📄 svmlightinterface.html
字号:
<HTML>
<BODY BGCOLOR="white">
<PRE>
<FONT color="green">001</FONT> /*<a name="line.1"></a>
<FONT color="green">002</FONT> * JNI_SVM-light - A Java Native Interface for SVM-light<a name="line.2"></a>
<FONT color="green">003</FONT> * <a name="line.3"></a>
<FONT color="green">004</FONT> * Copyright (C) 2005 <a name="line.4"></a>
<FONT color="green">005</FONT> * Tom Crecelius & Martin Theobald <a name="line.5"></a>
<FONT color="green">006</FONT> * Max-Planck Institute for Computer Science<a name="line.6"></a>
<FONT color="green">007</FONT> * <a name="line.7"></a>
<FONT color="green">008</FONT> * This program is free software; you can redistribute it and/or modify it under<a name="line.8"></a>
<FONT color="green">009</FONT> * the terms of the GNU General Public License as published by the Free Software<a name="line.9"></a>
<FONT color="green">010</FONT> * Foundation.<a name="line.10"></a>
<FONT color="green">011</FONT> * <a name="line.11"></a>
<FONT color="green">012</FONT> * This program is distributed in the hope that it will be useful, but WITHOUT<a name="line.12"></a>
<FONT color="green">013</FONT> * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS<a name="line.13"></a>
<FONT color="green">014</FONT> * FOR A PARTICULAR PURPOSE. See the GNU General Public License for more<a name="line.14"></a>
<FONT color="green">015</FONT> * details.<a name="line.15"></a>
<FONT color="green">016</FONT> * <a name="line.16"></a>
<FONT color="green">017</FONT> * You should have received a copy of the GNU General Public License along with<a name="line.17"></a>
<FONT color="green">018</FONT> * this program; if not, write to the Free Software Foundation, Inc., 51<a name="line.18"></a>
<FONT color="green">019</FONT> * Franklin St, Fifth Floor, Boston, MA 02110-1301 USA<a name="line.19"></a>
<FONT color="green">020</FONT> */<a name="line.20"></a>
<FONT color="green">021</FONT> <a name="line.21"></a>
<FONT color="green">022</FONT> package jnisvmlight;<a name="line.22"></a>
<FONT color="green">023</FONT> <a name="line.23"></a>
<FONT color="green">024</FONT> import java.io.BufferedReader;<a name="line.24"></a>
<FONT color="green">025</FONT> import java.io.IOException;<a name="line.25"></a>
<FONT color="green">026</FONT> import java.io.InputStreamReader;<a name="line.26"></a>
<FONT color="green">027</FONT> import java.net.URL;<a name="line.27"></a>
<FONT color="green">028</FONT> import java.text.ParseException;<a name="line.28"></a>
<FONT color="green">029</FONT> import java.util.ArrayList;<a name="line.29"></a>
<FONT color="green">030</FONT> import java.util.StringTokenizer;<a name="line.30"></a>
<FONT color="green">031</FONT> <a name="line.31"></a>
<FONT color="green">032</FONT> /**<a name="line.32"></a>
<FONT color="green">033</FONT> * The main interface class that transfers the training data to the SVM-light<a name="line.33"></a>
<FONT color="green">034</FONT> * library by a native call. Optionally takes as input an individually modified<a name="line.34"></a>
<FONT color="green">035</FONT> * set of training parameters or an array of string paramaters that exactly<a name="line.35"></a>
<FONT color="green">036</FONT> * simulate the command line input parameters used by the SVM-light binaries.<a name="line.36"></a>
<FONT color="green">037</FONT> * This class can also be used for native classification calls.<a name="line.37"></a>
<FONT color="green">038</FONT> * <a name="line.38"></a>
<FONT color="green">039</FONT> * @author Tom Crecelius & Martin Theobald<a name="line.39"></a>
<FONT color="green">040</FONT> */<a name="line.40"></a>
<FONT color="green">041</FONT> public class SVMLightInterface {<a name="line.41"></a>
<FONT color="green">042</FONT> <a name="line.42"></a>
<FONT color="green">043</FONT> /**<a name="line.43"></a>
<FONT color="green">044</FONT> * Apply an in-place quicksort prior to each native training call to<a name="line.44"></a>
<FONT color="green">045</FONT> * SVM-light. SVM-light requires each input feature vector to be sorted in<a name="line.45"></a>
<FONT color="green">046</FONT> * ascending order of dimensions. Disable this option if you are sure to<a name="line.46"></a>
<FONT color="green">047</FONT> * provide sorted vectors already.<a name="line.47"></a>
<FONT color="green">048</FONT> */<a name="line.48"></a>
<FONT color="green">049</FONT> public static boolean SORT_INPUT_VECTORS = true;<a name="line.49"></a>
<FONT color="green">050</FONT> <a name="line.50"></a>
<FONT color="green">051</FONT> static {<a name="line.51"></a>
<FONT color="green">052</FONT> System.loadLibrary("svmlight");<a name="line.52"></a>
<FONT color="green">053</FONT> }<a name="line.53"></a>
<FONT color="green">054</FONT> <a name="line.54"></a>
<FONT color="green">055</FONT> /**<a name="line.55"></a>
<FONT color="green">056</FONT> * Reads a set of labeled training vectors from a URL. The format is<a name="line.56"></a>
<FONT color="green">057</FONT> * compatible to the SVM-light training files.<a name="line.57"></a>
<FONT color="green">058</FONT> */<a name="line.58"></a>
<FONT color="green">059</FONT> public static LabeledFeatureVector[] getLabeledFeatureVectorsFromURL(<a name="line.59"></a>
<FONT color="green">060</FONT> URL file, int numOfLinesToSkip) throws ParseException {<a name="line.60"></a>
<FONT color="green">061</FONT> <a name="line.61"></a>
<FONT color="green">062</FONT> LabeledFeatureVector[] traindata = null;<a name="line.62"></a>
<FONT color="green">063</FONT> try {<a name="line.63"></a>
<FONT color="green">064</FONT> ArrayList data = new ArrayList();<a name="line.64"></a>
<FONT color="green">065</FONT> BufferedReader bi = new BufferedReader(new InputStreamReader(file<a name="line.65"></a>
<FONT color="green">066</FONT> .openStream()));<a name="line.66"></a>
<FONT color="green">067</FONT> <a name="line.67"></a>
<FONT color="green">068</FONT> String line = null;<a name="line.68"></a>
<FONT color="green">069</FONT> int cnt = 0;<a name="line.69"></a>
<FONT color="green">070</FONT> while ((line = bi.readLine()) != null) {<a name="line.70"></a>
<FONT color="green">071</FONT> cnt++;<a name="line.71"></a>
<FONT color="green">072</FONT> if (cnt <= numOfLinesToSkip) {<a name="line.72"></a>
<FONT color="green">073</FONT> continue;<a name="line.73"></a>
<FONT color="green">074</FONT> }<a name="line.74"></a>
<FONT color="green">075</FONT> String label = null;<a name="line.75"></a>
<FONT color="green">076</FONT> StringTokenizer st = new StringTokenizer(line.trim());<a name="line.76"></a>
<FONT color="green">077</FONT> if (st.countTokens() > 1) {<a name="line.77"></a>
<FONT color="green">078</FONT> label = (String) st.nextElement();<a name="line.78"></a>
<FONT color="green">079</FONT> <a name="line.79"></a>
<FONT color="green">080</FONT> ArrayList dimlist = new ArrayList();<a name="line.80"></a>
<FONT color="green">081</FONT> ArrayList vallist = new ArrayList();<a name="line.81"></a>
<FONT color="green">082</FONT> int tokencnt = 0;<a name="line.82"></a>
<FONT color="green">083</FONT> while (st.hasMoreElements()) {<a name="line.83"></a>
<FONT color="green">084</FONT> String dimval = (String) st.nextElement();<a name="line.84"></a>
<FONT color="green">085</FONT> if (dimval.trim().startsWith("#"))<a name="line.85"></a>
<FONT color="green">086</FONT> break;<a name="line.86"></a>
<FONT color="green">087</FONT> <a name="line.87"></a>
<FONT color="green">088</FONT> int idx = dimval.indexOf(':');<a name="line.88"></a>
<FONT color="green">089</FONT> if (idx >= 0) {<a name="line.89"></a>
<FONT color="green">090</FONT> String dim = dimval.substring(0, idx);<a name="line.90"></a>
<FONT color="green">091</FONT> String val = dimval.substring(idx + 1, dimval.length());<a name="line.91"></a>
<FONT color="green">092</FONT> dimlist.add(dim);<a name="line.92"></a>
<FONT color="green">093</FONT> vallist.add(val);<a name="line.93"></a>
<FONT color="green">094</FONT> } else {<a name="line.94"></a>
<FONT color="green">095</FONT> throw new ParseException("Parse error in FeatureVector of file '"<a name="line.95"></a>
<FONT color="green">096</FONT> + file.toString() + "' at line: " + cnt + ", token: "<a name="line.96"></a>
<FONT color="green">097</FONT> + tokencnt + ". Could not estimate a \"int:double\" pair ?! "<a name="line.97"></a>
<FONT color="green">098</FONT> + file.toString()<a name="line.98"></a>
<FONT color="green">099</FONT> + " contains a wrongly defined feature vector!", 0);<a name="line.99"></a>
<FONT color="green">100</FONT> }<a name="line.100"></a>
<FONT color="green">101</FONT> tokencnt++;<a name="line.101"></a>
<FONT color="green">102</FONT> }<a name="line.102"></a>
<FONT color="green">103</FONT> if (dimlist.size() > 0) {<a name="line.103"></a>
<FONT color="green">104</FONT> double labelvalue = new Double(label).doubleValue();<a name="line.104"></a>
<FONT color="green">105</FONT> int[] dimarray = new int[dimlist.size()];<a name="line.105"></a>
<FONT color="green">106</FONT> double[] valarray = new double[vallist.size()];<a name="line.106"></a>
<FONT color="green">107</FONT> for (int i = 0; i < dimlist.size(); i++) {<a name="line.107"></a>
<FONT color="green">108</FONT> dimarray[i] = new Integer((String) dimlist.get(i)).intValue();<a name="line.108"></a>
<FONT color="green">109</FONT> }<a name="line.109"></a>
<FONT color="green">110</FONT> for (int i = 0; i < vallist.size(); i++) {<a name="line.110"></a>
<FONT color="green">111</FONT> valarray[i] = new Double((String) vallist.get(i)).doubleValue();<a name="line.111"></a>
<FONT color="green">112</FONT> }<a name="line.112"></a>
<FONT color="green">113</FONT> data.add(new LabeledFeatureVector(labelvalue, dimarray, valarray));<a name="line.113"></a>
<FONT color="green">114</FONT> }<a name="line.114"></a>
<FONT color="green">115</FONT> } else {<a name="line.115"></a>
<FONT color="green">116</FONT> throw new ParseException("Parse error in FeatureVector of file '"<a name="line.116"></a>
<FONT color="green">117</FONT> + file.toString() + "' at line: " + cnt + ". "<a name="line.117"></a>
<FONT color="green">118</FONT> + " Wrong format of the labeled feature vector?", 0);<a name="line.118"></a>
<FONT color="green">119</FONT> }<a name="line.119"></a>
<FONT color="green">120</FONT> }<a name="line.120"></a>
<FONT color="green">121</FONT> if (data.size() > 0) {<a name="line.121"></a>
<FONT color="green">122</FONT> traindata = new LabeledFeatureVector[data.size()];<a name="line.122"></a>
<FONT color="green">123</FONT> for (int i = 0; i < data.size(); i++) {<a name="line.123"></a>
<FONT color="green">124</FONT> traindata[i] = (LabeledFeatureVector) data.get(i);<a name="line.124"></a>
<FONT color="green">125</FONT> }<a name="line.125"></a>
<FONT color="green">126</FONT> } else {<a name="line.126"></a>
<FONT color="green">127</FONT> throw new ParseException("No labeled features found within " + cnt<a name="line.127"></a>
<FONT color="green">128</FONT> + "lines of file '" + file.toString() + "'.", 0);<a name="line.128"></a>
<FONT color="green">129</FONT> }<a name="line.129"></a>
<FONT color="green">130</FONT> } catch (IOException ioe) {<a name="line.130"></a>
<FONT color="green">131</FONT> ioe.printStackTrace();<a name="line.131"></a>
<FONT color="green">132</FONT> }<a name="line.132"></a>
<FONT color="green">133</FONT> return traindata;<a name="line.133"></a>
<FONT color="green">134</FONT> }<a name="line.134"></a>
<FONT color="green">135</FONT> <a name="line.135"></a>
<FONT color="green">136</FONT> protected TrainingParameters m_tp;<a name="line.136"></a>
<FONT color="green">137</FONT> <a name="line.137"></a>
<FONT color="green">138</FONT> /**<a name="line.138"></a>
<FONT color="green">139</FONT> * Performs a classifcation step as a native call to SVM-light. If this method<a name="line.139"></a>
<FONT color="green">140</FONT> * is used exlusively, no additional SVMLightModel object has to be kept in<a name="line.140"></a>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -