Learn ORANGE with Real Code Examples

Download Orange from the official website or via Python pip

Install required Python environment (Python 3.8+ recommended)

Install additional add-ons as needed

Launch Orange Canvas (GUI) or run scripts via Python

Verify installation by loading a sample dataset and building a simple workflow

Install Python 3.8+

Install Orange via pip or standalone installer

Install optional add-ons for extra functionality

Verify installation by running Canvas and loading sample datasets

Test Python integration with Orange modules

Workflows/ - .ows files

Datasets/ - CSV, Excel, or ARFF files

Scripts/ - Python automation scripts

Add-ons/ - installed optional modules

Exports/ - visualizations and prediction outputs

python -m Orange.canvas

python -c 'import Orange; Orange.data.Table("iris.csv")'

Use scripts to run workflows programmatically

Install add-ons via GUI or pip

Export workflow results via GUI or Python

Supports Unicode datasets

Works on multiple operating systems worldwide

Documentation primarily in English

Adopted in academic and research institutions globally

Compliant with international data standards

Cross-platform support (Windows, macOS, Linux)

GUI-based for beginners, Python scripting for advanced users

Free and open-source under GPL

Educational-friendly and lightweight

Integrates with Python ML ecosystem

Canvas workspace for drag-and-drop widgets

Color-coded widgets for task differentiation

Interactive visualizations and plots

Real-time feedback from data changes

Export charts and tables for reporting

Save workflows for reuse

Document widget connections

Backup datasets and scripts

Track model evaluation metrics

Maintain reproducible environments with virtualenv

Use CSV, Excel, or ARFF files

Preprocess datasets using normalization, imputation, and filtering

Split datasets for training/testing

Track feature selection steps

Ensure reproducibility using saved workflows and scripts