| <!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/knn/mod.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>mod.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> |
| </pre><pre class="rust"><code><span class="doccomment">//! - k-Nearest Nerighbors |
| //! |
| //! Contains implemention of k-nearest search using |
| //! kd-tree, ball-tree and brute-force. |
| //! |
| //! # Usage |
| //! |
| //! ``` |
| //! # #[macro_use] extern crate rulinalg; extern crate rusty_machine; fn main() { |
| //! use rusty_machine::learning::knn::KNNClassifier; |
| //! use rusty_machine::learning::SupModel; |
| //! use rusty_machine::linalg::Vector; |
| //! |
| //! let data = matrix![1., 1., 1.; |
| //! 1., 2., 3.; |
| //! 2., 3., 1.; |
| //! 2., 2., 0.]; |
| //! let target = Vector::new(vec![0, 0, 1, 1]); |
| //! |
| //! // train the model to search 2-nearest |
| //! let mut knn = KNNClassifier::new(2); |
| //! knn.train(&data, &target).unwrap(); |
| //! |
| //! // predict new points |
| //! let res = knn.predict(&matrix![2., 3., 0.; 1., 1., 2.]).unwrap(); |
| //! assert_eq!(res, Vector::new(vec![1, 0])); |
| //! # } |
| //! ``` |
| </span><span class="kw">use </span>std::f64; |
| <span class="kw">use </span>std::collections::BTreeMap; |
| |
| <span class="kw">use </span>linalg::{Matrix, BaseMatrix, Vector}; |
| <span class="kw">use </span>learning::{LearningResult, SupModel}; |
| <span class="kw">use </span>learning::error::{Error, ErrorKind}; |
| |
| <span class="kw">mod </span>binary_tree; |
| <span class="kw">mod </span>brute_force; |
| |
| <span class="kw">pub use </span><span class="self">self</span>::binary_tree::{KDTree, BallTree}; |
| <span class="kw">pub use </span><span class="self">self</span>::brute_force::BruteForce; |
| |
| <span class="doccomment">/// k-Nearest Neighbor Classifier |
| </span><span class="attribute">#[derive(Debug)] |
| </span><span class="kw">pub struct </span>KNNClassifier<S: KNearestSearch> { |
| k: usize, |
| |
| searcher: S, |
| target: <span class="prelude-ty">Option</span><Vector<usize>>, |
| } |
| |
| <span class="kw">impl </span>Default <span class="kw">for </span>KNNClassifier<KDTree> { |
| <span class="doccomment">/// Constructs an untrained KNN Classifier with searching 5 neighbors. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::knn::KNNClassifier; |
| /// let _ = KNNClassifier::default(); |
| /// ``` |
| </span><span class="kw">fn </span>default() -> <span class="self">Self </span>{ |
| KNNClassifier { |
| k: <span class="number">5</span>, |
| searcher: KDTree::default(), |
| target: <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl </span>KNNClassifier<KDTree> { |
| <span class="doccomment">/// Constructs an untrained KNN Classifier with specified |
| /// number of search neighbors. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::knn::KNNClassifier; |
| /// let _ = KNNClassifier::new(3); |
| /// ``` |
| </span><span class="kw">pub fn </span>new(k: usize) -> <span class="self">Self </span>{ |
| KNNClassifier { |
| k: k, |
| searcher: KDTree::default(), |
| target: <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl</span><S: KNearestSearch> KNNClassifier<S> { |
| <span class="doccomment">/// Constructs an untrained KNN Classifier with specified |
| /// k and leafsize for KDTree. |
| /// |
| /// # Examples |
| /// |
| /// ``` |
| /// use rusty_machine::learning::knn::{KNNClassifier, BallTree}; |
| /// let _ = KNNClassifier::new_specified(3, BallTree::new(10)); |
| /// ``` |
| </span><span class="kw">pub fn </span>new_specified(k: usize, searcher: S) -> <span class="self">Self </span>{ |
| KNNClassifier { |
| k: k, |
| searcher: searcher, |
| target: <span class="prelude-val">None |
| </span>} |
| } |
| } |
| |
| <span class="kw">impl</span><S: KNearestSearch> SupModel<Matrix<f64>, Vector<usize>> <span class="kw">for </span>KNNClassifier<S> { |
| |
| <span class="kw">fn </span>predict(<span class="kw-2">&</span><span class="self">self</span>, inputs: <span class="kw-2">&</span>Matrix<f64>) -> LearningResult<Vector<usize>> { |
| <span class="kw">match </span><span class="self">self</span>.target { |
| <span class="prelude-val">Some</span>(<span class="kw-2">ref </span>target) => { |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>results: Vec<usize> = Vec::with_capacity(inputs.rows()); |
| <span class="kw">for </span>row <span class="kw">in </span>inputs.row_iter() { |
| <span class="kw">let </span>(idx, <span class="kw">_</span>) = <span class="self">self</span>.searcher.search(row.raw_slice(), <span class="self">self</span>.k)<span class="question-mark">?</span>; |
| <span class="kw">let </span>res = target.select(<span class="kw-2">&</span>idx); |
| <span class="kw">let </span>(uniques, counts) = freq(res.data()); |
| <span class="kw">let </span>(id, <span class="kw">_</span>) = counts.argmax(); |
| results.push(uniques[id]); |
| } |
| <span class="prelude-val">Ok</span>(Vector::new(results)) |
| }, |
| <span class="kw">_ </span>=> <span class="prelude-val">Err</span>(Error::new_untrained()) |
| } |
| } |
| |
| <span class="kw">fn </span>train(<span class="kw-2">&mut </span><span class="self">self</span>, inputs: <span class="kw-2">&</span>Matrix<f64>, targets: <span class="kw-2">&</span>Vector<usize>) -> LearningResult<()> { |
| <span class="kw">if </span>inputs.rows() != targets.size() { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::new(ErrorKind::InvalidData, |
| <span class="string">"inputs and targets must be the same length"</span>)); |
| } |
| <span class="kw">if </span>inputs.rows() < <span class="self">self</span>.k { |
| <span class="kw">return </span><span class="prelude-val">Err</span>(Error::new(ErrorKind::InvalidData, |
| <span class="string">"inputs number of rows must be equal or learger than k"</span>)); |
| } |
| <span class="self">self</span>.searcher.build(inputs.clone()); |
| <span class="self">self</span>.target = <span class="prelude-val">Some</span>(targets.clone()); |
| <span class="prelude-val">Ok</span>(()) |
| } |
| } |
| |
| <span class="doccomment">/// Container for k-Nearest search results |
| </span><span class="kw">struct </span>KNearest { |
| <span class="comment">// number to search |
| </span>k: usize, |
| <span class="comment">// tuple of index and its distances, sorted by distances |
| </span>pairs: Vec<(usize, f64)>, |
| } |
| |
| <span class="kw">impl </span>KNearest { |
| |
| <span class="kw">fn </span>new(k: usize, index: Vec<usize>, distances: Vec<f64>) -> <span class="self">Self </span>{ |
| <span class="macro">debug_assert!</span>(!index.is_empty(), <span class="string">"index can't be empty"</span>); |
| <span class="macro">debug_assert!</span>(index.len() == distances.len(), |
| <span class="string">"index and distance must have the same length"</span>); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>pairs: Vec<(usize, f64)> = index.into_iter() |
| .zip(distances.into_iter()) |
| .collect(); |
| <span class="comment">// sort by distance, take k elements |
| </span>pairs.sort_by(|x, y| x.<span class="number">1</span>.partial_cmp(<span class="kw-2">&</span>y.<span class="number">1</span>).unwrap()); |
| pairs.truncate(k); |
| |
| KNearest { |
| k: k, |
| pairs: pairs |
| } |
| } |
| |
| <span class="doccomment">/// Add new index and distances to the container, keeping first k elements which |
| /// distances are smaller. Returns the updated farthest distance. |
| </span><span class="kw">fn </span>add(<span class="kw-2">&mut </span><span class="self">self</span>, index: usize, distance: f64) -> f64 { |
| <span class="comment">// self.pairs can't be empty |
| </span><span class="kw">let </span>len = <span class="self">self</span>.pairs.len(); |
| <span class="comment">// index of the last element after the query |
| </span><span class="kw">let </span>last_index: usize = <span class="kw">if </span>len < <span class="self">self</span>.k { |
| len |
| } <span class="kw">else </span>{ |
| len - <span class="number">1 |
| </span>}; |
| |
| <span class="kw">unsafe </span>{ |
| <span class="kw">if </span><span class="self">self</span>.pairs.get_unchecked(len - <span class="number">1</span>).<span class="number">1 </span>< distance { |
| <span class="kw">if </span>len < <span class="self">self</span>.k { |
| <span class="comment">// append to the last |
| </span><span class="self">self</span>.pairs.push((index, distance)); |
| } |
| <span class="self">self</span>.pairs.get_unchecked(last_index).<span class="number">1 |
| </span>} <span class="kw">else </span>{ |
| <span class="comment">// last element is already compared |
| </span><span class="kw">if </span>len >= <span class="self">self</span>.k { |
| <span class="self">self</span>.pairs.pop().unwrap(); |
| } |
| |
| <span class="kw">for </span>i <span class="kw">in </span><span class="number">2</span>..(len + <span class="number">1</span>) { |
| <span class="kw">if </span><span class="self">self</span>.pairs.get_unchecked(len - i).<span class="number">1 </span>< distance { |
| <span class="self">self</span>.pairs.insert(len - i + <span class="number">1</span>, (index, distance)); |
| <span class="kw">return </span><span class="self">self</span>.pairs.get_unchecked(last_index).<span class="number">1</span>; |
| } |
| } |
| <span class="self">self</span>.pairs.insert(<span class="number">0</span>, (index, distance)); |
| <span class="self">self</span>.pairs.get_unchecked(last_index).<span class="number">1 |
| </span>} |
| } |
| } |
| |
| <span class="doccomment">/// Return the k-th distance with searching point |
| </span><span class="kw">fn </span>dist(<span class="kw-2">&</span><span class="self">self</span>) -> f64 { |
| <span class="comment">// KNearest should gather k element at least |
| </span><span class="kw">let </span>len = <span class="self">self</span>.pairs.len(); |
| <span class="kw">if </span>len < <span class="self">self</span>.k { |
| f64::MAX |
| } <span class="kw">else </span>{ |
| <span class="kw">unsafe </span>{ |
| <span class="comment">// unchecked ver of .last().unwrap(), |
| // because self.pairs can't be empty |
| </span><span class="self">self</span>.pairs.get_unchecked(len - <span class="number">1</span>).<span class="number">1 |
| </span>} |
| } |
| } |
| |
| <span class="doccomment">/// Extract the search result to k-nearest indices and corresponding distances |
| </span><span class="kw">fn </span>get_results(<span class="self">self</span>) -> (Vec<usize>, Vec<f64>) { |
| <span class="kw">let </span><span class="kw-2">mut </span>indices: Vec<usize> = Vec::with_capacity(<span class="self">self</span>.k); |
| <span class="kw">let </span><span class="kw-2">mut </span>distances: Vec<f64> = Vec::with_capacity(<span class="self">self</span>.k); |
| <span class="kw">for </span>(i, d) <span class="kw">in </span><span class="self">self</span>.pairs { |
| indices.push(i); |
| distances.push(d); |
| } |
| (indices, distances) |
| } |
| } |
| |
| <span class="doccomment">/// Search K-nearest items |
| </span><span class="kw">pub trait </span>KNearestSearch: Default{ |
| |
| <span class="doccomment">/// build data structure for search optimization |
| </span><span class="kw">fn </span>build(<span class="kw-2">&mut </span><span class="self">self</span>, data: Matrix<f64>); |
| |
| <span class="doccomment">/// Serch k-nearest items close to the point |
| /// Returns a tuple of searched item index and its distances |
| </span><span class="kw">fn </span>search(<span class="kw-2">&</span><span class="self">self</span>, point: <span class="kw-2">&</span>[f64], k: usize) -> <span class="prelude-ty">Result</span><(Vec<usize>, Vec<f64>), Error>; |
| } |
| |
| <span class="doccomment">/// Count target label frequencies |
| /// TODO: Used in decisition tree, move impl to somewhere |
| </span><span class="kw">fn </span>freq(labels: <span class="kw-2">&</span>[usize]) -> (Vector<usize>, Vector<usize>) { |
| <span class="kw">let </span><span class="kw-2">mut </span>map: BTreeMap<usize, usize> = BTreeMap::new(); |
| <span class="kw">for </span>l <span class="kw">in </span>labels { |
| <span class="kw">let </span>e = map.entry(<span class="kw-2">*</span>l).or_insert(<span class="number">0</span>); |
| <span class="kw-2">*</span>e += <span class="number">1</span>; |
| } |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>uniques: Vec<usize> = Vec::with_capacity(map.len()); |
| <span class="kw">let </span><span class="kw-2">mut </span>counts: Vec<usize> = Vec::with_capacity(map.len()); |
| <span class="kw">for </span>(<span class="kw-2">&</span>k, <span class="kw-2">&</span>v) <span class="kw">in </span><span class="kw-2">&</span>map { |
| uniques.push(k); |
| counts.push(v); |
| } |
| (Vector::new(uniques), Vector::new(counts)) |
| } |
| |
| <span class="doccomment">/// Return distances between given point and data specified with row ids |
| </span><span class="kw">fn </span>get_distances(data: <span class="kw-2">&</span>Matrix<f64>, point: <span class="kw-2">&</span>[f64], ids: <span class="kw-2">&</span>[usize]) -> Vec<f64> { |
| <span class="macro">assert!</span>(!ids.is_empty(), <span class="string">"target ids is empty"</span>); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>distances: Vec<f64> = Vec::with_capacity(ids.len()); |
| <span class="kw">for </span>id <span class="kw">in </span>ids.iter() { |
| <span class="comment">// ToDo: use .row(*id) |
| </span><span class="kw">let </span>row: Vec<f64> = data.select_rows(<span class="kw-2">&</span>[<span class="kw-2">*</span>id]).into_vec(); |
| <span class="comment">// let row: Vec<f64> = self.data.row(*id).into_vec(); |
| </span><span class="kw">let </span>d = dist(point, <span class="kw-2">&</span>row); |
| distances.push(d); |
| } |
| distances |
| } |
| |
| <span class="kw">fn </span>dist(v1: <span class="kw-2">&</span>[f64], v2: <span class="kw-2">&</span>[f64]) -> f64 { |
| <span class="comment">// ToDo: use metrics |
| </span><span class="kw">let </span>d: f64 = v1.iter() |
| .zip(v2.iter()) |
| .map(|(<span class="kw-2">&</span>x, <span class="kw-2">&</span>y)| (x - y) * (x - y)) |
| .fold(<span class="number">0.</span>, |s, v| s + v); |
| d.sqrt() |
| } |
| |
| <span class="attribute">#[cfg(test)] |
| </span><span class="kw">mod </span>tests { |
| |
| <span class="kw">use </span>std::f64; |
| <span class="kw">use </span><span class="kw">super</span>::KNearest; |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_knearest() { |
| <span class="kw">let </span><span class="kw-2">mut </span>kn = KNearest::new(<span class="number">2</span>, <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>], <span class="macro">vec!</span>[<span class="number">3.</span>, <span class="number">2.</span>, <span class="number">1.</span>]); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">2</span>, <span class="number">2.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">2.</span>); |
| |
| <span class="comment">// update KNearest |
| </span><span class="kw">let </span>res = kn.add(<span class="number">10</span>, <span class="number">3.</span>); |
| <span class="macro">assert_eq!</span>(res, <span class="number">2.</span>); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">2</span>, <span class="number">2.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">2.</span>); |
| |
| <span class="kw">let </span>res = kn.add(<span class="number">11</span>, <span class="number">0.</span>); |
| <span class="macro">assert_eq!</span>(res, <span class="number">1.</span>); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">2</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">11</span>, <span class="number">0.</span>), (<span class="number">3</span>, <span class="number">1.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">1.</span>); |
| } |
| |
| <span class="attribute">#[test] |
| </span><span class="kw">fn </span>test_knearest2() { |
| <span class="kw">let </span><span class="kw-2">mut </span>kn = KNearest::new(<span class="number">4</span>, <span class="macro">vec!</span>[<span class="number">1</span>, <span class="number">2</span>, <span class="number">3</span>], <span class="macro">vec!</span>[<span class="number">3.</span>, <span class="number">2.</span>, <span class="number">1.</span>]); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">2</span>, <span class="number">2.</span>), (<span class="number">1</span>, <span class="number">3.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), f64::MAX); |
| |
| <span class="kw">let </span>res = kn.add(<span class="number">5</span>, <span class="number">1.5</span>); |
| <span class="macro">assert_eq!</span>(res, <span class="number">3.</span>); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">5</span>, <span class="number">1.5</span>), (<span class="number">2</span>, <span class="number">2.</span>), (<span class="number">1</span>, <span class="number">3.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">3.</span>); |
| |
| <span class="kw">let </span>res = kn.add(<span class="number">6</span>, <span class="number">6.</span>); |
| <span class="macro">assert_eq!</span>(res, <span class="number">3.</span>); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">5</span>, <span class="number">1.5</span>), (<span class="number">2</span>, <span class="number">2.</span>), (<span class="number">1</span>, <span class="number">3.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">3.</span>); |
| |
| <span class="kw">let </span>res = kn.add(<span class="number">7</span>, <span class="number">0.5</span>); |
| <span class="macro">assert_eq!</span>(res, <span class="number">2.</span>); |
| <span class="macro">assert_eq!</span>(kn.k, <span class="number">4</span>); |
| <span class="macro">assert_eq!</span>(kn.pairs, <span class="macro">vec!</span>[(<span class="number">7</span>, <span class="number">0.5</span>), (<span class="number">3</span>, <span class="number">1.</span>), (<span class="number">5</span>, <span class="number">1.5</span>), (<span class="number">2</span>, <span class="number">2.</span>)]); |
| <span class="macro">assert_eq!</span>(kn.dist(), <span class="number">2.</span>); |
| } |
| } |
| </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> |
