Orange for Beginners
If you are new to Orange, than this is probably the best place to start. “Beginning with Orange” was written with a purpose to provide a gentle tutorial over basic functionality of Orange. The tutorial includes:
- Start with Orange shows hot to run python and import Orange,
- Load-in the data speaks about data formats and how to load the read the data from files,
- Basic data exploration demonstrates how to perform some basic statistical analysis,
- Classification describes how to set-up the learners, build classifiers, and evaluate them using cross-validation or alike,
- My first Orange classifier builds naive Bayesian classifier and shows how to use to predict class labels and probabilities,
- Selected classification methods lists other classification methods provided by Orange,
- Testing and evaluating speaks about of testing and comparison of learners,
- Build your own learner is a chapter on how to prototype your own learners/classifiers in Python.
- Regression introduces several methods that can be used for regression modelling,
- Association rules shows how to use Orange's association rules,
- Other topics
- Categorization lists several methods within Orange that can be used for categorization,
- Feature subset selection
- Ensemble techniques discusses how to use a particular Orange's module for boosting and bagging,
- Basic Data Manipulation illustrates how to select attributes, instances, craft new domains and data sets, and alike. Finishes with wrapper-based feature subset selector,
- What we did not cover
As Orange is integrated within Python, the tutorial is in essence a guide through some basic Orange scripting in this language. Although relying on Python, those of you who have some knowledge on programming won’t need to learn Python first: the tutorial should be simple enough to skip learning Python itself. If, however, you will later want to develop your own methods and test some of your more complex ideas, you may want to jump to Python’s site for some material on this rather new and appealing scripting language.
Through the tutorial, some basic python scripts are developed that most often read the data and do something with it. You will find that every piece of code we present has a pointer to the file with this code that you can download (use the mouse, press right-button on the link, and choose “Save Target As …”. You will also find that with it are pointers to the data files that you can download too. We recommend you to first open a special folder where you want to save both the scripts and files that come with them.
We expect this tutorial to be interactive, that is, we would like you to try Orange while reading the tutorial. Hence, we start with the basics on where to download Python and Orange and how to start Orange scripting.
For your convenience, you may also download a stand-alone version of Orange documentation that also includes all script files and data files.
Note: The documentation posted on the web is updated from the CVS in real-time and refers to the latest snapshot of Orange. If you encounter any inconsistencies please compare the standalone documentation with the one on the web.