Installation

TimeFeatures is an Orange3 add-on, so it requires a working Orange3 installation in the same Python environment.

From PyPI

pip install TimeFeatures

This pulls in every runtime dependency, including the precompiled psycopg2-binary wheel so the Save to DB widget works on macOS, Linux and Windows without a C toolchain.

From source

git clone https://github.com/alervgr/Orange-TimeFeatures.git
cd Orange-TimeFeatures
pip install -e .

The -e flag installs in editable mode so changes to the source tree are picked up on the next Orange restart without reinstalling.

Inside Orange

TimeFeatures also installs through Orange’s GUI:

1. Open Orange.

2. Go to Options → Add-ons….

3. Tick TimeFeatures in the list and confirm.

4. Restart Orange. The new widgets appear under the Time-Features toolbox section.

Anaconda

The same pip install TimeFeatures command works inside a Conda environment as long as Orange3 is installed there.

Dependencies

TimeFeatures needs Python 3.10 or newer and declares the following runtime dependencies (see setup.py):

Package	Minimum version	Used by
Orange3	3.36.2	Host application and data model. Older releases do not work with NumPy 2.
numpy	1.22.4	All widgets.
scipy	1.7.3	Sparse adjacency matrices in the dependency graph.
PyQt5	5.15.6	Widget UI.
PyQtWebEngine	5.15.6	Orange’s in-app help window.
AnyQt	0.2.0	Qt abstraction used by Orange.
SQLAlchemy	1.4.0	Dialect-agnostic SQL toolkit used by Save to DB.
psycopg2-binary	2.9.9	PostgreSQL driver for Save to DB.
PyMySQL	1.0.0	MySQL driver for Save to DB.
Orange3-Network	1.8.0	Network type produced by Variable Dependency Graph.

Orange3 is listed explicitly so a clean pip install gets a version the add-on is tested with. Inside an existing Orange installation that already meets the minimum, pip leaves it untouched.

The CI workflow (.github/workflows/ci.yml) runs the test suite on Python 3.10 with Orange3 3.36.2 and on Python 3.11 and 3.12 with the latest releases, builds the package and installs the wheel into an empty environment, and builds this documentation with warnings as errors.

Running tests

The test suite uses unittest and lives under timefeatures/widgets/tests/. From a checkout:

pip install -e .
python -m unittest discover -v timefeatures/widgets/tests

The widget-level tests inherit from Orange.widgets.tests.base.WidgetTest and therefore require Qt; a virtual display (Xvfb) is enough on a headless CI worker.

The Save to DB upload tests always run on SQLite. To also run them against real servers, point these variables to disposable databases (the tests create and drop tables there):

export TIMEFEATURES_TEST_POSTGRES_URL=postgresql://user:pass@localhost:5432/timefeatures_test
export TIMEFEATURES_TEST_MYSQL_URL=mysql://user:pass@127.0.0.1:3306/timefeatures_test