ref_selectd.xml

使用具有增量学习的监控式学习方法。包括几个不同的分类算法。

<refmeta>
<refentrytitle>selectd</refentrytitle>
<manvolnum>8</manvolnum>
</refmeta>

<refnamediv>
<refname>selectd</refname>
<refpurpose>email classification daemon</refpurpose>
</refnamediv>

<refsynopsisdiv>
<cmdsynopsis>
<command>selectd</command>
<arg><option>-a <replaceable>address</replaceable></option></arg>
<arg><option>-f <replaceable>configfile</replaceable></option></arg>
</cmdsynopsis>
</refsynopsisdiv>


<refsect1>
<title>Description</title>
<para>
To be written.
</para>
</refsect1>


<refsect1>
<title>Command Line Options</title>

<variablelist>

<varlistentry>
<term><option>-a</option> or <option>--address</option></term>
<listitem>
<simpara>
Selects socket address to use.
This overrides the value given in the configuration file.
</simpara>
</listitem>
</varlistentry>

<varlistentry>
<term><option>-f</option> or <option>--conf-file</option></term>
<listitem>
<simpara>
Selects which configuration file to use.
Default value is <filename>$HOME/.select/selectd.conf</filename>.
</simpara>
</listitem>
</varlistentry>

</variablelist>

</refsect1>


<refsect1>
<title>Configuration</title>
<para>
Configuration options for <application>selectd</application> is given in a file.
The default name of this file is <filename>$HOME/.select/selectd.conf</filename>.
</para>

<refsect2>
<title>Location options</title>

<para>
Options describing location of directories etc.
</para>

<refsect3>
<title>address</title>
<para>
Specifies the daemon address.
Addresses beginning with the character @ are interpreted as abstract addresses, otherwise they are filename addresses.
Default value is @my_select_classifier.
<programlisting>address                                 # Default address
address qwerty                          # Use the specified address
</programlisting>
</para>
</refsect3>

<refsect3>
<title>data_dir</title>
<para>
Data directory.
Indicates which directory database files are stored in.
Default value is to not save databases.
<programlisting>data_dir                                # Default: Don't save databases
data_dir        /home/mikael/.select    # Use the specified directory
</programlisting>
</para>
</refsect3>

<refsect3>
<title>share_dir</title>
<para>
Share directory.
Indicates which directory language files are stored in.
Default value is <filename>/usr/local/share/select</filename>.
<programlisting>share_dir                               # Default: /usr/local/share/select
share_dir       share                   # Use the specified directory
</programlisting>
</para>
</refsect3>

<refsect3>
<title>plugin_dir</title>
<para>
Plugin directory.
Indicates which directory classifiers and stemmers are stored in.
Default value is <filename>/usr/local/lib/select</filename>.
<programlisting>plugin_dir                              # Default: /usr/local/lib/select
plugin_dir      plugins                 # Use the specified directory
</programlisting>
</para>
</refsect3>

</refsect2>

<refsect2>
<title>Language options</title>

<para>
Options describing language handling.
</para>

<refsect3>
<title>language</title>
<para>
Specifies a language.
May be present several times. The first presence sets the default language.
Default value is no languages.
</para>
<para>
A language is specified by its name followed by a default locale string.
The name must be the same as is used by its stopwords and stemmer.
The stopwords and stemmers distibuted with <application>Select</application> use the language codes specified in ISO 639 as names.
If you use a custom stopword list (for example for several languages) a new name should be invented for it.
<programlisting>language                                # No languages
language        en C                    # English
language        sv sv_SE                # Swedish
language        sven sv_SE              # Swenglish
</programlisting>
</para>
</refsect3>

<refsect3>
<title>identifier</title>
<para>
Language identification.
Default value is off.
<programlisting>identifier      on                      # Use language identification
identifier      off                     # Don't use language identification
</programlisting>
</para>
</refsect3>

<refsect3>
<title>stemming</title>
<para>
Stemming.
Default value is off.
<programlisting>stemming        on                      # Perform stemming for chosen languages
stemming        off                     # Don't perform stemming
</programlisting>
</para>
</refsect3>

<refsect3>
<title>stopwords</title>
<para>
Stopwords.
Default value is off.
<programlisting>stopwords       on                      # Use stopwords for chosen languages
stopwords       off                     # Don't use any stopwords
</programlisting>
</para>
</refsect3>

</refsect2>

<refsect2>
<title>Classifier Options</title>

<para>
Classifiers are configured in special classifier sections in the configuration file.
A classifier selection is started by a line like this:
<screen>[classifier]
</screen>
There may be several classifiers specified.
</para>

<refsect3>
<title>name</title>
<para>
Classifier name.
No default value.
<programlisting>name            Henry                   # Call the classifier Henry
</programlisting>
</para>
</refsect3>

<refsect3>
<title>classifier</title>
<para>
Classifier algorithm.
No default value.
<programlisting># Multi classifiers
classifier      Alma                    # Alma classifier
classifier      NaiveBayes              # Naive bayes classifier
classifier      Perceptron              # Perceptron classifier
classifier      Rocchio                 # Rocchio classifier
classifier      Romma                   # Romma classifier
classifier      WidrowHoff              # Widrow-Hoff (LMS) classifier
classifier      WMA                     # Weighted Majority Algorithm
# Document classifiers
classifier      From                    # Sender classifier
classifier      Reply                   # Thread classifier
</programlisting>
</para>
</refsect3>

<refsect3>
<title>type</title>
<para>
Classifier type.
No default value.
<programlisting>type            multi_one               # Multi classifier, type ONE_MAX
type            multi_rest              # Multi classifier, type REST_MAX
type            multi_linmax            # Multi classifier, type LIN_MAX
type            multi_uc                # Multi classifier, type UC_MAX
type            document                # Document classifier
</programlisting>
</para>
</refsect3>

<refsect3>
<title>options</title>
<para>
Classifier options.
A string which is passed on to the classifier for interpretation.
Is used for changing the behavior of the classifier.
The string consists of a comma-separated list of entries of the form key=value.
Valid keys and values depends on the classifier.
Default value is none.
<programlisting>options                                 # No options
options         n=200,o=fifo            # Classifier dependent options
</programlisting>
</para>
</refsect3>

<refsect3>
<title>tokenizer</title>
<para>
Tokenizer.
Specifies which method is used for transforming texts into text-tokens.
Default value is alpha.
<programlisting>tokenizer       alpha                   # Alpha tokenizer
tokenizer       wspace.byte             # Whitespace byte tokenizer
tokenizer       ngram.byte              # N-gram byte tokenizer
tokenizer       null                    # Null tokenizer
</programlisting>
</para>
</refsect3>

<refsect3>
<title>vectorizer</title>
<para>
Vectorization mode.
Specifies which method is used for transforming text-tokens into a vector.
Default value is tf.
<programlisting>vectorizer      bool                    # Boolean
vectorizer      tf                      # Term Frequency
vectorizer      tfidf                   # TF-IDF
</programlisting>
</para>
</refsect3>

<refsect3>
<title>normalizer</title>
<para>
Normalization mode.
Specifies how vectors should be normalized.
Default value is none.
<programlisting>normalizer                              # No normalization
normalizer      cosine                  # Cosine normalization
</programlisting>
</para>
</refsect3>

</refsect2>

<refsect2>
<title>Example</title>

<para>
Here is a complete example of a <application>selectd</application> configuration file:
</para>
<informalexample>
<programlisting>address                                 # Use default address
data_dir        /home/mikael/.select    # Save databases in specified directory
share_dir                               # Default: /usr/local/share/select
plugin_dir                              # Default: /usr/local/lib/select

language        sven sv_SE              # Swenglish
identifier      off                     # Don't use language identification
stemming        off                     # Don't perform stemming
stopwords       on                      # Use stopwords for chosen languages

[classifier]
name            nb                      # Name the classifier nb
classifier      NaiveBayes              # NaiveBayes classifier
type            multi_one               # Multi classifier, type ONE_MAX
options                                 # No options
tokenizer       alpha                   # Alpha tokenizer
vectorizer      tfidf                   # TF-IDF vectorizer
normalizer                              # No normalization
</programlisting>
</informalexample>

</refsect2>

</refsect1>