-
Notifications
You must be signed in to change notification settings - Fork 0
Home
This wiki contains documentation for ViEWS 3. ViEWS 3 is an ecosystem of packages that provide facilities for data retrieval, time-series modelling, data transforms and model and model run management.
To open this wiki in a browser window from the terminal, run:
viewser help wiki
- Getting data: How to retrieve data from views3
- Defining data: How to define new querysets
- Model object storage: How to store and retrieve trained models
ViEWS 3 relies on several conventions for data and naming, to make exchange and interoperation between packages easier:
Documentation is provided for each of the constituent ViEWS 3 packages.
Notebooks are also available, which show complete workflows using the various
packages in concert. Note that package names are written with a dash (-) on
PyPi, and with an underscore (_) on github, due to differing naming
conventions.
-
viewser is the entrypoint for interacting with the ViEWS 3 cloud, which provides data for the ViEWS team.
-
views-runs provides helper classes for model run management
-
stepshift implements the step-shifting algorithm used for predictive modelling.
-
views-partitioning is used to partition data for training.
-
views-transformation-library contains data transformation functions available in ViEWS 3
-
views-dataviz has functions for making maps and plots
-
views-stepshift is a legacy package containing the reference implementation of the stepshifting algorithm
A pre-packaged docker image is also provided. This environment works as a common baseline environment for running notebooks, and contains a Jupyter environment with all relevant packages pre-installed.
To run a notebook server with this image, run the command:
viewser notebooks run
This downloads and launches the image.