📄 arff.html
字号:
<html><head><title>Attribute-Relation File Format (ARFF)</title></head>
<body bgcolor="white">
<p>
</p><h1>Attribute-Relation File Format (ARFF)</h1>
<p></p>
<p>
April 1st, 2002
</p>
<p>
An ARFF (Attribute-Relation File Format) file is an ASCII text file
that describes a list of instances sharing a set of attributes.
ARFF files were developed by the Machine Learning Project at the
Department of Computer Science of The University of Waikato for use
with the <a href="http://www.cs.waikato.ac.nz/%7Eml/">Weka machine
learning software</a>. This document descibes the version of ARFF
used with Weka versions 3.2 to 3.3; this is an extension of the ARFF
format as described in the data mining book written by Ian H. Witten
and Eibe Frank (the new additions are string attributes,
date attributes, and sparse instances).
</p>
<p>
This explanation was cobbled together by Gordon Paynter
(gordon.paynter@ucr.edu) from the Weka 2.1 ARFF description, email
from Len Trigg (lenbok@myrealbox.com) and Eibe Frank (eibe@cs.waikato.ac.nz),
and some datasets. It has been edited by Richard Kirkby (rkirkby@cs.waikato.ac.nz).
Contact Len if you're interested in seeing the ARFF 3 proposal.
</p>
<h2>Overview</h2>
<p>
ARFF files have two distinct sections. The first section is the
<b>Header</b> information, which is followed the <b>Data</b>
information.
</p>
<p>
The <b>Header</b> of the ARFF file contains the name of the
relation, a list of the attributes (the columns in the data), and
their types. An example header on the standard IRIS dataset looks
like this:
</p>
<pre> % 1. Title: Iris Plants Database
%
% 2. Sources:
% (a) Creator: R.A. Fisher
% (b) Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
% (c) Date: July, 1988
%
@RELATION iris
@ATTRIBUTE sepallength NUMERIC
@ATTRIBUTE sepalwidth NUMERIC
@ATTRIBUTE petallength NUMERIC
@ATTRIBUTE petalwidth NUMERIC
@ATTRIBUTE class {Iris-setosa,Iris-versicolor,Iris-virginica}
</pre>
<p>
The <b>Data</b> of the ARFF file looks like the following:
</p>
<pre> @DATA
5.1,3.5,1.4,0.2,Iris-setosa
4.9,3.0,1.4,0.2,Iris-setosa
4.7,3.2,1.3,0.2,Iris-setosa
4.6,3.1,1.5,0.2,Iris-setosa
5.0,3.6,1.4,0.2,Iris-setosa
5.4,3.9,1.7,0.4,Iris-setosa
4.6,3.4,1.4,0.3,Iris-setosa
5.0,3.4,1.5,0.2,Iris-setosa
4.4,2.9,1.4,0.2,Iris-setosa
4.9,3.1,1.5,0.1,Iris-setosa
</pre>
<p>
Lines that begin with a % are comments. The <b>@RELATION</b>,
<b>@ATTRIBUTE</b> and <b>@DATA</b> declarations are case
insensitive.
</p>
<h2>Examples</h2>
<p>
Several well-known machine learning datasets are distributed with
Weka in the $WEKAHOME/data directory as ARFF files.
</p>
<h2>The ARFF Header Section</h2>
<p>
The ARFF Header section of the file contains the relation
declaration and attribute declarations.
</p>
<h3>The @relation Declaration</h3>
<p>
The relation name is defined as the first line in the ARFF file. The
format is:
</p><pre> @relation <relation-name>
</pre>
where <relation-name> is a string. The string must be quoted if
the name includes spaces.
<p></p>
<h3>The @attribute Declarations</h3>
<p>
Attribute declarations take the form of an orderd sequence of
<b>@attribute</b> statements. Each attribute in the data set has
its own <b>@attribute</b> statement which uniquely defines the name
of that attribute and it's data type. The order the attributes are
declared indicates the column position in the data section of the
file. For example, if an attribute is the third one declared then
Weka expects that all that attributes values will be found in the
third comma delimited column.
</p>
<p>
The format for the <b>@attribute</b> statement is:
</p><pre> @attribute <attribute-name> <datatype>
</pre>
where the <i><attribute-name></i> must start with an
alphabetic character. If spaces are to be included in the name
then the entire name must be quoted.
<p></p>
<p>
The <i><datatype></i> can be any of the four types currently
(version 3.2.1) supported by Weka:
</p><ul>
<li>numeric</li>
<li><nominal-specification></li>
<li>string</li>
<li>date [<date-format>]</li>
</ul>
where <nominal-specification> and <date-format> are
defined below. The keywords <b>numeric</b>,
<b>string</b> and <b>date</b> are case insensitive.
<p></p>
<h4>Numeric attributes</h4>
<p>
Numeric attributes can be real or integer numbers.
</p>
<h4>Nominal attributes</h4>
<p>
Nominal values are defined by providing an
<nominal-specification> listing the possible values:
{<nominal-name1>, <nominal-name2>, <nominal-name3>, ...}
</p>
<p>
For example, the class value of the Iris dataset can be defined as
follows:
</p><pre> @ATTRIBUTE class {Iris-setosa,Iris-versicolor,Iris-virginica}
</pre>
<p></p>
<p>
Values that contain spaces must be quoted.
</p>
<h4>String attributes</h4>
<p>
String attributes allow us to create attributes containing
arbitrary textual values. This is very useful in text-mining
applications, as we can create datasets with string attributes,
then write Weka Filters to manipulate strings (like
StringToWordVectorFilter). String attributes are declared as
follows:
</p><pre> @ATTRIBUTE LCC string
</pre>
<p></p>
<h4>Date attributes</h4>
<p>
Date attribute declarations take the form:
</p><pre> @attribute <name> date [<date-format>]
</pre>
where <name> is the name for the attribute and
<date-format> is an optional string specifying how date
values should be parsed and printed (this is the same format used
by SimpleDateFormat). The default format string accepts the
ISO-8601 combined date and time format: "yyyy-MM-dd'T'HH:mm:ss".
<p></p>
<p>
Dates must be specified in the data section as the corresponding
string representations of the date/time (see example below).
</p>
<h2>ARFF Data Section</h2>
<p>
The ARFF Data section of the file contains the data declaration
line and the actual instance lines.
</p>
<h3>The @data Declaration</h3>
<p>
The <b>@data</b> declaration is a single line denoting the start of
the data segment in the file. The format is:
</p><pre> @data
</pre>
<p></p>
<h3>The instance data</h3>
<p>
Each instance is represented on a single line, with carriage returns
denoting the end of the instance.
</p>
<p>
Attribute values for each instance are delimited by commas. They
must appear in the order that they were declared in the header
section (i.e. the data corresponding to the nth <b>@attribute</b>
declaration is always the nth field of the attribute).
</p>
<p>
Missing values are represented by a single question mark, as in:
</p><pre> @data
4.4,?,1.5,?,Iris-setosa
</pre>
<p></p>
<p>
Values of string and nominal attributes are case sensitive, and any
that contain space must be quoted, as follows:
</p><pre> @relation LCCvsLCSH
@attribute LCC string
@attribute LCSH string
@data
AG5, 'Encyclopedias and dictionaries.;Twentieth century.'
AS262, 'Science -- Soviet Union -- History.'
AE5, 'Encyclopedias and dictionaries.'
AS281, 'Astronomy, Assyro-Babylonian.;Moon -- Phases.'
AS281, 'Astronomy, Assyro-Babylonian.;Moon -- Tables.'
</pre>
<p></p>
<p>
Dates must be specified in the data section using the string
representation specified in the attribute declaration. For
example:
</p><pre> @RELATION Timestamps
@ATTRIBUTE timestamp DATE "yyyy-MM-dd HH:mm:ss"
@DATA
"2001-04-03 12:12:12"
"2001-05-03 12:59:55"
</pre>
<p></p>
<h2>Sparse ARFF files</h2>
<p>
Sparse ARFF files are very similar to ARFF files, but data with
value 0 are not be explicitly represented.
</p>
<p>
Sparse ARFF files have the same header (i.e <b>@relation</b> and
<b>@attribute</b> tags) but the data section is different. Instead of
representing each value in order, like this:
</p><pre> @data
0, X, 0, Y, "class A"
0, 0, W, 0, "class B"
</pre>
the non-zero attributes are explicitly identified by attribute
number and their value stated, like this:
<pre> @data
{1 X, 3 Y, 4 "class A"}
{2 W, 4 "class B"}
</pre>
<p></p>
<p>
Each instance is surrounded by curly braces, and the format for
each entry is: <index> <space> <value> where index is the
attribute index (starting from 0).
</p>
<p>
Note that the omitted values in a sparse instance are <b>0</b>,
they are not "missing" values! If a value is unknown,
you must explicitly represent it with a question mark (?).
</p>
<p>
<b>Warning</b>: There is a known problem saving SparseInstance
objects from datasets that have string attributes. In Weka, string
and nominal data values are stored as numbers; these numbers act as
indexes into an array of possible attribute values (this is very
efficient). However, the first string value is assigned index 0:
this means that, internally, this value is stored as a 0. When a
SparseInstance is written, string instances with internal value 0
are not output, so their string value is lost (and when the arff
file is read again, the default value 0 is the index of a different
string value, so the attribute value appears to change). To get
around this problem, add a dummy string value at index 0 that is
never used whenever you declare string attributes that are likely
to be used in SparseInstance objects and saved as Sparse ARFF
files.
</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 + -