Skip to main content

Clusterpolate: Inter- and extrapolation for clustered data.

Project description

Traditional approaches for inter- and extrapolation of scattered data work on a filled rectangular area surrounding the data points or in their filled convex hull. However, scattered data often consists of different clusters of irregular shapes and usually contains areas where there simply is no data. Forcing such data into a traditional inter- or extrapolation scheme often does not lead to the desired results.

Heatmaps, on the other hand, deal well with scattered data but often do not provide real interpolation: Instead they usually use raw sums of kernel functions which overestimate the target value in densely populated areas.

Clusterpolation is a hybrid inter- and extrapolation scheme to fix this. It uses kernel functions for a weighted inter- and extrapolation of local values, as well as for a density estimation of the data. The latter is used to assign a membership degree to clusterpolated points: Points with a low membership degree lie in an area where there’s just not enough data.

Project details

Download files

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

Filename, size & hash SHA256 hash help File type Python version Upload date
clusterpolate-0.2.0.tar.gz (21.3 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page