Changeset 5027:ee91abc4b46a in orange


Ignore:
Timestamp:
07/30/08 12:15:47 (6 years ago)
Author:
ales_erjavec <ales.erjavec@…>
Branch:
default
Convert:
b1ebb4c867fa1c9d60cd7eb63264ae0866f79d0a
Message:

-fixed constant names

File:
1 edited

Legend:

Unmodified
Added
Removed
  • orange/doc/reference/SupportVectorMachines.htm

    r4824 r5027  
    1717<ul> 
    1818 <li>C support vector classification (C_SVC)</li> 
    19  <li>NU support vector classification (NU_SVC)</li> 
    20  <li>ONE CLASS distribution estimation (ONE_CLASS)</li> 
    21  <li>EPSILON support vector regression (EPSILON_SVR)</li> 
    22  <li>NU support vector regression (NU_SVR)</li> 
     19 <li>NU support vector classification (Nu_SVC)</li> 
     20 <li>ONE CLASS distribution estimation (OneClass)</li> 
     21 <li>EPSILON support vector regression (Epsilon_SVR)</li> 
     22 <li>NU support vector regression (Nu_SVR)</li> 
    2323</ul> 
    2424 
     
    4141<dl class=attributes> 
    4242  <dt>svm_type</dt> 
    43   <dd>Defines the type of SVM (can be SVMLearner.C_SVC (default), SVMLearner.NU_SVC, SVMLearner.ONE_CLASS, SVMLearner.EPSILON_SVR, SVMLearner.NU_SVR)</dd> 
     43  <dd>Defines the type of SVM (can be SVMLearner.C_SVC (default), SVMLearner.Nu_SVC, SVMLearner.OneClass, SVMLearner.Epsilon_SVR, SVMLearner.Nu_SVR)</dd> 
    4444  <dt>kernel_type</dt> 
    45   <dd>Defines the type of a kernel to use for learning (can be SVMLearner.RBF (default), SVMLearner.LINEAR, SVMLearner.POLY, SVMLearner.SIGMOID, SVMLearner.CUSTOM)</dd> 
     45  <dd>Defines the type of a kernel to use for learning (can be SVMLearner.RBF (default), SVMLearner.Linear, SVMLearner.Polynomial, SVMLearner.Sigmoid, SVMLearner.Custom)</dd> 
    4646  <dt>degree</dt> 
    47   <dd>Kernel parameter (POLY) (default 3)</dd> 
     47  <dd>Kernel parameter (Polynomial) (default 3)</dd> 
    4848  <dt>gamma</dt> 
    49   <dd>Kernel parameter (POLY/RBF/SIGMOID) (default 1.0/number_of_examples)</dd> 
     49  <dd>Kernel parameter (Polynomial/RBF/Sigmoid) (default 1.0/number_of_examples)</dd> 
    5050  <dt>coef0</dt> 
    51   <dd>Kernel parameter (POLY/SIGMOID) (default 0)</dd> 
     51  <dd>Kernel parameter (Polynomial/Sigmoid) (default 0)</dd> 
    5252  <dt>kernelFunc</dt> 
    53   <dd>Function that will be called if <code>kernel_type</code> is SVMLearner.CUSTOM. It must accept two orange.Example arguments and return a float.</dd> 
     53  <dd>Function that will be called if <code>kernel_type</code> is SVMLearner.Custom. It must accept two orange.Example arguments and return a float.</dd> 
    5454  <dt>C</dt> 
    55   <dd>C parameter for C_SVC, EPSILON_SVR, NU_SVR</dd> 
     55  <dd>C parameter for C_SVC, Epsilon_SVR, Nu_SVR</dd> 
    5656  <dt>nu</dt> 
    57   <dd>Nu parameter for NU_SVC, NU_SVR and ONE_CLASS (default 0.5)</dd> 
     57  <dd>Nu parameter for Nu_SVC, Nu_SVR and OneClass (default 0.5)</dd> 
    5858  <dt>p</dt> 
    59   <dd>Epsilon in loss-function for EPSILON_SVR</dd> 
     59  <dd>Epsilon in loss-function for Epsilon_SVR</dd> 
    6060  <dt>cache_size</dt> 
    6161  <dd>Cache memory size in MB (default 100)</dd> 
     
    7272 
    7373<h2>SVMClassifier</h2> 
    74 <p>Classifier used for classification, regression or distribution estimation (ONE_CLASS). In the later case the return value of the __call__ function can be 1.0 (positive case) or -1.0(negative case).</p> 
     74<p>Classifier used for classification, regression or distribution estimation (OneClass). In the later case the return value of the __call__ function can be 1.0 (positive case) or -1.0(negative case).</p> 
    7575<p>For a multiclass classification problem with k classes there are k*(k-1)/2 1class vs. 1class internal binary classifiers being build. The multiclass classification is then performed by a majority vote.</p> 
    7676<p class=section>Attributes</p> 
     
    9797>>> data=orange.ExampleTable("iris.tab") 
    9898>>> l=orange.SVMLearner() 
    99 >>> l.svm_type=orange.SVMLearner.NU_SVC 
     99>>> l.svm_type=orange.SVMLearner.Nu_SVC 
    100100>>> l.nu=0.3 
    101101>>> l.probability=True 
Note: See TracChangeset for help on using the changeset viewer.