NAME

set_em_cluster_options - set_em_cluster_options

SYNOPSIS

#include "r/r_cluster.h"

Example compile flags (system dependent):
  -DLINUX_X86_64 -DLINUX_X86_64_OPTERON  -DGNU_COMPILER 
   -I/home/kobus/include
   -L/home/kobus/misc/load/linux_x86_64_opteron -L/usr/lib/x86_64-linux-gnu
  -lKJB                               -lfftw3  -lgsl -lgslcblas -ljpeg  -lSVM -lstdc++                    -lpthread -lSLATEC -lg2c    -lacml -lacml_mv -lblas -lg2c      -lncursesw 


int set_em_cluster_options
(
	const char *option,
	const char *value
);

DESCRIPTION

     Cluster data perturbation.
 cluster-discrete-threshold
     Cluster threshold for excluding discrete probabilities.
 cluster-num-tries-per-cluster-count
     When trying different cluster counts, this option specifies the number number of EM tries each number of clusters gets (must be at least one) (default 1)
 cluster-num-cluster-count-samples
     Number of log-spaced EM clusters counts to try (must be at least one) (default 30).
 cluster-max-num-iterations
     The maximum number of EM iterations to use (default 20).
 cluster-iteration-tolerance
     EM iteration tolerance (default 1e-6).
 cluster-plot-log-likelihood
     Plot EM log likelihood vs num clusters. (Boolean, default false)
 cluster-norm-data
     Normalize Cluster data. (boolean, default false)
 cluster-var-offset
     Cluster variance offset (default 1e-4)
 cluster-use-unbiased-var-estimate-in-M-step
     Unbiased estimate for variance %s used in the M step. (Boolean, default false)
 cluster-held-out-data-fraction
     Held out data fraction.3e. (default 1/10)
 cluster-tie-var
     Use cluster tie variance (Boolean, default false)
 cluster-tie-feature-var
     Use cluster tie feature variance (Boolean, default false)
 cluster-tie-cluster-var
     Use cluster tie cluster variance. (Boolean, default false)
 cluster-model-selection-training-MDL
     Use training data MDL criterion for model selection. (Boolean, default false)
 cluster-model-selection-held-out-LL
     Use held out data log likelihood criterion for model selection. (Boolean, default True)
 cluster-model-selection-held-out-MDL
     Use held out data MDL criterion for model selection. (Boolean, default false)
 cluster-model-selection-held-out-corr-diff
     Use held out data correlation difference criterion for model selection. (Boolean, default true)
 cluster-model-selection-held-out-max-membership
     Use held out data maximum membership criterion for model selection. (Boolean, default true).
 cluster-EM-stop-criterion-training-LL
     Use training data log likelihood as EM stopping criterion. (Boolean, default true).
 cluster-EM-stop-criterion-held-out-LL
     Use held out data log likelihood as EM stopping criterion. (Boolean, default false).
 cluster-use-initialized-cluster-means-variances-and-priors
     Use initialized cluster means and variances in the EM algorithm. (Boolean, default false).
 cluster-max-num-CEM-iterations
     The maximum of N CEM iterations are used. (default 100)
 cluster-write-CEM-intermediate-results
     Whether to write CEM intermediate results. (default true)
 cluster-force-equal-prob-for-CEM-split-and-merge
     Whether the probabilities of choosing a CEM split or a merge operation are forced to be equal. (default true)
 cluster-crop-feature-dimensions
     Crop some feature dimensions before clustering  (default false)
 cluster-crop-num-feature-dimensions-left
     Number of feature dimensions to the left to crop. (default 0)
 cluster-crop-num-feature-dimensions-right
     Number of feature dimensions to the right to crop. (default 0)

SEE ALSO get_independent_GMM , get_independent_GMM_using_CEM , get_independent_GMM_with_shift , get_independent_GMM_with_shift_2 , get_GMM_blk_compound_sym_cov , get_GMM_blk_compound_sym_cov_1