Introduction to Visual Notebooks
Welcome to Visual Notebooks! Visual Notebooks is a no-code analytics tool designed to bring the power of enterprise AI to everyone. Using an intuitive drag-and-drop interface, you can load data from multiple sources, explore and prep that data, train machine learning (ML) models, visualize predictions, and share your insights with others on your team.
The building blocks of Visual Notebooks
There are six major components of Visual Notebooks: visual notebooks, ML pipelines, stories, datasets, schedules, and connectors. Combine these components to create an end-to-end analytic workflow.
- Visual notebooks: Visual notebooks are blank canvases used to create analytical workflows. Input and wrangle data, perform analyses, create visualizations, and use trained ML models.
- ML pipelines: ML pipelines are specialized visual notebooks used for feature engineering and training machine learning models.
- Stories: Stories are interactive, multi-page dashboards used to display visualizations.
- Datasets: Datasets are persisted snapshots of a dataframe that are versioned and shareable.
- Schedules: Schedules are repeatable, pre-defined visual notebook executions used to automate analyses.
- Connectors: Connectors are shareable credentials used to access data storage systems.
Learn more about the components of Visual Notebooks in the corresponding chapters.