I have referred to this over and over again. I learnt how to use SVM using this article. This is like a newbie's guide to SVM to whoever is doing research. Page on ntu.edu.tw Infact I think this has been cited over 2000 times in various places!
There are two versions of Weka: Weka 3.8 is the latest stable version and Weka 3.9 is the development version. For the bleeding edge, it is also possible to download nightly snapshots. Stable versions receive only bug fixes, while the development version receives new features.
Weka 3.8 and 3.9 feature a package management system that makes it easy for the Weka community to add new functionality to Weka. The package management system requires an internet connection in order to download and install packages.
If your computer has a display that has a high pixel density, and you are using Windows, Weka's user interfaces may not be scaled appropriately and appear tiny. Installing Java 9 or later solves this problem. Alternatively, in the Program menu of Weka's GUIChooser, go into Settings, and select WindowsLookAndFeel from the 'Look and feel for UI' dropdown menu. Some Weka packages currently do not work (properly) with Java 9 or later (tigerJython and scatterPlot3D).- SnapshotsEvery night a snapshot of the Subversion repository is taken, compiled and put together in ZIP files. Those who want the latest bug fixes before the next official stable release is made can download these snapshots here.
- Stable versionWeka 3.8 is the latest stable version of Weka. This branch of Weka receives bug fixes only, although new features may become available in packages. There are different options for downloading and installing it on your system:
- WindowsClick here to download a self-extracting executable for 64-bit Windows that includes Oracle's 64-bit Java VM 1.8
(weka-3-8-3jre-x64.exe; 120.3 MB)Click here to download a self-extracting executable for 64-bit Windows without a Java VM
(weka-3-8-3-x64.exe; 51 MB)Click here to download a self-extracting executable for 32-bit Windows that includes Oracle's 32-bit Java VM 1.8
(weka-3-8-3jre.exe; 113.4 MB)Click here to download a self-extracting executable for 32-bit Windows without a Java VM
(weka-3-8-3.exe; 51 MB)These executables will install Weka in your Program Menu. Download the version without the Java VM if you already have Java 1.8 (or later) on your system. - Mac OS XClick here to download a disk image for OS X that contains a Mac application including Amazon's Corretto Java 1.8 JVM
(weka-3-8-3-corretto-jvm.dmg; 112.9 MB) - Other platforms (Linux, etc.)Click here to download a zip archive containing Weka
(weka-3-8-3.zip; 51.4 MB)First unzip the zip file. This will create a new directory called weka-3-8-3. To run Weka, change into that directory and typejava -jar weka.jar
Note that Java needs to be installed on your system for this to work. Also note, that using-jar
will override your current CLASSPATH variable and only use theweka.jar
.
- Windows
- Developer versionThis is the trunk of Weka and continues from the stable-3-8 code line. It receives both bug fixes and new features.
- WindowsClick here to download a self-extracting executable that includes 64 bit Java VM 1.8
(weka-3-9-3jre-x64.exe; 120.1 MB)Click here to download a self-extracting executable without the Java VM
(weka-3-9-3-x64.exe; 50.9 MB)Click here to download a self-extracting executable that includes Java VM 1.8
(weka-3-9-3jre.exe; 113.2 MB)Click here to download a self-extracting executable without the Java VM
(weka-3-9-3.exe; 50.9 MB)These executables will install Weka in your Program Menu. Download the second version if you already have Java 1.8 (or later) on your system. - Mac OS XClick here to download a disk image for OS X that contains a Mac application including Amazon's Corretto Java 1.8 JVM
(weka-3-9-3-corretto-jvm.dmg; 142.1 MB) - Other platforms (Linux, etc.)Click here to download a zip archive containing Weka
(weka-3-9-3.zip; 51.3 MB)First unzip the zip file. This will create a new directory called weka-3-9-3. To run Weka, change into that directory and typejava -jar weka.jar
Note that Java needs to be installed on your system for this to work. Also note, that using-jar
will override your current CLASSPATH variable and only use theweka.jar
.
- Windows
- Old versionsAll old versions of Weka are available from the Sourceforge website.
installedPackageCache.ser
in the packages
folder that resides in the wekafiles
folder in your user home. Also, serialized models created in 3.7 are incompatible with 3.8. The model migrator tool that can migrate some models to 3.8 (a known exception is RandomForest). Usage is as follows:java -cp <path to modelMigrator.jar>:<path to weka.jar> weka.core.ModelMigrator -i <path to old serialized weka model> -o <upgraded model file name>
Ranch Hand
posted 5 years agoHi
A question from left field if I may.....................
I am using Windows 7 and weka 3.7.10
I am calling weka (an open source data mining program] in a larger java program
I am attempting to use 7 classifiers
I have 6 working OK with my data but the 7th is a problem
It is libsvm and is a third party classifier
I have followed all the instructions from the weka pages but continue to get the following error message
libsvm.jar is not in the classpath
I have asked at the weka forum but the authors of weka do not have much experience using weka under windows!
Can I improve on my error trapping vode to help identify the 'real' problem?
Should I be thinking of changing my operation system to linux?
That is I have
1) gone to environment variables and added paths to libsvm.jar and LibSVM.jar
2) I have edited runweka.ini and added cp = ...... twice (one for each of the above jar files)
Any suggestions welcome
A question from left field if I may.....................
I am using Windows 7 and weka 3.7.10
I am calling weka (an open source data mining program] in a larger java program
I am attempting to use 7 classifiers
I have 6 working OK with my data but the 7th is a problem
It is libsvm and is a third party classifier
I have followed all the instructions from the weka pages but continue to get the following error message
libsvm.jar is not in the classpath
I have asked at the weka forum but the authors of weka do not have much experience using weka under windows!
Can I improve on my error trapping vode to help identify the 'real' problem?
Should I be thinking of changing my operation system to linux?
That is I have
1) gone to environment variables and added paths to libsvm.jar and LibSVM.jar
2) I have edited runweka.ini and added cp = ...... twice (one for each of the above jar files)
Any suggestions welcome
Marshal
posted 5 years agoQuestion too difficult for “beginning”. Moving. Maybe to the right place, maybe not
Ranch Hand
posted 5 years agoHi again
I have just received an email from one of the co-authors of weka stating that I do not have to do either 1) or 2) in my original posting if I am using weka 3.7 (which I am)
and so I have no idea on what to do next?
I have just received an email from one of the co-authors of weka stating that I do not have to do either 1) or 2) in my original posting if I am using weka 3.7 (which I am)
and so I have no idea on what to do next?
Sheriff
posted 5 years ago![Install Libsvm Weka Windows Install Libsvm Weka Windows](https://3qeqpr26caki16dnhd19sv6by6v-wpengine.netdna-ssl.com/wp-content/uploads/2014/02/weka-zeror.png)
Seems to me that all you needed to do was to put libsvm.jar into the classpath used by your application at run time. I don't know what those environment variables you changed were, but it's unnecessary to use any environment variables at all. It might be as simple as just adding libsvm.jar to the list of jars in your -cp parameter at the command line -- if you are using the command line, which you didn't say. At any rate your problem appears to be mostly in setting the classpath. So if you could start by explaining how you run your code, I expect somebody here could explain how to modify that.
Ranch Hand
posted 5 years agoHi Paul
my code starts with importing com.dukascopy.api
The API has about a dozen sections - one of which is OnBar
Here I decide whether I wish to open a trade
If I do, I do some calculations and then run weka in a loop handling six different classifiers
The code here is:-
try {
new WekaApp().doIt();
}
catch (Exception e) {
}
**************
private class WekaApp()
etc. etc.
Is this want you are asking ?
Bob M
my code starts with importing com.dukascopy.api
The API has about a dozen sections - one of which is OnBar
Here I decide whether I wish to open a trade
If I do, I do some calculations and then run weka in a loop handling six different classifiers
The code here is:-
try {
new WekaApp().doIt();
}
catch (Exception e) {
}
**************
private class WekaApp()
etc. etc.
Is this want you are asking ?
Bob M
Ranch Hand
posted 5 years agoHi guys
I am desperate for any sort of answer to my problem
Also, I should have stated that by coming away from my java program altogether and simply running weka on its own, I am able to get the classifier LIBSVM selected and used
Bob M
I am desperate for any sort of answer to my problem
Also, I should have stated that by coming away from my java program altogether and simply running weka on its own, I am able to get the classifier LIBSVM selected and used
Bob M