P  #㿠 $`@ `@ ` @ `@ `@ @`@@y@@㿠@ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ @ p'D"` 2 !#% )`  "` ""#`$ $`$% " "`"#  #!$ #$`%$'$)% "  ""#  #!$ #$`%'$$) D  " c?@@@@`2@@  @`&$@   `"@`2@@ κ @`&$@   `# @`2!@@  @`@+2 #`@ @ ` `#`b#`@`2!@@  @`@2 #`@ @ z`  `#=#@`2 @# $`%$'$)-% @`2 @ "`""# @`2 @ #!$ #$`% $@`2 @'$)% "  "@`2 @ # #`#@`2 @!$ % $'$@`2 @)% "  "@`2 @ # #`#@`2 @!$ % $'$@`2 @)% "  "@`2@ # @`2@ #@`2@@  @`@ސ2! @   `u$ @`2@@  @`#  `_$`@`2@' U$@`2@ K" @`2@B"`@`2@ 8"@`2@ .#`@`2"@ U @`&$#`@ G `  L`##/ @@ 6  4`@2#@ ' `%')$$@`@`$$`@`% % "` $  #` 㿠@ @ @ @@ 8 "` ` "`  "`  `;`@` "`  "`  `;`@` "  @` ` "  @`  @` `#  "`"` "" #`#` " " "`" $7 ``  &@%@ (` %%@@&'@'`'`'` `` *'@@:'@`@*'@ `` ڶ("`"`  %&@ $#   * ` '` '`'`'@`` ' ' ' '  @:  ''@`@    `(Դ(` '`?`    ?$` $&Ԟ " `"@ `@ @Ȯ%% @%%@#@#`r Ӳ`$C`` ^` + `$ '`'' '@' ' '` '`' ' '`'`' '  '`'`` `*@:``''  '@'``@*` $N` ?????  (  @@@@@`&&&& &@&`'@ '`#hh…"'@'` &&` ` &ؤئتfϬ "f$c``?`! - ` ?``9?' '&&&&'`'@' ' & && &'` '`' ' &&&&'`'`' ' &&&&   '`'`` `@*@:''  &&&&'@'``@*` "4 $. ``&@ @ (` && '@'`'`'` `` *'@@:'@`@*'@`   (߲`#" 㿘@ " 7 ,32 *`@ @ `*`@ 2) @ `(*, #  㿐'DD'HH @#]`D#U H#M`L##!C `P#'%=T#+)5 `X#/--\#31% `B#75F#;9 `J#;h  hl ;`@`/.?> & 4  @R??zG{@#A.~??zG{?@K?@N?QR@P?(\)@Q?@R?噙@T?"`@U@?O;d@V?\(@W?QR@X@?tj@X@Usage: description namesfile trainfile testfile outputfile seed [options] Required Parameters: descriptionfile contains the predictee/predictor info namesfile contains the datafile's format information trainfile contains training instances testfile contains testing instances outputfile will contain the experiment's results seed is used to initialize random variable generator User Parameters: (name, default, and brief description) -signif_accept (75 confidence) above class frequency -signif_drop (75 confidence) below class frequency -ib1 (off) Act like IB1 rather than IB3 -ib2 (on) Act like IB2 rather than IB3 -ib3 (off) Act like IB3 -ib4 (off) Act like IB4 rather than IB3 -k (1) Number of nearest acceptables wanted -norm_none (off) No normalization option -norm_linear (on) Linear normalization option -norm_sd (off) Standard deviation normalize option -missing_maxdiff (on) Assume maximum possible difference -missing_ave (off) Assume average or most frequent value -missing_ignore (off) Ignore, Normalize the sim'y results -storeall (off) IBn>1: Save (initially) all instances -multiline (off) Allows alternative input format - Instances can then appear on multiple lines - Final line per instance must contain only one symbol: < Convenience Options: -testrate (100) How often to run on test set -reportrate (25) How often to report on things -startup (0) When to start testing/reporting -overlap (off) IB4: set of binary concepts -best_concept_only (off) IB4: if overlap, give only best -probability_weights (off) IB4: Toggles between 2 methods -printweights (off) IB4: always print attribute weights -testlast (off) Test after finished? -testrateTest rate option need integer argument. Test rate argument x: 1 <= x <= 20000. -reportrateReport rate option need integer argument. Report rate argument x: 1 <= x <= 10000. -signif_acceptFrequency significance option needs integer arg. Frequency Significance argument: -signif_dropInstance record significance option needs int arg. Instance record significance argument: -ib1-ib2-ib3-ib4-norm_none-norm_linear-norm_sd-missing_maxdiff-missing_ave-missing_ignore-storeall-multiline-kk option needs an odd integer argument. k argument: integer less than %d. -startupStartup option needs int arg. -overlap-best_concept_only-probability_weights-printweights-testlast-learning_rateLearning rate option needs integer arg. Learning rate option must be in range [1,25]. Unknown argument to ibl: %s Bad data format. Initializing variables... Training and testing... Finished Experiment. %d-IB1%d-IB2%d-IB3%d-IB4NoneLinearStandard DeviationMaximum DifferenceAverage or Most Frequent ValueIgnore and Normalize Similarity Results{55,60,67,70,75,80,85,90,95,97,99} FAILURE IN SIGNIFICANCE LEVEL (with value %f)!!! t$J(t,J4E8t<ED*HtL*TuXt\u`qhXiP XiD i8 i, -i  -Wi Wi i  i 'i  '$a(i, a04i8 <@iD HLiP T/Xi\ /`fdih flpit x|i  ix  Iil Ii` iT iH Ci< C}i0 }i$ i i  ?i ?z i zi  $i( , .0i4 .8 k<i@ kD HiL `Pd PhAlAp{x;cdefA PI{{;cdefI##  }}77 DDTTU U$),)048B<BDzHzL=P=T<X<\X` XdXhXpXt`x `t` sP  i0 q !;!i  !(;,!;0s4 !;L!GPiT !G`qt!r!rix !r!sP !!i0 !q !i !$A4A<A@!DsH !`" dih " tq"@ih "@{{{"hs( "hccddeeff"ms "m,d4d8c<c@eDeHfPfT"rXs\ "rletexc|cddff"wsh "weeccddff"|s( "|II "s "$I(I,48@D"HsL "\I`Idhlx|"s "##  }}"sH "##  }}"s "##  } }$"(s, "<7H7L"PsT "dDpDt"xs| ""ih "qX)#  # i0)#/s #/ #8 i  #8 (q 0 H L#W Ps T #W d p t#` xs | #` B B #s s`  #s z z # s<  # = = # s  # < < # s  # $$ 0# 4i 8 # Dq X# h# li p # X X X iP  $ K, h $$ i  $$  h r l ( r r h A A (A ,{ 0l 4l 8{ @{ H( P( T X \ ` d h; l; |; ;   $6 i`  $6 $Q iL  $Q D $j i8  $j c c d $   $  d e $   $ $ (e 4$ 8$ < @ $ H L P T $ X) \) d pI tI  $ P  $ P  $ $ P  $ P P P  $ t4 # # $ ~ ~ t  $ U U z z  $ $ $~ (~ ,t 0 $ 4U 8U <z Dz H~ L~ Pt T $ XU \U `z dz h l pp t p x |x ] 3    x ' ] ]  x T 3 3  x    '  T G [  1 W O & & OW1 [lTTTGG_LL_TTTTx x x x++TT@@| |$T(T4vVVT    99VV88     ( , @ D l xT|    TT 2oo2   HH   TT  x x $ x(!,!0"4"LPX x\`D   UVVUx x%bb%0VHVLVhUlUpztz%ix % dlddddd l(l0d8l@lHdPdXd`d           $, 0 @DL P `dl p     0( ( 0@8 8 @H H%9 %9i P Pd!*4=!I}d p?LU^gm@PDp(((+(CDpUxi}"`(!d.83C,Uf |P(Dp&0:H3[(t@|PdDp'2d=Ow ((lp-(CRl'(XP1(Kafkpu Dpp "*2d>C3V n(_sum_values_descriptionfile_norm_sd_data_set_overlap_value_name_probability_of_membership_num_training_correct_in_alg_previous_num_dropped_in_alg_num_correct_in_alg_num_queries_in_alg_missing_ave_my_infinity_instance_number_train_and_test_num_training_incorrect_in_alg_num_predictor_training_values_norm_linear_sprintf_srandom_startup_main_raw_test_instances_num_training_correct_in_concept_previous_print_usage_conditional_probability_number_of_known_values_algorithm_string_num_dropped_in_concept_num_correct_in_concept_num_queries_in_concept_attribute_weight_significance_level_standard_deviation_sum_squared_values_missing_maxdiff_percent_correct_in_alg_num_training_instances_with_value_num_training_incorrect_in_concept_num_data_in_alg_signif_drop_k_testingfile_num_uses_distances_good_value_for_k_rejected_dataid_class_drop_threshold_percent_correct_in_concept_num_data_in_concept_weight_size_initcorrectcount_percent_data_in_alg_num_accepted_num_rejected_storeall_scalemin_scalemax_instances_testrate_testlast_printweights_accepted_distance_num_accepted_in_concept_counts_signif_accept_level_best_concept_only_percent_data_in_concept_multiline_trainingfile_num_attributes_to_translate_num_training_correct_in_alg_attribute_weight_used_norm_none_namesfile_read_data_format_num_training_incorrect_in_alg_previous_experiment_predictee_num_train_with_value_normalization_string_num_incorrect_in_alg_predictor_attribute_type_number_of_predictees_number_of_predictors_number_of_attributes_num_train_in_concept_learning_rate_known_significance_level_predictee_value_name_num_training_correct_in_concept_able_to_interpret_options_initusages_print_known_significance_levels_num_training_incorrect_in_concept_previous_number_of_test_instances_num_incorrect_in_concept_sum_predictor_values_ib1_ib2_ib3_ib4_raw_instances_read_test_set_printf_num_to_be_dropped_accepted_id_signif_accept_initialization_to_be_dropped_attribute_weight_total_num_values_atoi_unknown_value_strcmp_strcpy_outputfile.mul_rejected_distance_class_accept_threshold_accepted_dataid_weight_method_signif_drop_level_usages_missing_ignore_missing_string_initincorrectcount_reportrate