Features
Data Ingestion
SweatStack offers several integrations to ingest data from your favourite wearables and training platforms and more integrations are added regularly. Data can also be uploaded manually, or with code using our Python client library.
The data models are optimized for medium frequency timeseries data (<=1Hz) but we are working on support for higher frequency timeseries data and other types of data. Reach out to us if you have specific data requests.
SweatStack is designed to be data source agnostic (allowing you to analyze data from any source using the same tools) and offers data fusion, merging data from multiple sources into a single data model and allowing you to, for example, combine data from multiple sensors that cannot be recorded on the same device.
Traces
SweatStack allows the user to store manually recorded data (e.g. lactate measurements or RPE values) as "traces". Using data fusion, traces are automatically combined with data from other sources, giving you 1 convenient interface to all your data.
Longitudinal Analysis
Sweat Stack not only gives you access to data on a per activity basis, but also allows you to access data across multiple activities and across many months (and even years). You can easily query months of data and start analyzing the results within seconds. More info on how to do this can be found in the Python client library documentation.
Data Sharing
Data can be shared with other users, groups or applications with fine-grained access control. And if someone gave you access to their data, all that data is available in the SweatStack app and via the API.
Python Client Library
For ease of use, an intuitive Python client library is available.
App Marketplace
Developers can create apps that use SweatStack data and services. Individual apps can be published to the SweatStack app marketplace, where they can be discovered and used by other users.
More Features
Info
More features will be announced soon...