I am a total newbie when it comes to Weka.
As a part of my Bachelor thesis I want to evaluate my results against a machine learning algorithm, so I decided to give Weka a try.
I have created an ARFF file with labelled texts (short texts without stop words & stemmed) and managed to import it.
The problem arises when I want to use the NaiveBayes classifier - the start button is greyed out. ZeroR works.
What am I doing wrong?
I attach the screenshots showing the described scenario and the ARFF.
Thanks in advance!
I've finally had success in get the CSVLoader to process a CSV file that has two string values using the following syntax:
java weka.core.converters.CSVLoader -S 1,2 -E \" inputFile.csv > outputFile.arff
The only problem I'm having is that the output is not redirected to outputFile.arff and instead appears on the console. The only thing I can think of that might be causing this to fail are the initial warnings that get displayed:
---Registering Weka Editors---
Trying to add database driver (JDBC): RmiJdbc.RJDriver - Error, not in CLASSPATH?
Trying to add database driver (JDBC): jdbc.idbDriver - Error, not in CLASSPATH?
Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Error, not in CLASSPATH?
Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Error, not in CLASSPATH?
Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Error, not in CLASSPATH?
I know these are just warnings that I can ignore but perhaps they have something to do with why I'm not getting my inputFile's output redirected properly.
Oh, I've tried this using Weka 3.6.10 and 3.7.10 (64-bit) all on a Windows 7 platform.
I would like to save cluster assignments to an arff file directly from java
code. I found the ClusterEvaluation getClusterAssignments() method but the
metho gives only a double array. What I would like to obtain is something
similar to what the visualize cluster assignments panel saves. I found this
on the weka wiki which is useful.
But I don't want to go through the panel each time i run the program. Any
help would be appreciated.
I'm trying to use logistic regression in numeric prediction. My training.arff file has 5 numeric attributes; the fifth is the attribute to be predicted.
The Weka Explorer dims the 'logistic' regression when I choose 'functions'. Any clues?