SVMlight windows使用

首先在http://svmlight.joachims.org/下载适合自己系统的SVMlight版本。

本文以Windows为例。下载下来svm_classify.exe和svm_learn.exe。

在它的网站上有例子可以下载试用。

输入的数据可以有多种文件格式，txt，log，dat等。

SVM输入文件的数据格式为: #SVMlight和LibSVM相同

[label] [index1]:[value1] [index2]:[value2] …

[label] [index1]:[value1] [index2]:[value2] …

label

或说是class, 就是你要分类的种类，通常是一些整数。

index

是有顺序的索引，通常是连续的整数。

value

就是用来 train 的数据，通常是一堆实数。

每一行都是如上的结构, 意思就是: 我有一排数据, 分别是 value1, value2, …. value, (而且它们的顺序已由 index 分别指定)，这排数据的分类结果就是label。

或许你会不太懂，为什么会是 value1,value2,…. 这样一排呢？ 这牵涉到 SVM 的原理。你可以这样想（我没说这是正确的）， 它的名字就叫 Support “Vector” Machine，所以输入的训练数据是 “Vector”(向量), 也就是一排的 x1, x2, x3, … 这些值就是 value，而 x[n] 的n就是由index 指定。这些东西又称为 “（属性）attribute”。

真实的情况是，大部份时候我们给定的数据可能有很多 “特征(feature)” 或说 “属性(attribute)”，所以输入会是一组的。举例来说，以前面点分区的例子 来说，我们不是每个点都有 X 跟 Y 的坐标吗？所以它就有两种属性。假定我有两个点： (0,3) 跟 (5,8) 分别在 label(class) 1 跟 2 ，那就会写成

1 1:0 2:3
2 1:5 2:8
同理，空间中的三维坐标就等于有三组属性。这种文件格式最大的好处就是可以使用稀疏矩阵（sparse matrix），或说有些数据的属性可以有缺失。

在命令行输入

svm_learn [options] example_file model_file

可选的参数有：

General options:
         -?          - this help
         -v [0..3]   - verbosity level (default 1)
Learning options:
         -z {c,r,p}  - select between classification (c), regression (r), and 
                       preference ranking (p) (see [Joachims, 2002c])
                       (default classification)          
         -c float    - C: trade-off between training error
                       and margin (default [avg. x*x]^-1)
         -w [0..]    - epsilon width of tube for regression
                       (default 0.1)
         -j float    - Cost: cost-factor, by which training errors on
                       positive examples outweight errors on negative
                       examples (default 1) (see [Morik et al., 1999])
         -b [0,1]    - use biased hyperplane (i.e. x*w+b0) instead
                       of unbiased hyperplane (i.e. x*w0) (default 1)
         -i [0,1]    - remove inconsistent training examples
                       and retrain (default 0)
Performance estimation options:
         -x [0,1]    - compute leave-one-out estimates (default 0)
                       (see [5])
         -o ]0..2]   - value of rho for XiAlpha-estimator and for pruning
                       leave-one-out computation (default 1.0) 
                       (see [Joachims, 2002a])
         -k [0..100] - search depth for extended XiAlpha-estimator
                       (default 0)
Transduction options (see [Joachims, 1999c], [Joachims, 2002a]):
         -p [0..1]   - fraction of unlabeled examples to be classified
                       into the positive class (default is the ratio of
                       positive and negative examples in the training data)
Kernel options:
         -t int      - type of kernel function:
                        0: linear (default)
                        1: polynomial (s a*b+c)^d
                        2: radial basis function exp(-gamma ||a-b||^2)
                        3: sigmoid tanh(s a*b + c)
                        4: user defined kernel from kernel.h
         -d int      - parameter d in polynomial kernel
         -g float    - parameter gamma in rbf kernel
         -s float    - parameter s in sigmoid/poly kernel
         -r float    - parameter c in sigmoid/poly kernel
         -u string   - parameter of user defined kernel
Optimization options (see [Joachims, 1999a], [Joachims, 2002a]):
         -q [2..]    - maximum size of QP-subproblems (default 10)
         -n [2..q]   - number of new variables entering the working set
                       in each iteration (default n = q). Set n<q to prevent
                       zig-zagging.
         -m [5..]    - size of cache for kernel evaluations in MB (default 40)
                       The larger the faster...
         -e float    - eps: Allow that error for termination criterion
                       [y [w*x+b] - 1] = eps (default 0.001) 
         -h [5..]    - number of iterations a variable needs to be
                       optimal before considered for shrinking (default 100) 
         -f [0,1]    - do final optimality check for variables removed by
                       shrinking. Although this test is usually positive, there
                       is no guarantee that the optimum was found if the test is
                       omitted. (default 1) 
         -y string   -> if option is given, reads alphas from file with given
                        and uses them as starting point. (default 'disabled')
         -# int      -> terminate optimization, if no progress after this
                        number of iterations. (default 100000)
Output options: 
         -l char     - file to write predicted labels of unlabeled examples 
                       into after transductive learning 
         -a char     - write all alphas to this file after learning (in the 
                       same order as in the training set)

A more detailed description of the parameters and how they link to the respective algorithms is given in the appendix of [Joachims, 2002a].

The input file example_file contains the training examples. The first lines may contain comments and are ignored if they start with #. Each of the following lines represents one training example and is of the following format:

<line> .=. <target> <feature>:<value> <feature>:<value> ... <feature>:<value> # <info>
<target> .=. +1 | -1 | 0 | <float> 
<feature> .=. <integer> | "qid"
<value> .=. <float>
<info> .=. <string> 部分内容摘自

http://blog.sina.com.cn/s/blog_53c2bcbb01008zi5.html