_count, features),
pseudo_count: <span class="number">1f64</span>,
}
}
<span class="kw">fn </span>update_params(<span class="kw-2">&amp;mut </span><span class="self">self</span>, data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;, class: usize) -&gt; LearningResult&lt;()&gt; {
<span class="kw">let </span>features = data.cols();
<span class="kw">let </span>pseudo_fc = data.sum_rows() + <span class="self">self</span>.pseudo_count;
<span class="kw">let </span>pseudo_cc = pseudo_fc.sum();
<span class="kw">let </span>log_probs = (pseudo_fc.apply(<span class="kw-2">&amp;</span>|x| x.ln()) - pseudo_cc.ln()).into_vec();
<span class="kw">for </span>(i, item) <span class="kw">in </span>log_probs.iter().enumerate().take(features) {
<span class="self">self</span>.log_probs[[class, i]] = <span class="kw-2">*</span>item;
}
<span class="prelude-val">Ok</span>(())
}
<span class="kw">fn </span>joint_log_lik(<span class="kw-2">&amp;</span><span class="self">self</span>,
data: <span class="kw-2">&amp;</span>Matrix&lt;f64&gt;,
class_prior: <span class="kw-2">&amp;</span>[f64])
-&gt; LearningResult&lt;Matrix&lt;f64&gt;&gt; {
<span class="kw">let </span>class_count = class_prior.len();
<span class="kw">let </span>res = data * <span class="self">self</span>.log_probs.transpose();
<span class="kw">let </span><span class="kw-2">mut </span>per_class_row = Vec::with_capacity(class_count);
<span class="kw">for </span>p <span class="kw">in </span>class_prior {
per_class_row.push(p.ln());
}
<span class="kw">let </span>class_row_mat = Matrix::new(<span class="number">1</span>, class_count, per_class_row);
<span class="prelude-val">Ok</span>(res + class_row_mat.select_rows(<span class="kw-2">&amp;</span><span class="macro">vec!</span>[<span class="number">0</span>; data.rows()]))
}
}
<span class="attribute">#[cfg(test)]
</span><span class="kw">mod </span>tests {
<span class="kw">use </span><span class="kw">super</span>::NaiveBayes;
<span class="kw">use </span><span class="kw">super</span>::Gaussian;
<span class="kw">use </span><span class="kw">super</span>::Bernoulli;
<span class="kw">use </span><span class="kw">super</span>::Multinomial;
<span class="kw">use </span>learning::SupModel;
<span class="kw">use </span>linalg::Matrix;
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_gaussian() {
<span class="kw">let </span>inputs = Matrix::new(<span class="number">6</span>,
<span class="number">2</span>,
<span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">1.1</span>, <span class="number">1.1</span>, <span class="number">0.9</span>, <span class="number">2.2</span>, <span class="number">2.3</span>, <span class="number">2.5</span>, <span class="number">2.7</span>, <span class="number">5.2</span>, <span class="number">4.3</span>, <span class="number">6.2</span>, <span class="number">7.3</span>]);
<span class="kw">let </span>targets = Matrix::new(<span class="number">6</span>,
<span class="number">3</span>,
<span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>,
<span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>]);
<span class="kw">let </span><span class="kw-2">mut </span>model = NaiveBayes::&lt;Gaussian&gt;::new();
model.train(<span class="kw-2">&amp;</span>inputs, <span class="kw-2">&amp;</span>targets).unwrap();
<span class="kw">let </span>outputs = model.predict(<span class="kw-2">&amp;</span>inputs).unwrap();
<span class="macro">assert_eq!</span>(outputs.into_vec(), targets.into_vec());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_bernoulli() {
<span class="kw">let </span>inputs = Matrix::new(<span class="number">4</span>,
<span class="number">3</span>,
<span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">1.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>]);
<span class="kw">let </span>targets = Matrix::new(<span class="number">4</span>, <span class="number">2</span>, <span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>]);
<span class="kw">let </span><span class="kw-2">mut </span>model = NaiveBayes::&lt;Bernoulli&gt;::new();
model.train(<span class="kw-2">&amp;</span>inputs, <span class="kw-2">&amp;</span>targets).unwrap();
<span class="kw">let </span>outputs = model.predict(<span class="kw-2">&amp;</span>inputs).unwrap();
<span class="macro">assert_eq!</span>(outputs.into_vec(), targets.into_vec());
}
<span class="attribute">#[test]
</span><span class="kw">fn </span>test_multinomial() {
<span class="kw">let </span>inputs = Matrix::new(<span class="number">4</span>,
<span class="number">3</span>,
<span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">5.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">11.0</span>, <span class="number">13.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">12.0</span>, <span class="number">3.0</span>,
<span class="number">0.0</span>]);
<span class="kw">let </span>targets = Matrix::new(<span class="number">4</span>, <span class="number">2</span>, <span class="macro">vec!</span>[<span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>, <span class="number">0.0</span>, <span class="number">1.0</span>]);
<span class="kw">let </span><span class="kw-2">mut </span>model = NaiveBayes::&lt;Multinomial&gt;::new();
model.train(<span class="kw-2">&amp;</span>inputs, <span class="kw-2">&amp;</span>targets).unwrap();
<span class="kw">let </span>outputs = model.predict(<span class="kw-2">&amp;</span>inputs).unwrap();
<span class="macro">assert_eq!</span>(outputs.into_vec(), targets.into_vec());
}
}
</code></pre></div>
</section></div></main><div id="rustdoc-vars" data-root-path="../../../" data-current-crate="rusty_machine" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html>