test2.in

高效的k-means算法实现

  stats tree				# statistics output level
  show_assignments yes			# show final cluster assignments
  validate yes				# validate assignments
  dim 2					# dimension

  data_size 20				# number of data points
  seed 1				# random number seed
read_data_pts test1-dat.txt		# read data points

  kcenters 4				# number of centers
  max_tot_stage 50 0 0 0		# number of stages
  min_consec_rdl 0.20			# minimum improvement for Lloyd's
  init_prob_accept 0.50			# init. prob. of accept. for SA
  temp_run_length  10			# number of runs per temp change
  temp_reduc_fact  0.75			# temperature reduction factor

  seed 4				# use different seed
run_kmeans hybrid			# run with this algorithm