Investigating New Projection Pursuit Index Functions
Plot the comparison of smoothing methods.
Plot traces of indexes obtained with get_trace.
Simulate and Summarize Projection Pursuit Index (PPI) Values
Estimate the 95th Percentile of a Projection Pursuit Index Under Noise
Simulate Effect of Sample Size on Projection Pursuit Index Under Gauss...
Simulate and Compare Index Scale on Structured vs Noisy Data
Test rotation invariance of index functions for selected 2-d data set.
Matching index functions to the required format.
Generating sine wave sample
spinebil
Generating spiral sample
Generate 2-d basis in directions i, j in n dimensions (i,j <= n)
Generate nearby bases, e.g. for simulated annealing.
Generate basis vector in direction i in n dimensions (i <= n)
Compare traces with different smoothing options.
Generate Synthetic Data with Various Structures
Collecting all pairwise distances between input planes.
Collecting distances between input planes and input special plane.
Calculate information required to interpolate along a geodesic path be...
Evaluate mean index value over n jittered views.
Tracing the index over an interpolated planned tour path.
Re-evaluate index after jittering the projection by an angle alpha.
Re-evaluate index after jittering all points by an amount alpha.
Generate Synthetic Noise
Generating a sample of points on a pipe
Plot rotation traces of indexes obtained with profileRotation.
Estimating squint angle of 2-d structure in high-d dataset under selec...
Step along an interpolated path by fraction of path length.
Time each index evaluation for projections in the tour path.
Projection pursuit is used to find interesting low-dimensional projections of high-dimensional data by optimizing an index over all possible projections. The 'spinebil' package contains methods to evaluate the performance of projection pursuit index functions using tour methods. A paper describing the methods can be found at <doi:10.1007/s00180-020-00954-8>.