Scale Partitioning by Incremental Nested Entropy. You supply a measure and an orientation; everything after them is computed.
pip install entropy-spine — then read the user guide first — worked scenarios, runnable cell by cell. The pages below are the reference.
spine | spine: apply SPINE to raw data in one call. |
spine_summary | say in words what a partition found. |
spine_compare | run the same data under several measures and see |
spine_measure | turn data into a nonnegative measure. |
spine_data_plot | Draw the data in the space it lives in, coloured by score. |
spine_plot | Show where a partition came from: the measure, and the profile. |
spine_network_plot | Draw a network with its nodes coloured by score. |
spine_score_map | Sequential colormap for SPINE scores, as an (n, 3) RGB array. |
spine_version | report which copy of entropy-spine is running, and |
Choosing a measure is the piece to read before applying SPINE to your own problem.
Generated by python/doc/build_docs.py. Every example on these pages was executed during the build.