The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
This is a new submission to CRAN.
The {inphr} package is intended to be a package for making inference on samples of persistence homology data. It is part of the TDAverse suite of packages, which are designed to provide a collection of packages for enabling machine learning and data science tasks using persistent homology.
The package currently exposes two main functions which test if two samples of PH data have been generated from the same distribution:
two_sample_diagram_test()
works in the space of diagrams, using test statistics based on
inter-point distances only.two_sample_functional_test()
works in a functional space (one of Betti, Euler characteristic,
normalized life, silhouette or entropy) and uses interval-wise testing
(providing strong control of familywise error rate) to output on which
portions of the scale sequence does the difference occur.Messages, warnings and errors are relayed to the user using the {rlang} package and the {cli} package which are both licensed under the MIT license and with no dependency trail.
Inference in the space of diagrams is performed thanks to the combination of {phutil} which computes distances between diagrams in an efficient manner and {flipr} which powers the permutation schemes and test statistics based on inter-point distances.
Inference in functional spaces is performed thanks to the combination of {TDAvec} which provides the suitable PH vectorization and {fdatest} which powers the interval-wise testing procedure for functional data.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.