archetypal: archetypal: Finds the archetypal analysis of a data frame by...

In archetypal: Finds the Archetypal Analysis of a Data Frame

archetypal: Finds the archetypal analysis of a data frame by using a variant of the PCHA algorithm

Description

Performs archetypal analysis by using Principal Convex Hull Analysis (PCHA) under a full control of all algorithmic parameters.

Usage

archetypal(df, kappas, initialrows = NULL,
  method = "projected_convexhull", nprojected = 2, npartition = 10,
  nfurthest = 10, maxiter = 2000, conv_crit = 1e-06,
  var_crit = 0.9999, verbose = TRUE, rseed = NULL, aupdate1 = 25,
  aupdate2 = 10, bupdate = 10, muAup = 1.2, muAdown = 0.5,
  muBup = 1.2, muBdown = 0.5, SSE_A_conv = 1e-09,
  SSE_B_conv = 1e-09, save_history = FALSE, nworkers = NULL,
  stop_varexpl = TRUE)

Arguments

df	The data frame with dimensions n x d
kappas	The number of archetypes
initialrows	The initial set of rows from data frame that will be used for starting algorithm
method	The method that will be used for computing initial approximation: projected_convexhull, see find_outmost_projected_convexhull_points convexhull, see find_outmost_convexhull_points partitioned_convexhull, see find_outmost_partitioned_convexhull_points furthestsum, see find_furthestsum_points outmost, see find_outmost_points random, a random set of kappas points will be used
nprojected	The dimension of the projected subspace for find_outmost_projected_convexhull_points
npartition	The number of partitions for find_outmost_partitioned_convexhull_points
nfurthest	The number of times that FurthestSum algorithm will be applied by find_furthestsum_points
maxiter	The maximum number of iterations for main algorithm application
conv_crit	The SSE convergence criterion of termination: iterate until |dSSE|/SSE<conv_crit
var_crit	The Variance Explained (VarExpl) convergence criterion of termination: iterate until VarExpl<var_crit
verbose	If it is set to TRUE, then both initialization and iteration details are printed out
rseed	The random seed that will be used for setting initial A matrix. Useful for reproducible results.
aupdate1	The number of initial applications of Aupdate for improving the initially randomly selected A matrix
aupdate2	The number of Aupdate applications in main iteration
bupdate	The number of Bupdate applications in main iteration
muAup	The factor (>1) by which muA is multiplied when it holds SSE<=SSE_old(1+SSE_A_conv)
muAdown	The factor (<1) by which muA is multiplied when it holds SSE>SSE_old(1+SSE_A_conv)
muBup	The factor (>1) by which muB is multiplied when it holds SSE<=SSE_old(1+SSE_B_conv)
muBdown	The factor (<1) by which muB is multiplied when it holds SSE>SSE_old(1+SSE_B_conv)
SSE_A_conv	The convergence value used in SSE<=SSE_old(1+SSE_A_conv). Warning: there exists a Matlab crash sometimes after setting this to 1E-16 or lower
SSE_B_conv	The convergence value used in SSE<=SSE_old(1+SSE_A_conv). Warning: there exists a Matlab crash sometimes after setting this to 1E-16 or lower
save_history	If set TRUE, then iteration history is being saved for further use
nworkers	The number of logical processors that will be used for parallel computing (usually it is the double of available physical cores). Parallel computation is applied when asked by functions find_furthestsum_points, find_outmost_partitioned_convexhull_points and find_outmost_projected_convexhull_points.
stop_varexpl	If set TRUE, then algorithm stops if varexpl is greater than var_crit

Value

A list with members:

1. BY, the kappas \times d matrix of archetypes found

2. A, the n \times kappas matrix such that Y ~ ABY or Frobenius norm ||Y-ABY|| is minimum

3. B, the kappas \times n matrix such that Y ~ ABY or Frobenius norm ||Y-ABY|| is minimum

4. SSE, the sum of squared error SSE = ||Y-ABY||^2

5. varexpl, the Variance Explained = (SST-SSE)/SST where SST is the total sum of squares for data set matrix

6. initialsolution, the initially used set of rows from data frame in order to start the algorithm

7. freqstable, the frequency table for all found rows, if it is available.

8. iterations, the number of main iterations done by algorithm

9. time, the time in seconds that was spent from entire run

10. converges, if it is TRUE, then convergence was achieved before the end of maximum allowed iterations

11. nAup, the total number of times when it was SSE<=SSE_old(1+SSE_A_conv) in Aupdate processes. Useful for debugging purposes.

12. nAdown, the total number of times when it was SSE>SSE_old(1+SSE_A_conv) in Aupdate processes. Useful for debugging purposes.

13. nBup, the total number of times when it was SSE<=SSE_old(1+SSE_B_conv) in Bupdate processes. Useful for debugging purposes.

14. nBdown, the total number of times when it was SSE>SSE_old(1+SSE_A_conv in Bupdate processes. Useful for debugging purposes.

15. run_results, a list of iteration related details: SSE, varexpl, time, B, BY for all iterations done.

16. Y, the n \times d matrix of initial data used

17. data.tables, the initial data frame if column dimension is at most 3 or a list of frequencies for each variable

18. call, the exact calling used

References

[1] M Morup and LK Hansen, "Archetypal analysis for machine learning and data mining", Neurocomputing (Elsevier, 2012). https://doi.org/10.1016/j.neucom.2011.06.033.

[2] Source: https://mortenmorup.dk/?page_id=2 , last accessed 2024-03-09

Examples

{
	# Create a small 2D data set from 3 corner-points:
	p1 = c(1,2);p2 = c(3,5);p3 = c(7,3)
	dp = rbind(p1,p2,p3);dp
	set.seed(916070)
	pts = t(sapply(1:20, function(i,dp){
	  cc = runif(3)
	  cc = cc/sum(cc)
	  colSums(dp*cc)
	},dp))
	df = data.frame(pts)
	colnames(df) = c("x","y")
	# Run AA:
	aa = archetypal(df = df, kappas  =  3, verbose = FALSE, save_history  =  TRUE)
	# Print class "archetypal":
	print(aa)
	# Summary class "archetypal":
	summary(aa)
	# Plot class "archetypal":
	plot(aa)
	# See history of iterations:
	names(aa$run_results)	

}

archetypal documentation built on May 29, 2024, 8:46 a.m.