Scribd
Upload
305 views13 pages

Weka: A Beginner's Guide to ML Tools

Weka is a Java-based machine learning tool that implements various classification algorithms. It has three modes of operation: a graphical user interface (GUI), command line, and Java API. Weka contains sample datasets in ARFF format and can be used to classify data, analyze results, and save models. The document provides instructions for loading data, running classifiers like Naive Bayes through the GUI or command line, evaluating accuracy, and using Weka's tools to complete homework assignments.

Uploaded by

hugobernal
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
305 views13 pages

Weka: A Beginner's Guide to ML Tools

Weka is a Java-based machine learning tool that implements various classification algorithms. It has three modes of operation: a graphical user interface (GUI), command line, and Java API. Weka contains sample datasets in ARFF format and can be used to classify data, analyze results, and save models. The document provides instructions for loading data, running classifiers like Naive Bayes through the GUI or command line, evaluating accuracy, and using Weka's tools to complete homework assignments.

Uploaded by

hugobernal
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

A Short Introduction to Weka

Natural Language Processing Thursday, November 5th

What is weka?

Java-based Machine Learning Tool


Implements numerous classifiers 3 modes of operation

GUI Command Line Java API (not discussed here)

Google: weka java

weka Homepage

[Link]
To run:

java -Xmx1024M -jar ~cs4705/bin/[Link] &

.arff file format

[Link]

% 1. Title: Iris Plants Database % @RELATION iris @ATTRIBUTE @ATTRIBUTE @ATTRIBUTE @ATTRIBUTE @ATTRIBUTE sepallength NUMERIC sepalwidth NUMERIC petallength NUMERIC petalwidth NUMERIC class {Iris-setosa,Iris-versicolor, Iris-virginica}

@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

.arff file format


@attribute attrName {numeric, string, <nominal>, date}

numeric: a number nominal: a (finite) set of strings, e.g.


{Iris-setosa,Iris-versicolor, Irisvirginica}

string: <arbitrary strings>

date: (default ISO-8601) yyyy-MMddTHH:mm:ss

Example Arff Files

~cs4705/bin/weka-3-4-11/data/

[Link] [Link] [Link]

To Classify with weka GUI


1. Run weka GUI
1. (in Unix: java jar [Link])

[Link] 'Start'
[Link]... [Link]-click on Result list entry
a.'Save result buffer'

[Link] 'Explorer'

3.'Open file...'
[Link] 'Classify' tab

5.'Choose' a classifier
[Link] options

b.'Save model'

Classify

Some classifiers to start with.


NaiveBayes JRip J48 SMO

Find References by selecting a classifier


Use Cross-Validation!

Analyzing Results

Important tools for Homework 3

Accuracy

Correctly classified instances

F-measure Confusion matrix

Save model
Visualization

Running weka from the Command Line

[Link]
Running an N-fold cross validation experiment

java -cp ~cs4705/bin/[Link] [Link] -t [Link] -x N -i

Using a predefined test set

java -cp ~cs4705/bin/[Link] [Link] -t [Link] -T [Link]

Saving the model

java -cp ~cs4705/bin/[Link] [Link] -t [Link] -d [Link]

Classifying a test set

java -cp ~cs4705/bin/[Link] [Link] -l [Link] -T [Link]

Getting help

java -cp ~cs4705/bin/[Link] [Link] -?

Homework 3 Weka Workflow


T1

TN

S1 S2 SN
results
Your Feature Extractor

Your Feature Extractor

.arff

Weka

best model

Test .arff

Weka

results

Preprocessing (you)

Experimentation (you)

Grading (us)

Tips for Homework Success


Start early Read instructions carefully Start simply Your system should always work

80/20 Rule

Add features incrementally


This way, you always have something you can turn in.

You might also like