Skip to main content

Open access to competing prediction algorithms

Project description

Rediz / Microprediction

Server and client packages enabling open community microprediction at www.microprediction.com.

Overview

The python packages called "microprediction" (user client library) and "rediz" (system implementation using redis as transport) are demonstrated at www.microprediction.com, where they make it easy for anyone who needs a live source of data predicted to receive help from clever humans and self-navigating time series algorithms. They do this by:

They can then access history (e.g. https://www.microprediction.com/live/lagged::cop.json) and predictions (e.g. https://www.microprediction.com/cdf/cop.json). This is an easy way to normalize data and perform anomaly detection. Over time it may garner other insights such as assessment of the predictive value of the data stream the identities of streams that might be causally related.

This setup is especially well suited to collective prediction of civic data streams such as transport, water, electricity, public supply chain indicators or the spread of infectious diseases.

Client README (microprediction package)

https://github.com/microprediction/rediz/blob/master/README_MICROPREDICTION.md

Server README (rediz package)

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rediz-0.3.7.tar.gz (28.2 kB view hashes)

Uploaded Source

Built Distribution

rediz-0.3.7-py3-none-any.whl (35.1 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page