WEKA: A Practical Machine Learning Tool

Download Report

Transcript WEKA: A Practical Machine Learning Tool

WEKA: A Practical Machine Learning Tool
WEKA:A Practical Machine Learning Tool
WEKA: A Practical Machine Learning Tool
Contents
1.Introduction to Weka
2.Explorer
3.Other three main tools
4.Conclusions
5.Reference
WEKA: A Practical Machine Learning Tool
Introduction – What is Weka?




In nature: A flightless bird with an inquisitive nature found only
on the islands of New Zealand.
Actually: A practical machine learning tool developed by the
University of Waikato in New Zealand. It is short for Waikato
Environment for Knowledge Analysis.
Definition: A collection of machine learning algorithms for data
mining tasks.
Language: It is written in Java and runs on almost any platform.
 Usage: The algorithms can either be applied:
(1) directly to a dataset (without writing any codes);
(2) called from your own Java code.
WEKA: A Practical Machine Learning Tool
Introduction – Weka consists of






Explorer
Experimenter
Knowledge flow
Simple Command Line Interface(CLI)
Other tools and Visualization
Java interface
WEKA: A Practical Machine Learning Tool
Explorer




WEKA’s main graphical user interface
Gives access to all its facilities using menu selection and form
filling.(Data-Preprocess/Classify/Cluster/Associate/Select
Attributes/Visualize)
1.Data
2. Operations of Explorer with a Classification example.
WEKA: A Practical Machine Learning Tool
Explorer – Data(1)


From files: CSV, ARFF, C4.5…(no *.xls)
Data loaded from URL or DB
Attribute-Class Attribute
Instance
*.xls
Instances
Tips:weather.arff ( C:/Program Files/Weka/data/ )
*.csv
WEKA: A Practical Machine Learning Tool
Explorer – Data(2)
ARFF(Attribute-Relation File Format)
@relation <relation-name>
@attribute <attribute-name> <datatype>
①numeric (real or integer numbers)
②<nominal-specification>
③string
④date [<date-format>]
@data
% notes
More details:
http://www.cs.waikato.ac.nz/
~ml/weka/arff.html
WEKA: A Practical Machine Learning Tool
Explorer – Operations with an example
Input data Data preprocess Choose classifier  Test
options Run Result analysis
WEKA: A Practical Machine Learning Tool
Explorer
Summary Statistics
Input data
Select an attribute
Visualization
WEKA: A Practical Machine Learning Tool
Explorer
Weka Filter
Tune Parameters
Apply the Filter
Select a Filter
WEKA: A Practical Machine Learning Tool
Explorer
Tune Parameters
Results
Select a Classifier
Decide how to evaluate
Model list
WEKA: A Practical Machine Learning Tool
Right-click on model to get
Menu (save, visualize, etc)
WEKA: A Practical Machine Learning Tool
WEKA: A Practical Machine Learning Tool
Others – Experimenter




Comparing different learning algorithms
------on different datasets
------with various parameter settings
------and analyzing the performance statistics
Click it for Experimenter
WEKA: A Practical Machine Learning Tool
Others – KnowledgeFlow


The KnowledgeFlow provides an alternative to the Explorer as a
graphical front end to Weka's core algorithms.
The KnowledgeFlow is a work in progress so some of the
functionality from the Explorer is not yet available.
Click it for KnowledgyFlow
WEKA: A Practical Machine Learning Tool
Others – Simple command line interface


All implementations of the algorithms have a uniform commandline interface.
java weka.classifiers.trees.J48 -t weather.arff
Click it for Simple CLI
WEKA: A Practical Machine Learning Tool
Conclusions
1.Explorer:
Input data Data preprocess Choose classifier  Test options
Run Result analysis
2.Experimenter:
It is necessary for further studies.
3.Make full use of:
 1. Java tips;
 2. WekaManual.pdf; (C:/Program Files/Weka/ )
 3. Play it yourself!
WEKA: A Practical Machine Learning Tool
Reference







Mitchell, T. Machine Learning, 1997 McGraw Hill.
Ian H. Witten, Eibe Frank, Len Trigg, Mark Hall, Geoffrey Holmes, and Sally Jo
Cunningham (1999). Weka: Practical machine learning tools and techniques with Java
implementations.
Ian H. Witten, Eibe Frank (2005). Data Mining: Practical Machine Learning Tools
and Techniques (Second Edition, 2005). San Francisco: Morgan Kaufmann
Weka Homepage: http://www.cs.waikato.ac.nz/~ml/weka/
Wekawiki: http://weka.wikispaces.com/
Weka on SourceForge.net: http://sourceforge.net/projects/weka
WekaManual.pdf (C:\Program Files\Weka-3-6\WekaManual.pdf)