Explore and run machine learning code with Kaggle Notebooks Using data from German Credit Risk - With Target. Attribute-Relation File Format (ARFF) November 1st, 2008. This documentation is superceded by the Wiki article on the ARFF format. April 1st, 2002. An ARFF (Attribute-Relation File Format) file is an ASCII text file that describes a list of instances sharing a set of attributes.
The resources for this dataset can be found at https://www.openml.org/d/31
Author: Dr. Hans Hofmann
Source: UCI - 1994
Please cite: UCI
German Credit data
This dataset classifies people described by a set of attributes as good or bad credit risks.
This dataset comes with a cost matrix:
It is worse to class a customer as good when they are bad (5), than it is to class a customer as bad when they are good (1).
Attribute description
- Status of existing checking account, in Deutsche Mark.
- Duration in months
- Credit history (credits taken, paid back duly, delays, critical accounts)
- Purpose of the credit (car, television,…)
- Credit amount
- Status of savings account/bonds, in Deutsche Mark.
- Present employment, in number of years.
- Installment rate in percentage of disposable income
- Personal status (married, single,…) and sex
- Other debtors / guarantors
- Present residence since X years
- Property (e.g. real estate)
- Age in years
- Other installment plans (banks, stores)
- Housing (rent, own,…)
- Number of existing credits at this bank
- Job
- Number of people being liable to provide maintenance for
- Telephone (yes,no)
- Foreign worker (yes,no)
German Credit Data Set Arff Download Pdf
Skip to end of metadataGo to start of metadataGroovy is an agile and dynamic language for the Java virtual machine. It compiles directly to Java bytecode and integrates with all existing Java objects and libraries. The Groovy scripting plugin for WEKA's KnowledgeFlow allows you to write, test and debug KnowledgeFlow steps in Groovy. This is much faster than writing a standard plugin for the KnowledgeFlow because the dynamic nature of Groovy eliminates the need to restart the KnowledgeFlow after changes to the code. Furthermore, the Groovy scripting plugin provides a fully compilable class template that implements all the important KnowledgeFlow interfaces - you just fill in the methods that you need. This makes for an easy way to get started with learning to program for the KnowledgeFlow.
Download the Groovy scripting plugin for the KnowledgeFlow here (includes the examples below). From Weka 3.7.2 the Groovy scripting plugin is available as a package called 'kfGroovy', which can be downloaded and installed by the package manager. You can also browse the package's details online at: http://weka.sourceforge.net/packageMetaData/kfGroovy/index.html
Requirements
WEKA 3.7.0 or higher.
The screenshot below shows the KnowledgeFlow with a Groovy script that loads all the ARFF files in a directory and passes them on, one-by-one, to the naive Bayes classifier for evaluation (via cross-validation) and for saving out the model learned from each to a file. It also shows the built-in editor for creating Groovy scripts.
The DirectoryLoader.groovy script can be seen here. It shows how to implement the 'Startable' interface, how to generate 'DataSet' events and how to use environment variables.
The screenshot below shows another example. This time a Groovy script has been written to generate a learning curve for an incoming data set (the german credit data in this example).
German Credit Data Set Arff Downloads
The LearningCurve.groovy script can be seen here. It demonstrates how a script can provide a graphical dialog for setting options and further use of environment variables. Environment variables can be quite useful in KnowledgeFlow Groovy scripts as parameters edited by the user at runtime for an object of the script class can't be saved when the KnowledgeFlow layout is saved to disk (this is because the source code of the script is saved, not the object instantiated from the script).