📄 doc2mat.html
字号:
<HTML><HEAD><TITLE>doc2mat - Converting documents into the vector-space format used by CLUTO</TITLE><LINK REV="made" HREF="mailto:bhcompile@daffy.perf.redhat.com"></HEAD><BODY><A NAME="__index__"></A><!-- INDEX BEGIN --><UL> <LI><A HREF="#name">NAME</A></LI> <LI><A HREF="#synopsis">SYNOPSIS</A></LI> <LI><A HREF="#arguments">ARGUMENTS</A></LI> <LI><A HREF="#options">OPTIONS</A></LI> <LI><A HREF="#description">DESCRIPTION</A></LI> <LI><A HREF="#author">AUTHOR</A></LI></UL><!-- INDEX END --><HR><P><H1><A NAME="name">NAME</A></H1><P>doc2mat - Converting documents into the vector-space format used by CLUTO</P><P><HR><H1><A NAME="synopsis">SYNOPSIS</A></H1><P>doc2mat [options] doc-file mat-file</P><P><HR><H1><A NAME="arguments">ARGUMENTS</A></H1><P><STRONG>doc2mat</STRONG> takes as input two arguments. The first argument is thename of the file that stores the documents to be converted into the vector-space format used by CLUTO and the second argument isthe name of the file that stores the resulting document-term matrix.</P><DL><DT><STRONG><A NAME="item_doc%2Dfile"><STRONG>doc-file</STRONG></A></STRONG><BR><DD>This is the name of the file that stores the documents using one document at each line format.<P></P><DT><STRONG><A NAME="item_mat%2Dfile"><STRONG>mat-file</STRONG></A></STRONG><BR><DD>This is the name of the file that will store the generated CLUTO compatible mat file, and the file-stem for the .clabel file and the .rlabel file if itis applicable.<P></P></DL><P><HR><H1><A NAME="options">OPTIONS</A></H1><DL><DT><STRONG><A NAME="item_%2Dnostem"><STRONG>-nostem</STRONG></A></STRONG><BR><DD>Disable word stemming. By default all words are stemmed.<P></P><DT><STRONG><A NAME="item_%2Dnostop"><STRONG>-nostop</STRONG></A></STRONG><BR><DD>Disable the elimination of stop words using the internal list of stop words. By default stop words are eliminated.<P></P><DT><STRONG><A NAME="item_%2Dmystoplist%3Dfile"><STRONG>-mystoplist=file</STRONG></A></STRONG><BR><DD>Specifies a user supplied file that specifies local stop-words.If the <STRONG>-nostop</STRONG> option has been specified, then by providinga user-supplied file you essentially over-ride all internal stopwords.<P></P><DT><STRONG><A NAME="item_%2Dskipnumeric"><STRONG>-skipnumeric</STRONG></A></STRONG><BR><DD>Specifies that any words that contain numeric digits are to be eliminated. By default, a token that contains numeric digits is retained.<P></P><DT><STRONG><A NAME="item_%2Dminwlen%3Dint"><STRONG>-minwlen=int</STRONG></A></STRONG><BR><DD>Specifies the length of the smallest token to be kept prior to stemming.The default value is three.<P></P><DT><STRONG><A NAME="item_%2Dnlskip%3Dint"><STRONG>-nlskip=int</STRONG></A></STRONG><BR><DD>Indicates the number of leading tokens to be ignored duringtext processing. This parameter is useful for ignoring anydocument identifier information that may be in the beginningof each document line. The default value is zero.<P></P><DT><STRONG><A NAME="item_%2Dtokfile"><STRONG>-tokfile</STRONG></A></STRONG><BR><DD>Writes the token representation of each document after performing thetokenization and/or stemming and stop-word elimination.<P></P><DT><STRONG><A NAME="item_%2Dhelp"><STRONG>-help</STRONG></A></STRONG><BR><DD>Displays this information.<P></P></DL><P><HR><H1><A NAME="description">DESCRIPTION</A></H1><P><STRONG>doc2mat</STRONG> convertes a set of documents into a vector-space formatand stores the resulting document-term matrix into a mat-file thatis compatible with CLUTO's clustering algorithms.</P><P>The documents are supplied in the file <EM>doc-file</EM>, and each documentmust be stored on a single line in that file. As a result, the totalnumber of documents in the resulting document-term matrix will be equalto the number of rows in the file <EM>doc-file</EM>.</P><P><STRONG>doc2mat</STRONG> supports both word stemming (using Porter's stemming algorithm)and stop-word elimination. It contains a default list of stop-words thatit can be either ignored or augmented by providing an file containing alist of words to be eliminated as well. This user-supplied stop-listfile is supplied using the <STRONG>-mystoplist</STRONG> option and should containa white-space separated list of words. All of these words can be on the same line or multiple lines. Note that stop-word elimination occursbefore stemming, so the user-supplied stop words should not be stemmed.</P><P>The tokenization performed by <STRONG>doc2mat</STRONG> is quite straight-forward. Itstarts by replacing all non-alphanumeric characters with spaces, andthen the white-space characters are used to break up the line into tokens. Each of these tokens is then checked against the stop-list, and if they are not there they get stemmed. By using the <STRONG>-skipnumeric</STRONG> option you can force <STRONG>doc2mat</STRONG> to eliminate any tokens that containnumeric digits. Also, by specifying the <STRONG>-tokfile</STRONG> option, <STRONG>doc2mat</STRONG> will create a file called <EM>mat-file.tokens</EM>, in which each line stores the tokenized form of each document.</P><P>Some of leading fields of each line can potentially store document specific information (e.g., document identifier, class label, <EM>etc</EM>), and they canbe ignored by using the <STRONG>-nlskip</STRONG> option. In cases in which <STRONG>-nlskip</STRONG> isgreater than zero, the <STRONG>-nlskip</STRONG> leading tokens are treated as the labelof each row and they are written in the file called <EM>mat-file.rlabel</EM>.</P><P><HR><H1><A NAME="author">AUTHOR</A></H1><P>George Karypis <<A HREF="mailto:karypis@cs.umn.edu">karypis@cs.umn.edu</A>></P></BODY></HTML>⌨️ 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 + -