| <!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/registry/src/github.com-1ecc6299db9ec823/gbdt-0.1.1/src/input.rs`."><meta name="keywords" content="rust, rustlang, rust-lang"><title>input.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="../../gbdt/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="../../gbdt/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> |
| </pre><pre class="rust"><code><span class="doccomment">//! This module implements the data loader. |
| //! |
| //! Currently we support to kind of input format: csv format and libsvm data format. |
| //! |
| //! # Example |
| //! ## LibSVM format |
| //! ```rust |
| //! use gbdt::input::InputFormat; |
| //! use gbdt::input; |
| //! let test_file = "data/xgb_binary_logistic/agaricus.txt.test"; |
| //! let mut fmt = input::InputFormat::txt_format(); |
| //! fmt.set_feature_size(126); |
| //! fmt.set_delimeter(' '); |
| //! let test_data = input::load(test_file, fmt); |
| //! ``` |
| //! |
| //! ## CSV format |
| //! ```rust |
| //! use gbdt::input::InputFormat; |
| //! use gbdt::input; |
| //! let test_file = "data/xgb_multi_softmax/dermatology.data.test"; |
| //! let mut fmt = InputFormat::csv_format(); |
| //! fmt.set_feature_size(34); |
| //! let test_data = input::load(test_file, fmt); |
| //! ``` |
| |
| </span><span class="attribute">#[cfg(all(feature = <span class="string">"mesalock_sgx"</span>, not(target_env = <span class="string">"sgx"</span>)))] |
| </span><span class="kw">use </span>std::prelude::v1::<span class="kw-2">*</span>; |
| |
| <span class="kw">use </span><span class="kw">crate</span>::decision_tree::{Data, DataVec, ValueType, VALUE_TYPE_UNKNOWN}; |
| |
| <span class="macro">cfg_if! </span>{ |
| <span class="kw">if </span><span class="attribute">#[cfg(all(feature = <span class="string">"mesalock_sgx"</span>, not(target_env = <span class="string">"sgx"</span>)))] </span>{ |
| <span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::error::Error; |
| <span class="kw">use </span>std::untrusted::fs::File; |
| <span class="kw">use </span>std::io::{BufRead, BufReader, Seek, SeekFrom}; |
| } <span class="kw">else </span>{ |
| <span class="kw">use </span>std::collections::HashMap; |
| <span class="kw">use </span>std::error::Error; |
| <span class="attribute">#[cfg(not(feature = <span class="string">"mesalock_sgx"</span>))] |
| </span><span class="kw">use </span>std::fs::File; |
| <span class="attribute">#[cfg(feature = <span class="string">"mesalock_sgx"</span>)] |
| </span><span class="kw">use </span>std::untrusted::fs::File; |
| <span class="kw">use </span>std::io::{BufRead, BufReader, Seek, SeekFrom}; |
| } |
| } |
| |
| <span class="kw">use </span>regex::Regex; |
| <span class="kw">use </span>serde_derive::{Deserialize, Serialize}; |
| |
| <span class="doccomment">/// This enum type defines the data file format. |
| /// |
| /// We support two data format: |
| /// 1. CSV format |
| /// 2. LibSVM data format |
| </span><span class="attribute">#[derive(Copy, Debug, PartialEq, Clone, Serialize, Deserialize)] |
| </span><span class="kw">pub enum </span>FileFormat { |
| <span class="doccomment">/// CSV format |
| </span>CSV, |
| <span class="doccomment">/// LibSVM data format |
| </span>TXT, |
| } |
| |
| <span class="doccomment">/// The input file format struct. |
| </span><span class="attribute">#[derive(Copy, Debug, Clone, Serialize, Deserialize)] |
| </span><span class="kw">pub struct </span>InputFormat { |
| <span class="doccomment">/// Data file format |
| </span><span class="kw">pub </span>ftype: FileFormat, |
| |
| <span class="doccomment">/// Set if ftype is set to [FileFormat](enum.FileFormat.CSV). |
| /// Indicates whether the csv has header. |
| </span><span class="kw">pub </span>header: bool, |
| |
| <span class="doccomment">/// Set if ftype is set to [FileFormat](enum.FileFormat.CSV). |
| /// Indicates which colume is the data label. (default = 0) |
| </span><span class="kw">pub </span>label_idx: usize, |
| |
| <span class="doccomment">/// Set if ftype is set to [FileFormat](enum.FileFormat.CSV). |
| /// Indicates if we allow unknown value in data file or not. |
| </span><span class="kw">pub </span>enable_unknown_value: bool, |
| |
| <span class="doccomment">/// Delimeter of the data file. |
| </span><span class="kw">pub </span>delimeter: char, |
| |
| <span class="doccomment">/// Set if ftype is set to [FileFormat](enum.FileFormat.TXT). |
| /// Indicates the total feature size. |
| </span><span class="kw">pub </span>feature_size: usize, |
| } |
| |
| <span class="kw">impl </span>InputFormat { |
| <span class="doccomment">/// Return a default CSV input format. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::csv_format(); |
| /// println!("{}", fmt.to_string()); |
| /// ``` |
| </span><span class="kw">pub fn </span>csv_format() -> InputFormat { |
| InputFormat { |
| ftype: FileFormat::CSV, |
| header: <span class="bool-val">false</span>, |
| label_idx: <span class="number">0</span>, |
| enable_unknown_value: <span class="bool-val">false</span>, |
| delimeter: <span class="string">','</span>, |
| feature_size: <span class="number">0</span>, |
| } |
| } |
| |
| <span class="doccomment">/// Return a default LibSVM input format. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::txt_format(); |
| /// println!("{}", fmt.to_string()); |
| /// ``` |
| </span><span class="kw">pub fn </span>txt_format() -> InputFormat { |
| InputFormat { |
| ftype: FileFormat::TXT, |
| header: <span class="bool-val">false</span>, |
| label_idx: <span class="number">0</span>, |
| enable_unknown_value: <span class="bool-val">false</span>, |
| delimeter: <span class="string">'\t'</span>, |
| feature_size: <span class="number">0</span>, |
| } |
| } |
| <span class="doccomment">/// Transform the input format to human readable string. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::csv_format(); |
| /// println!("{}", fmt.to_string()); |
| /// ``` |
| </span><span class="kw">pub fn </span>to_string(<span class="kw-2">&</span><span class="self">self</span>) -> String { |
| <span class="kw">let </span><span class="kw-2">mut </span>s = String::from(<span class="string">""</span>); |
| s.push_str(<span class="kw-2">&</span><span class="macro">format!</span>( |
| <span class="string">"File type: {}\n"</span>, |
| <span class="kw">match </span><span class="self">self</span>.ftype { |
| FileFormat::CSV => <span class="string">"CSV"</span>, |
| FileFormat::TXT => <span class="string">"TXT"</span>, |
| } |
| )); |
| <span class="kw">match </span><span class="self">self</span>.ftype { |
| FileFormat::CSV => { |
| s.push_str(<span class="kw-2">&</span><span class="macro">format!</span>(<span class="string">"Has header: {}\n"</span>, <span class="self">self</span>.header)); |
| s.push_str(<span class="kw-2">&</span><span class="macro">format!</span>(<span class="string">"Label index: {}\n"</span>, <span class="self">self</span>.label_idx)); |
| } |
| FileFormat::TXT => { |
| s.push_str(<span class="kw-2">&</span><span class="macro">format!</span>(<span class="string">"Feature size: {}\n"</span>, <span class="self">self</span>.feature_size)); |
| } |
| } |
| s.push_str(<span class="kw-2">&</span><span class="macro">format!</span>(<span class="string">"Delemeter: [{}]"</span>, <span class="self">self</span>.delimeter)); |
| s |
| } |
| |
| <span class="doccomment">/// Set feature size for the LibSVM input format. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::txt_format(); |
| /// fmt.set_feature_size(126); // the total feature size |
| /// ``` |
| </span><span class="kw">pub fn </span>set_feature_size(<span class="kw-2">&mut </span><span class="self">self</span>, size: usize) { |
| <span class="self">self</span>.feature_size = size; |
| } |
| |
| <span class="doccomment">/// Set for label index for CSV format. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::csv_format(); |
| /// fmt.set_label_index(34); |
| /// ``` |
| </span><span class="kw">pub fn </span>set_label_index(<span class="kw-2">&mut </span><span class="self">self</span>, idx: usize) { |
| <span class="self">self</span>.label_idx = idx; |
| } |
| |
| <span class="doccomment">/// Set for label index for CSV format. |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// let mut fmt = InputFormat::txt_format(); |
| /// fmt.set_delimeter(' '); |
| /// ``` |
| </span><span class="kw">pub fn </span>set_delimeter(<span class="kw-2">&mut </span><span class="self">self</span>, delim: char) { |
| <span class="self">self</span>.delimeter = delim; |
| } |
| } |
| |
| <span class="doccomment">/// Function for char counting, used in [infer](function.input.infer) |
| </span><span class="kw">fn </span>count(<span class="kw-2">mut </span>hash_map: HashMap<char, u32>, word: char) -> HashMap<char, u32> { |
| { |
| <span class="kw">let </span>c = hash_map.entry(word).or_insert(<span class="number">0</span>); |
| <span class="kw-2">*</span>c += <span class="number">1</span>; |
| } |
| hash_map |
| } |
| |
| <span class="doccomment">/// Function used for input file type inference. This can help recognize the file format. |
| /// If the file is in csv type, this function also helps to check whether the csv file has |
| /// header. |
| /// |
| /// # Example |
| /// ```rust |
| /// use gbdt::input::infer; |
| /// let train_file = "dataset/iris/train.txt"; |
| /// let fmt = infer(train_file); |
| /// println!("{}", fmt.to_string()); |
| /// ``` |
| </span><span class="kw">pub fn </span>infer(file_name: <span class="kw-2">&</span>str) -> InputFormat { |
| <span class="kw">let </span>file = File::open(file_name.to_string()).unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>reader = BufReader::new(file); |
| |
| <span class="comment">// check CSV or TXT |
| </span><span class="kw">let </span><span class="kw-2">mut </span>first_line = String::new(); |
| reader.read_line(<span class="kw-2">&mut </span>first_line).unwrap(); |
| <span class="kw">let </span><span class="kw-2">mut </span>input_format = <span class="kw">if </span>first_line.contains(<span class="string">':'</span>) { |
| InputFormat::txt_format() |
| } <span class="kw">else </span>{ |
| InputFormat::csv_format() |
| }; |
| |
| <span class="comment">// Check delimeter |
| </span><span class="kw">let </span>reg = <span class="kw">match </span>input_format.ftype { |
| FileFormat::CSV => Regex::new(<span class="string">r"[+-]?\d+(,\d+)*(.\d+(e\d+)?)?"</span>).unwrap(), |
| FileFormat::TXT => Regex::new(<span class="string">r"\d+:[+-]?\d+(,\d+)*(.\d+(e\d+)?)?"</span>).unwrap(), |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>second_line = String::new(); |
| reader |
| .read_line(<span class="kw-2">&mut </span>second_line) |
| .expect(<span class="string">"No second line to read"</span>); |
| <span class="kw">let </span>caps = reg.captures(<span class="kw-2">&</span>second_line).unwrap().len(); |
| <span class="kw">let </span>second_line_after = reg.replace_all(<span class="kw-2">&</span>second_line, <span class="string">""</span>); |
| <span class="kw">let </span>cnt = second_line_after.chars().fold(HashMap::new(), count); |
| <span class="kw">let </span>default_delim: char = <span class="kw">match </span>input_format.ftype { |
| FileFormat::CSV => <span class="string">','</span>, |
| FileFormat::TXT => <span class="string">'\t'</span>, |
| }; |
| <span class="kw">let </span><span class="kw-2">mut </span>flag = <span class="bool-val">false</span>; |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(value) = cnt.get(<span class="kw-2">&</span>default_delim) { |
| <span class="kw">if </span><span class="kw-2">*</span>value > ((caps <span class="kw">as </span>u32) - <span class="number">2</span>) { |
| input_format.delimeter = default_delim; |
| flag = <span class="bool-val">true</span>; |
| } |
| } |
| <span class="kw">if </span>!flag { |
| <span class="kw">let </span><span class="kw-2">mut </span>max_cnt: u32 = <span class="number">0</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>delim = <span class="string">'\t'</span>; |
| <span class="kw">for </span>(k, v) <span class="kw">in </span><span class="kw-2">&</span>cnt { |
| <span class="kw">if </span><span class="kw-2">*</span>v > max_cnt { |
| max_cnt = <span class="kw-2">*</span>v; |
| delim = <span class="kw-2">*</span>k; |
| } |
| } |
| input_format.delimeter = delim; |
| flag = <span class="bool-val">true</span>; |
| } |
| <span class="comment">// we shouldn't reach here |
| </span><span class="macro">assert_eq!</span>(flag, <span class="bool-val">true</span>); |
| |
| <span class="comment">// if CSV, check header |
| // use the first value as label or target value by default |
| |
| </span><span class="kw">if let </span>FileFormat::CSV = input_format.ftype { |
| <span class="kw">let </span>first_line_after = reg.replace_all(<span class="kw-2">&</span>first_line, <span class="string">""</span>); |
| <span class="kw">let </span>letters = Regex::new(<span class="string">r"[a-zA-Z]"</span>).unwrap(); |
| <span class="kw">if let </span><span class="prelude-val">Some</span>(letter_caps) = letters.captures(<span class="kw-2">&</span>first_line_after) { |
| input_format.header = letter_caps.len() > <span class="number">0</span>; |
| } |
| } |
| |
| input_format |
| } |
| |
| <span class="doccomment">/// Load csv file. |
| /// # Example |
| /// ```rust |
| /// use std::fs::File; |
| /// use gbdt::input::{InputFormat, load_csv}; |
| /// let train_file = "dataset/iris/train.txt"; |
| /// let mut file = File::open(train_file.to_string()).unwrap(); |
| /// let mut fmt = InputFormat::csv_format(); |
| /// fmt.set_label_index(4); |
| /// let train_dv = load_csv(&mut file, fmt); |
| /// ``` |
| /// |
| /// # Error |
| /// Raise error if file cannot be read correctly. |
| </span><span class="kw">pub fn </span>load_csv(file: <span class="kw-2">&mut </span>File, input_format: InputFormat) -> <span class="prelude-ty">Result</span><DataVec, Box<Error>> { |
| file.seek(SeekFrom::Start(<span class="number">0</span>))<span class="question-mark">?</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>dv = Vec::new(); |
| |
| <span class="kw">let </span><span class="kw-2">mut </span>reader = BufReader::new(file); |
| <span class="kw">let </span><span class="kw-2">mut </span>l = String::new(); |
| <span class="kw">if </span>input_format.header { |
| reader.read_line(<span class="kw-2">&mut </span>l).unwrap_or(<span class="number">0</span>); |
| } |
| <span class="kw">let </span><span class="kw-2">mut </span>v: Vec<ValueType>; |
| <span class="kw">for </span>line <span class="kw">in </span>reader.lines() { |
| <span class="kw">let </span>content = line<span class="question-mark">?</span>; |
| <span class="kw">if </span>input_format.enable_unknown_value { |
| v = content |
| .split(input_format.delimeter) |
| .map(|x| x.parse::<ValueType>().unwrap_or(VALUE_TYPE_UNKNOWN)) |
| .collect(); |
| } <span class="kw">else </span>{ |
| v = content |
| .split(input_format.delimeter) |
| .map(|x| x.parse::<ValueType>().unwrap()) |
| .collect(); |
| } |
| dv.push(Data { |
| label: v.swap_remove(input_format.label_idx), |
| feature: v, |
| target: <span class="number">0.0</span>, |
| weight: <span class="number">1.0</span>, |
| residual: <span class="number">0.0</span>, |
| initial_guess: <span class="number">0.0</span>, |
| }) |
| } |
| <span class="prelude-val">Ok</span>(dv) |
| } |
| |
| <span class="doccomment">/// Load txt file. |
| /// |
| /// # Example |
| /// ```rust |
| /// use std::fs::File; |
| /// use gbdt::input::{InputFormat, load_txt}; |
| /// let test_file = "xgb-data/xgb_binary_logistic/agaricus.txt.test"; |
| /// let mut file = File::open(test_file.to_string()).unwrap(); |
| /// let mut fmt = InputFormat::csv_format(); |
| /// fmt.set_feature_size(126); |
| /// fmt.set_delimeter(' '); |
| /// let test_dv = load_txt(&mut file, fmt); |
| /// ``` |
| /// |
| /// # Error |
| /// Raise error if file cannot be read correctly. |
| </span><span class="kw">pub fn </span>load_txt(file: <span class="kw-2">&mut </span>File, input_format: InputFormat) -> <span class="prelude-ty">Result</span><DataVec, Box<Error>> { |
| file.seek(SeekFrom::Start(<span class="number">0</span>))<span class="question-mark">?</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>dv = Vec::new(); |
| |
| <span class="kw">let </span>reader = BufReader::new(file); |
| <span class="kw">let </span><span class="kw-2">mut </span>label: ValueType = <span class="number">0.0</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>idx: usize = <span class="number">0</span>; |
| <span class="kw">let </span><span class="kw-2">mut </span>val: ValueType = <span class="number">0.0</span>; |
| <span class="kw">for </span>line <span class="kw">in </span>reader.lines() { |
| <span class="kw">let </span><span class="kw-2">mut </span>v: Vec<ValueType> = <span class="macro">vec!</span>[VALUE_TYPE_UNKNOWN; input_format.feature_size]; |
| <span class="kw">for </span>token <span class="kw">in </span>line.unwrap().split(input_format.delimeter) { |
| <span class="kw">let </span>splited_token: Vec<<span class="kw-2">&</span>str> = token.split(<span class="string">':'</span>).collect(); |
| <span class="kw">if </span>splited_token.len() == <span class="number">2 </span>{ |
| <span class="kw">let </span><span class="kw-2">mut </span>err = <span class="bool-val">false</span>; |
| <span class="kw">match </span>splited_token[<span class="number">0 </span><span class="kw">as </span>usize].parse::<usize>() { |
| <span class="prelude-val">Ok</span>(kk) => { |
| idx = kk; |
| } |
| <span class="prelude-val">Err</span>(<span class="kw">_</span>) => err = <span class="bool-val">true</span>, |
| } |
| <span class="kw">match </span>splited_token[<span class="number">1 </span><span class="kw">as </span>usize].parse::<ValueType>() { |
| <span class="prelude-val">Ok</span>(vv) => { |
| val = vv; |
| } |
| <span class="prelude-val">Err</span>(<span class="kw">_</span>) => err = <span class="bool-val">true</span>, |
| } |
| <span class="kw">if </span>idx >= input_format.feature_size { |
| err = <span class="bool-val">true</span>; |
| } |
| <span class="kw">if </span>!err { |
| v[idx] = val; |
| } |
| } |
| <span class="kw">if </span>splited_token.len() == <span class="number">1 </span>{ |
| label = splited_token[<span class="number">0 </span><span class="kw">as </span>usize].parse::<ValueType>().unwrap(); |
| } <span class="kw">else </span>{ |
| <span class="comment">// report error |
| </span>} |
| } |
| dv.push(Data { |
| label, |
| feature: v, |
| target: <span class="number">0.0</span>, |
| weight: <span class="number">1.0</span>, |
| residual: <span class="number">0.0</span>, |
| initial_guess: <span class="number">0.0</span>, |
| }); |
| } |
| |
| <span class="prelude-val">Ok</span>(dv) |
| } |
| |
| <span class="doccomment">/// Load file with certain input format. |
| /// # Example |
| /// ## LibSVM format |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// use gbdt::input; |
| /// let test_file = "data/xgb_binary_logistic/agaricus.txt.test"; |
| /// let mut fmt = input::InputFormat::txt_format(); |
| /// fmt.set_feature_size(126); |
| /// fmt.set_delimeter(' '); |
| /// let test_data = input::load(test_file, fmt); |
| /// ``` |
| /// |
| /// ## CSV format |
| /// ```rust |
| /// use gbdt::input::InputFormat; |
| /// use gbdt::input; |
| /// let test_file = "data/xgb_multi_softmax/dermatology.data.test"; |
| /// let mut fmt = InputFormat::csv_format(); |
| /// fmt.set_feature_size(34); |
| /// let test_data = input::load(test_file, fmt); |
| /// ``` |
| /// |
| /// # Error |
| /// Raise error if file cannot be open correctly. |
| </span><span class="kw">pub fn </span>load(file_name: <span class="kw-2">&</span>str, input_format: InputFormat) -> <span class="prelude-ty">Result</span><DataVec, Box<Error>> { |
| <span class="kw">let </span><span class="kw-2">mut </span>file = File::open(file_name.to_string())<span class="question-mark">?</span>; |
| <span class="kw">match </span>input_format.ftype { |
| FileFormat::CSV => load_csv(<span class="kw-2">&mut </span>file, input_format), |
| FileFormat::TXT => load_txt(<span class="kw-2">&mut </span>file, input_format), |
| } |
| } |
| </code></pre></div> |
| </section></div></main><div id="rustdoc-vars" data-root-path="../../" data-current-crate="gbdt" data-themes="ayu,dark,light" data-resource-suffix="" data-rustdoc-version="1.66.0-nightly (5c8bff74b 2022-10-21)" ></div></body></html> |
