Ounias documentation
Guides and reference material for preparing data, creating analyses, and working with analytical outputs in Ounias.
Getting started
Prepare, import, and configure tabular data for analysis in Ounias.
Prepare your data
Structure your dataset for unsupervised, supervised, longitudinal, or external-result analysis before uploading it to Ounias.
Import and configure a dataset
Upload a prepared dataset, review its contents, assign analytical roles, validate the configuration, and make it available for analysis.
Concepts & guides
Explanations for Ounias-specific concepts, analytical choices, and workflows that may not be obvious from the interface alone.
Feature space vs embedded space
Understand the difference between clustering directly on dataset features and clustering on a generated lower-dimensional representation.
Feature roles
Understand how Ounias interprets dataset columns and why their assigned roles affect downstream analyses.
Exporting from Ounias
Export derived datasets, plots, trained models, and structured analytical outputs for use outside Ounias.
Runs, lineage and variations
Understand how Ounias represents analyses and preserves the relationships between original and derived runs.
Evaluation and metric pillars
Understand how Ounias organizes heterogeneous analytical metrics into comparable higher-level dimensions.
Longitudinal datasets
Configure repeated observations so Ounias can evaluate state changes, transitions, timing, and trajectories.
Dataset updates and versions
Understand what happens when an imported dataset changes and how Ounias preserves analyses associated with earlier dataset states.
Snapshots
Preserve a selected analytical state as an immutable, view-only reference that can be shared independently of the live workspace.