Felomeng翻译：libsvm2.88之示例

<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-scale -l -1 -u 1 -s range train > train.scale</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-scale -r range test > test.scale</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style="font-size: small;"><span style="">将训练数据中的每个属性都在区间</span><span style=""><span style="font-family: Times New Roman;">[-1,1]</span></span><span style="">中数值化。先将数据化因子保存到文件</span><span style=""><span style="font-family: Times New Roman;">range</span></span><span style="">中，然后再用于数值化测试数据。</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-train -s 0 -c 5 -t 2 -g 0.5 -e 0.1 data_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style="font-size: small;"><span style="">使用</span><span style=""><span style="font-family: Times New Roman;">RBF</span></span><span style="">内核函数</span><span style=""><span style="font-family: Times New Roman;">exp(-0.5|u-v|^2)</span></span><span style="">，</span><span style=""><span style="font-family: Times New Roman;">C=10</span></span><span style="">，并且设定结束条件为</span><span style=""><span style="font-family: Times New Roman;">0.1</span></span><span style="">来训练分类器</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-train -s 3 -p 0.1 -t 0 data_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style="font-size: small;"><span style="">使用线性内核函数</span><span style=""><span style="font-family: Times New Roman;">u'v</span></span><span style="">，设定损失方程中</span><span style=""><span style="font-family: Times New Roman;">epsilon=0.1</span></span><span style="">解决支持向量机回归问题。</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-train -c 10 -w1 1 -w-1 5 data_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style="font-size: small;"><span style="">对类</span><span style=""><span style="font-family: Times New Roman;">1</span></span><span style="">使用惩罚因子</span><span style=""><span style="font-family: Times New Roman;">10=1*10</span></span><span style="">，而对类</span><span style=""><span style="font-family: Times New Roman;">-1</span></span><span style="">使用惩罚因子</span><span style=""><span style="font-family: Times New Roman;">50=5*50</span></span><span style="">来训练分类器。</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-train -s 0 -c 100 -g 0.1 -v 5 data_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style="font-size: small;"><span style="">使用参数</span><span style=""><span style="font-family: Times New Roman;">C=100</span></span><span style="">和</span><span style=""><span style="font-family: Times New Roman;">gamma=0.1</span></span><span style="">对分类器进行五次交叉验证。</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-train -s 0 -b 1 data_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small; font-family: Times New Roman;">> svm-predict -b 1 test_file data_file.model output_file</span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span lang="EN-US"><span style="font-size: small; font-family: Times New Roman;"></span></span></p>
<p class="MsoNormal" style="margin: 0cm 0cm 0pt;"><span style=""><span style="font-size: small;">根据概率信息和有概率期望的预测数据获得一个模型。</span></span></p>