//*******************************************************************
// WinMain - Neural main
//
// parameters:
// hInstance - The instance of this instance of this
// application.
// hPrevInstance - The instance of the previous instance
// of this application. This will be 0
// if this is the first instance.
// lpszCmdLine - A long pointer to the command line that
// started this application.
// cmdShow - Indicates how the window is to be shown
// initially. ie. SW_SHOWNORMAL, SW_HIDE,
// SW_MIMIMIZE.
//
// returns:
// wParam from last message.
//
//*******************************************************************
int PASCAL WinMain(HINSTANCE hInstance, HINSTANCE hPrevInstance,
LPSTR lpszCmdLine, int cmdShow)
{
/*
Declarations of local variables
*/
int control_file_number = -1 ; // Stack pointer for control files
FILE *control_files[MAX_CONTROL_FILES] ; // This is the stack
char *control_line ; // User's commands here
char *command, *rest ; // Pointers to its command and parameter parts
int n_command, n_rest ; // Lengths of those parts
int net_model = -1 ; // Network model (see NETMOD_? in CONST.H)
int out_model = -1 ; // Output model (see OUTMOD_? in CONST.H)
int n_inputs = -1 ; // Number of input neurons
int n_outputs = -1 ; // Number of output neurons
int n_hidden1 = -1 ; // Number of hidden layer one neurons
int n_hidden2 = -1 ; // Ditto layer 2 (0 if just one hidden layer)
TrainingSet *tset = NULL ; // Training set here
Network *network = NULL ; // Network here
struct LearnParams learn_params ; // General learning parameters
struct AnnealParams anneal_params ; // Simulated annealing parameters
struct GenInitParams geninit_params ; // Genetic initialization parameters
struct KohParams koh_params ; // Kohonen parameters
int classif_output = -1 ; // Current class (0=reject) for classif training
char out_file[80] = "" ; // File for EXECUTE output
float threshold ; // CLASSIFY confusion reject cutoff
char resp_file[80]=""; // file for initializing output neuron's name
char train_file[80]="";
/*
Miscellaneous variables
*/
int i, n, m ;
float p ;
char *msg ;
FILE *fp ;
unsigned long me,mc;
char *fname;
char *control;
#if VERSION_16_BIT
if (sizeof(int) > 2) {
printf ( "\nRecompile with VERSION_16_BIT set to 0 in CONST.H" ) ;
exit ( 1 ) ;
}
#else
if (sizeof(int) < 4) {
printf ( "\nRecompile with VERSION_16_BIT set to 1 in CONST.H" ) ;
exit ( 1 ) ;
}
#endif
printf ( "\nNEURAL SYSTEM - Program to train and test neural networks" ) ;
if (argc>1)
{
strcpy(fname,argv[1]);
}
/*
Process command line parameters
*/
mem_name[0] = 0 ; // Default is no memory allocation file
/*
if (strlen ( mem_name )) {
strcat ( mem_name , ":mem.log" ) ;
fp = fopen ( mem_name , "wt" ) ;
if (fp == NULL) {
printf ( "\nCannot open debugging file %s", mem_name ) ;
exit ( 1 ) ;
}
fclose ( fp ) ;
mem_log = 1 ;
}
else
mem_log = 0 ;
*/
mem_log = 0 ;
mem_used = 0 ;
/*
Initialize defaults
*/
learn_params.init = -1 ;
learn_params.quit_err = 0.0 ;
learn_params.retries = 32767 ;
anneal_params.temps0 = 3 ;
anneal_params.temps = 4 ;
anneal_params.iters0 = 50 ;
anneal_params.iters = 20 ;
anneal_params.setback0 = 50 ;
anneal_params.setback = 20 ;
anneal_params.start0 = 3.0 ;
anneal_params.start = 4.0 ;
anneal_params.stop0 = 1.0 ;
anneal_params.stop = 0.02 ;
geninit_params.pool = 50 ;
geninit_params.gens = 3 ;
geninit_params.climb = 0 ;
geninit_params.overinit = 1.5 ;
geninit_params.pcross = 0.8 ;
geninit_params.pmutate = 0.0001 ;
koh_params.normalization = 0 ; // 0=multiplicative, 1=Z
koh_params.learn_method = 1 ; // 0=additive, 1=subtractive
koh_params.rate = 0.4 ; // learning rate
koh_params.reduction = 0.99 ; // learning rate reduction
learn_params.ap = &anneal_params ;
learn_params.gp = &geninit_params ;
learn_params.kp = &koh_params ;
act_func_init () ; // Initialize interpolation table for activation function
MEMTEXT ( "NEURAL: control_line, msg" ) ;
if (((control_line = (char *) MALLOC ( CONTROL_LINE_LENGTH+1 )) == NULL)
|| ((msg = (char *) MALLOC ( CONTROL_LINE_LENGTH+1 )) == NULL)) {
printf ( "\nInsufficient memory" ) ;
exit ( 1 ) ;
}
/*
Main loop processes all commands
*/
for (;;) {
if (argv[1])
{
strcpy(control_line,"CONTROL:");
strcat(control_line,fname);
//printf("%s\n",control_line);
argv[1]=NULL;
}
else
get_control_line ( control_line , &control_file_number, control_files ) ;
split_control_line ( control_line , &command , &n_command ,
&rest , &n_rest ) ;
if (! n_command) {
if (n_rest) {
sprintf ( msg , "No colon after command: %s", rest ) ;
error_message ( msg ) ;
}
continue ;
}
sprintf ( msg , "%s : %s", command, rest ) ;
normal_message ( msg ) ;
/*
Act on the command
*/
if (! strcmp ( command , "QUIT" ))
break ;
if (! strcmp ( command , "CONTROL" )) {
stack_control_file (rest, &control_file_number, control_files) ;
continue ;
}
if (! strcmp ( command , "NETWORK MODEL" )) {
// Multi layer network
if (! strcmp ( rest , "LAYER" ))
n = NETMOD_LAYER ;
// Kohonen network
else if (! strcmp ( rest , "KOHONEN" ))
n = NETMOD_KOH ;
// Hopfield network
else if (! strcmp ( rest , "HOPFIELD" ))
n = NETMOD_HOP ;
// Bidirectionnal associative memory network
else if (! strcmp ( rest , "BAM" ))
n = NETMOD_BAM ;
else {
sprintf ( msg , "Illegal NETWORK MODEL: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (net_model == n)
continue ;
if (ok_to_clear_weights( &network )) {
net_model = n ;
learn_params.init = -1 ;
}
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "OUTPUT MODEL" )) {
if (! strcmp ( rest , "CLASSIFY" ))
n = OUTMOD_CLASSIFY ;
else if (! strcmp ( rest , "AUTO" ))
n = OUTMOD_AUTO ;
else if (! strcmp ( rest , "GENERAL" ))
n = OUTMOD_GENERAL ;
else {
sprintf ( msg , "Illegal OUTPUT MODEL: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (out_model == n)
continue ;
if ((ok_to_clear_tset( &tset )) && (ok_to_clear_weights( &network)))
out_model = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N INPUTS" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n <= 0) || (n > MAX_INPUTS)) {
sprintf ( msg , "Illegal N INPUTS: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_inputs == n)
continue ;
if ((ok_to_clear_tset( &tset)) && (ok_to_clear_weights(&network)))
n_inputs = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N OUTPUTS" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n <= 0) || (n > MAX_OUTPUTS)) {
sprintf ( msg , "Illegal N OUTPUTS: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_outputs == n)
continue ;
if ((ok_to_clear_tset( &tset)) && (ok_to_clear_weights(&network)))
n_outputs = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N HIDDEN1" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0) || (n > MAX_HIDDEN)) {
sprintf ( msg , "Illegal N HIDDEN1: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_hidden1 == n)
continue ;
if (ok_to_clear_weights( &network ))
n_hidden1 = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N HIDDEN2" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0) || (n > MAX_HIDDEN)) {
sprintf ( msg , "Illegal N HIDDEN2: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n && ! n_hidden1) {
error_message ( "N HIDDEN2 must be 0 if N HIDDEN1 IS 0." ) ;
continue ;
}
if (n_hidden2 == n)
continue ;
if (ok_to_clear_weights( &network ))
n_hidden2 = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "TRAIN" )) {
if ((out_model == OUTMOD_AUTO) && (n_outputs != n_inputs)) {
warning_message ( "Setting N OUTPUTS = N INPUTS" ) ;
n_outputs = n_inputs ;
}
if (out_model <= 0)
error_message ( "TRAIN used before OUTPUT MODEL set." ) ;
else if (n_inputs <= 0)
error_message ( "TRAIN used before N INPUTS set." ) ;
else if (n_outputs <= 0)
error_message ( "TRAIN used before N OUTPUTS set." ) ;
else if ((net_model == NETMOD_HOP) && (n_inputs != n_outputs))
error_message("HOPFIELD netowork requires INPUTS = OUTPUTS.");
else if ((net_model == NETMOD_BAM) && (out_model != OUTMOD_GENERAL))
error_message("BAM network requires AUTO output mode.");
else if ((net_model == NETMOD_HOP) && (out_model != OUTMOD_AUTO))
error_message("HOFIELD network requires AUTO output mode.");
else if ((net_model != NETMOD_KOH) && (out_model == OUTMOD_CLASSIFY)
&& (classif_output < 0))
error_message( "CLASSIFY output mode but CLASSIFY OUTPUT not set.");
else if ((net_model == NETMOD_KOH) && (out_model != OUTMOD_CLASSIFY))
error_message( "KOHONEN network requires CLASSIFY output mode.");
else {
if (tset == NULL) {
MEMTEXT ( "NEURAL: new tset" ) ;
tset = new TrainingSet ( out_model , n_inputs , n_outputs ) ;
}
tset->train ( rest , classif_output ) ;
strcpy(train_file,rest);
}
continue ;
}
if (check_anneal ( command , rest , &anneal_params ))
continue ;
if (check_genetic ( command , rest , &geninit_params ))
continue ;
if (check_kohonen ( command , rest , &koh_params , &network ))
continue ;
if (check_learn_params ( command , rest , &learn_params , net_model ))
continue ;
if (! strcmp ( command , "LEARN" )) {
if ((tset == NULL) || (tset->ntrain == 0)) {
error_message ( "Cannot LEARN; No training set exists." ) ;
continue ;
}
if ((net_model == NETMOD_KOH) && (out_model != OUTMOD_CLASSIFY)) {
error_message( "KOHONEN network requires CLASSIFY output mode.");
continue ;
}
if (learn_params.init < 0) {
error_message( "Initialization method not set.");
continue ;
}
if (network == NULL)
{
if (net_model == NETMOD_LAYER)
{
if (n_hidden1 < 0)
{
error_message ( "LEARN used before N HIDDEN1 set." ) ;
continue ;
}
else if (n_hidden2 < 0)
{
error_message ( "LEARN used before N HIDDEN2 set." ) ;
continue ;
}
else
{
MEMTEXT ( "NEURAL: new LayerNet" ) ;
network = new LayerNet ( out_model , n_inputs , n_hidden1 ,
n_hidden2 , n_outputs , 1 , 1 ) ;
}
}
else if (net_model == NETMOD_KOH)
{
MEMTEXT ( "NEURAL: new KohNet" ) ;
network = new KohNet ( n_inputs , n_outputs ,
&koh_params , 1 , 1 ) ;
}
else if (net_model == NETMOD_HOP)
{
MEMTEXT ( "NEURAL: new HopNet" );
network = new HopNet (n_inputs,n_outputs, 1,1);
}
else if (net_model == NETMOD_BAM)
{
MEMTEXT ("NEURAL: new BamNet");
network = new LayerNet ( out_model , n_inputs , n_hidden1 ,
n_hidden2 , n_outputs , 1 , 1 ) ;
}
}
if ((network == NULL) || (! network->ok)) { // Malloc failure?
memory_message ( "to create network." ) ;
if (network != NULL) {
delete network ;
network = NULL ;
}
continue ;
}
normal_message("Learning...\n");
network->learn ( tset , &learn_params ) ;
normal_message("End of Learning\n");
if (network->neterr > 0.999999) { // Indicates massive failure
MEMTEXT ( "NEURAL: learn failure delete network" ) ;
delete network ;
network = NULL ;
}
else {
sprintf ( msg , "Final error = %.4lf%% of max possible",
100.0 * network->neterr ) ;
normal_message ( msg ) ;
}
continue ;
}
if (! strcmp ( command , "SAVE WEIGHTS" )) {
if (network == NULL)
error_message ( "There are no learned weights to save." ) ;
else
wt_save ( network , net_model , 0 , rest ) ;
continue ;
}
if (! strcmp ( command , "RESTORE WEIGHTS" )) {
if (network != NULL) {
MEMTEXT ( "NEURAL: delete network for restore" ) ;
delete network ;
network = NULL ;
}
network = wt_restore ( rest , &net_model ) ;
if (network == NULL)
continue ;
if (tset != NULL) {
if ((tset->nin != network->nin)
|| (tset->nout != network->nout)
|| (tset->outmod != network->outmod)) {
error_message ( "Network conflicts with existing training set.");
continue ;
}
}
out_model = network->outmod ;
n_inputs = network->nin ;
n_outputs = network->nout ;
if (net_model == NETMOD_LAYER) {
n_hidden1 = ((LayerNet*) network)->nhid1 ;
n_hidden2 = ((LayerNet*) network)->nhid2 ;
}
if (net_model == NETMOD_KOH)
koh_params.normalization = ((KohNet *) network)->normalization ;
learn_params.init = -1 ;
continue ;
}
if (! strcmp ( command , "CLEAR TRAINING" )) {
if (tset != NULL) {
MEMTEXT ( "NEURAL: delete tset" ) ;
delete tset ;
tset = NULL ;
}
continue ;
}
if (! strcmp ( command , "CLEAR WEIGHTS" )) {
if (network != NULL) {
MEMTEXT ( "NEURAL: delete network" ) ;
delete network ;
network = NULL ;
}
continue ;
}
if (! strcmp ( command , "CLASSIFY OUTPUT" )) {
if (net_model == NETMOD_KOH) {
error_message ( "Cannot specify output for KOHONEN model." ) ;
continue ;
}
if (n_outputs < 0) {
error_message ( "CLASSIFY OUTPUT used before N OUTPUTS set." ) ;
continue ;
}
if (out_model != OUTMOD_CLASSIFY) {
error_message
( "CLASSIFY OUTPUT only valid when OUTPUT MODEL:CLASSIFY" ) ;
continue ;
}
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0)) {
sprintf ( msg , "Illegal CLASSIFY OUTPUT: %s", rest ) ;
error_message ( msg ) ;
}
else if (n > n_outputs) {
sprintf ( msg , "CLASSIFY OUTPUT (%d) exceeds N OUTPUTS (%d)",
n, n_outputs ) ;
error_message ( msg ) ;
}
else
classif_output = n ;
continue ;
}
if (! strcmp ( command , "OUTPUT FILE" )) {
strcpy ( out_file , rest ) ;
continue ;
}
if (! strcmp ( command , "EXECUTE" ))
{
if (network == NULL)
error_message ( "There is no trained network" ) ;
else
{
network->execute_from_file ( rest , out_file) ;
continue ;
}
}
if (! strcmp ( command , "TEST NETWORK" ))
{
if (network == NULL)
error_message ( "There is no trained network" ) ;
else
{
network->test_from_file ( rest ,out_file,net_model) ;
continue ;
}
}
if (! strcmp ( command , "CLASSIFY" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CLASSIFY valid only in CLASSIFY output mode" ) ;
else
network->classify_from_file ( rest , threshold ) ;
continue ;
}
if (! strcmp ( command , "RESET CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else
network->reset_confusion () ;
continue ;
}
if (! strcmp ( command , "CONFUSION THRESHOLD" )) {
p = atof ( rest ) ;
if ((p < 0.0) || (p > 100.0)) {
sprintf ( msg , "Illegal CONFUSION THRESHOLD: %s", rest ) ;
error_message ( msg ) ;
}
else
threshold = p / 100.0 ;
continue ;
}
if (! strcmp ( command , "SHOW CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CONFUSION valid only in CLASSIFY output mode" ) ;
else
network->show_confusion () ;
continue ;
}
if (! strcmp ( command , "SAVE CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CONFUSION valid only in CLASSIFY output mode" ) ;
else
network->save_confusion ( rest ) ;
continue ;
}
sprintf ( msg , "Unknown command: %s", command ) ;
error_message ( msg ) ;
} // Endless command loop
MEMTEXT ( "NEURAL: control_line, msg" ) ;
FREE ( control_line ) ;
FREE ( msg ) ;
MEMCLOSE () ;
exit ( 0 ) ;
}
int main (
int argc , // Number of command line arguments (includes prog name)
char *argv[] // Arguments (prog name is argv[0])
)
{
int i, j, k, nvars, ncases, irep, nreps, ivar, nties, ties ;
int n_indep_vars, idep, icand, *index, *mcpt_max_counts, *mcpt_same_counts, *mcpt_solo_counts ;
double *data, *work, dtemp, *save_info, criterion, *crits ;
char filename[256], **names, depname[256] ;
FILE *fp ;
MutualInformationAdaptive *mi_adapt ;
/*
Process command line parameters
*/
#if 1
if (argc != 5) {
printf ( "\nUsage: MI_ONLY datafile n_indep depname nreps" ) ;
printf ( "\n datafile - name of the text file containing the data" ) ;
printf ( "\n The first line is variable names" ) ;
printf ( "\n Subsequent lines are the data." ) ;
printf ( "\n Delimiters can be space, comma, or tab" ) ;
printf ( "\n n_indep - Number of independent vars, starting with the first" ) ;
printf ( "\n depname - Name of the 'dependent' variable" ) ;
printf ( "\n It must be AFTER the first n_indep variables" ) ;
printf ( "\n nreps - Number of Monte-Carlo permutations, including unpermuted" ) ;
exit ( 1 ) ;
}
strcpy ( filename , argv[1] ) ;
n_indep_vars = atoi ( argv[2] ) ;
strcpy ( depname , argv[3] ) ;
nreps = atoi ( argv[4] ) ;
#else
strcpy ( filename , "..\\SYNTH.TXT" ) ;
n_indep_vars = 7 ;
strcpy ( depname , "SUM1234" ) ;
nreps = 100 ;
#endif
_strupr ( depname ) ;
/*
These are used by MEM.CPP for runtime memory validation
*/
_fullpath ( mem_file_name , "MEM.LOG" , 256 ) ;
fp = fopen ( mem_file_name , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open MEM.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
fclose ( fp ) ;
mem_keep_log = 0 ; // Change this to 1 to keep a memory use log (slows execution!)
mem_max_used = 0 ;
/*
Open the text file to which results will be written
*/
fp = fopen ( "MI_ONLY.LOG" , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open MI_ONLY.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
/*
Read the file and locate the index of the dependent variable
*/
if (readfile ( filename , &nvars , &names , &ncases , &data ))
return EXIT_FAILURE ;
for (idep=0 ; idep<nvars ; idep++) {
if (! strcmp ( depname , names[idep] ))
break ;
}
if (idep == nvars) {
printf ( "\nERROR... Dependent variable %s is not in file", depname ) ;
return EXIT_FAILURE ;
}
if (idep < n_indep_vars) {
printf ( "\nERROR... Dependent variable %s must be beyond independent vars",
depname ) ;
return EXIT_FAILURE ;
}
/*
Check each variable for ties. This is not needed for the algorithm,
but it is good to warn the user, because more than a very few tied values
in any variable seriously degrades performance of the adaptive partitioning algorithm.
*/
MEMTEXT ( "MI_ONLY: Work" ) ;
work = (double *) MALLOC ( ncases * sizeof(double) ) ;
assert ( work != NULL ) ;
ties = 0 ;
assert ( work != NULL ) ;
for (ivar=0 ; ivar<nvars ; ivar++) {
if (ivar > n_indep_vars && ivar != idep)
continue ; // Check only the variables selected by the user
for (i=0 ; i<ncases ; i++)
work[i] = data[i*nvars+ivar] ;
qsortd ( 0 , ncases-1 , work ) ;
nties = 0 ;
for (i=1 ; i<ncases ; i++) {
if (work[i] == work[i-1])
++nties ;
}
if ((double) nties / (double) ncases > 0.05) {
++ties ;
fprintf ( fp , "\nWARNING... %s has %.2lf percent ties!",
names[ivar], 100.0 * nties / (double) ncases ) ;
}
} // For all variables
if (ties) {
fprintf ( fp , "\nThe presence of ties will seriously degrade" ) ;
fprintf ( fp , "\nperformance of the adaptive partitioning algorithm\n\n" ) ;
}
/*
Allocate scratch memory and create the MutualInformation object using the
dependent variable
crits - Mutual information criterion
index - Indices that sort the criterion
save_info - Ditto, this is univariate information, to be sorted
mi_adapt - The MutualInformation object, constructed with the 'dependent' variable
*/
MEMTEXT ( "MI_ONLY work allocs plus MutualInformation" ) ;
crits = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( crits != NULL ) ;
index = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( index != NULL ) ;
mcpt_max_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_max_counts != NULL ) ;
mcpt_same_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_same_counts != NULL ) ;
mcpt_solo_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_solo_counts != NULL ) ;
save_info = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( save_info != NULL ) ;
for (irep=0 ; irep<nreps ; irep++) {
for (i=0 ; i<ncases ; i++) // Get the 'dependent' variable
work[i] = data[i*nvars+idep] ;
// Shuffle dependent variable if in permutation run (irep>0)
if (irep) { // If doing permuted runs, shuffle
i = ncases ; // Number remaining to be shuffled
while (i > 1) { // While at least 2 left to shuffle
j = (int) (unifrand () * i) ;
if (j >= i)
j = i - 1 ;
dtemp = work[--i] ;
work[i] = work[j] ;
work[j] = dtemp ;
}
}
// Here we use a tiny split theshold (instead of the usual 6.0) so that it picks up
// small amounts of mutual information (perhaps including noise).
// If we used 6.0, nearly all permutations of any reasonably sized dataset
// would have a computed mutual information of zero. It's safe picking up
// some noise because the permutation test will account for this.
mi_adapt = new MutualInformationAdaptive ( ncases , work , 1 , 0.1 ) ; // Deliberately tiny for low information
assert ( mi_adapt != NULL ) ;
/*
Compute and save the mutual information for the dependent variable
with each individual independent variable candidate.
*/
for (icand=0 ; icand<n_indep_vars ; icand++) { // Try all candidates
for (i=0 ; i<ncases ; i++)
work[i] = data[i*nvars+icand] ;
criterion = mi_adapt->mut_inf ( work , 1 ) ;
save_info[icand] = criterion ; // We will sort this when all candidates are done
if (irep == 0) { // If doing original (unpermuted), save criterion
index[icand] = icand ; // Will need original indices when criteria are sorted
crits[icand] = criterion ;
mcpt_max_counts[icand] = mcpt_same_counts[icand] = mcpt_solo_counts[icand] = 1 ; // This is >= itself so count it now
}
else {
if (criterion >= crits[icand])
++mcpt_solo_counts[icand] ;
}
} // Initial list of all candidates
delete mi_adapt ;
mi_adapt = NULL ;
if (irep == 0) // Find the indices that sort the candidates per criterion
qsortdsi ( 0 , n_indep_vars-1 , save_info , index ) ;
else {
qsortd ( 0 , n_indep_vars-1 , save_info ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) {
if (save_info[icand] >= crits[index[icand]])
++mcpt_same_counts[index[icand]] ;
if (save_info[n_indep_vars-1] >= crits[index[icand]]) // Valid only for largest
++mcpt_max_counts[index[icand]] ;
}
}
} // For all reps
fprintf ( fp , "\nAdaptive partitioning mutual information of %s", depname);
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nPredictors, in order of decreasing mutual information" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n Variable Information Solo pval Min pval Max pval" ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) { // Do all candidates
k = index[n_indep_vars-1-icand] ; // Index of sorted candidate
fprintf ( fp , "\n%31s %11.5lf %12.4lf %10.4lf %10.4lf", names[k], crits[k],
(double) mcpt_solo_counts[k] / nreps,
(double) mcpt_same_counts[k] / nreps,
(double) mcpt_max_counts[k] / nreps ) ;
}
MEMTEXT ( "MI_ONLY: Finish" ) ;
fclose ( fp ) ;
FREE ( work ) ;
FREE ( crits ) ;
FREE ( index ) ;
FREE ( mcpt_max_counts ) ;
FREE ( mcpt_same_counts ) ;
FREE ( mcpt_solo_counts ) ;
FREE ( save_info ) ;
free_data ( nvars , names , data ) ;
MEMCLOSE () ;
printf ( "\n\nPress any key..." ) ;
_getch () ;
return EXIT_SUCCESS ;
}
int main (
int argc , // Number of command line arguments (includes prog name)
char *argv[] // Arguments (prog name is argv[0])
)
{
/*
Declarations of local variables
*/
/*
User's command control line related variables are here.
Control_file_number and control_files permit nesting of 'CONTROL' commands.
If control_file_number equals -1, control commands are read from stdin.
Otherwise they are read from that file in FILE *control_files.
Up to MAX_CONTROL_FILES can be stacked.
*/
int control_file_number = -1 ; // Stack pointer for control files
FILE *control_files[MAX_CONTROL_FILES] ; // This is the stack
char *control_line ; // User's commands here
char *command, *rest ; // Pointers to its command and parameter parts
int n_command, n_rest ; // Lengths of those parts
/*
These are network parameters which may be set by the user via commands.
They are initialized to defaults which indicate that the user has not
yet set them. As they are set, their current values are placed here.
When learning is done for a network, their values are copied from here
into the network object. When a network is read, the object's values
are copied from it to here. Otherwise, these variables are not used;
the values in the network object itself are used. The only purpose of
these variables is to keep track of current values.
*/
int net_model = -1 ; // Network model (see NETMOD_? in CONST.H)
int out_model = -1 ; // Output model (see OUTMOD_? in CONST.H)
int n_inputs = -1 ; // Number of input neurons
int n_outputs = -1 ; // Number of output neurons
int n_hidden1 = -1 ; // Number of hidden layer one neurons
int n_hidden2 = -1 ; // Ditto layer 2 (0 if just one hidden layer)
TrainingSet *tset = NULL ; // Training set here
Network *network = NULL ; // Network here
struct LearnParams learn_params ; // General learning parameters
struct AnnealParams anneal_params ; // Simulated annealing parameters
struct GenInitParams geninit_params ; // Genetic initialization parameters
struct KohParams koh_params ; // Kohonen parameters
int classif_output = -1 ; // Current class (0=reject) for classif training
char out_file[80] = "" ; // File for EXECUTE output
double threshold ; // CLASSIFY confusion reject cutoff
/*
Miscellaneous variables
*/
int i, n, m ;
double p ;
char *msg ;
FILE *fp ;
/*
--------------------------------------------------------------------------------
Program starts here.
Verify that a careless user didn't fail to set the integer size
correctly when compiling.
--------------------------------------------------------------------------------
*/
#if VERSION_16_BIT
if (sizeof(int) > 2) {
printf ( "\nRecompile with VERSION_16_BIT set to 0 in CONST.H" ) ;
exit ( 1 ) ;
}
#else
if (sizeof(int) < 4) {
printf ( "\nRecompile with VERSION_16_BIT set to 1 in CONST.H" ) ;
exit ( 1 ) ;
}
#endif
printf ( "\nNEURAL - Program to train and test neural networks" ) ;
printf("\nCopyright (c) 1993 by Academic Press, Inc.");
printf("\nAll rights reserved. Permission is hereby granted, until further notice,");
printf("\nto make copies of this diskette, which are not for resale, provided these");
printf("\ncopies are made from this master diskette only, and provided that the");
printf("\nfollowing copyright notice appears on the diskette label:");
printf("\n(c) 1993 by Academic Press, Inc.");
printf("\nExcept as previously stated, no part of the computer program embodied in");
printf("\nthis diskette may be reproduced or transmitted in any form or by any means,");
printf("\nelectronic or mechanical, including input into storage in any information");
printf("\nsystem for resale, without permission in writing from the publisher.");
printf("\nProduced in the United States of America.");
printf("\nISBN 0-12-479041-0");
/*
Process command line parameters
*/
mem_name[0] = 0 ; // Default is no memory allocation file
for (i=1 ; i<argc ; i++) { // Process all command line args
str_to_upr ( argv[i] ) ; // Easier if all upper case
if (! strcmp ( argv[i] , "/DEBUG" )) {
sscanf ( argv[++i] , "%s" , mem_name ) ;
if ((strlen ( mem_name ) > 1) || ! isalpha ( mem_name[0] )) {
printf ( "\nIllegal DEBUG drive (%s); must be 1 letter." ) ;
exit ( 1 ) ;
}
continue ;
}
printf ( "\nIllegal command line parameter (%s)", argv[i] ) ;
exit ( 1 ) ;
}
/*
Initialize memory allocation debugging
*/
if (strlen ( mem_name )) {
strcat ( mem_name , ":mem.log" ) ;
fp = fopen ( mem_name , "wt" ) ;
if (fp == NULL) {
printf ( "\nCannot open debugging file %s", mem_name ) ;
exit ( 1 ) ;
}
fclose ( fp ) ;
mem_log = 1 ;
}
else
mem_log = 0 ;
mem_used = 0 ;
/*
Initialize defaults
*/
learn_params.init = -1 ;
learn_params.quit_err = 0.0 ;
learn_params.retries = 32767 ;
anneal_params.temps0 = 3 ;
anneal_params.temps = 4 ;
anneal_params.iters0 = 50 ;
anneal_params.iters = 20 ;
anneal_params.setback0 = 50 ;
anneal_params.setback = 20 ;
anneal_params.start0 = 3.0 ;
anneal_params.start = 4.0 ;
anneal_params.stop0 = 1.0 ;
anneal_params.stop = 0.02 ;
geninit_params.pool = 50 ;
geninit_params.gens = 3 ;
geninit_params.climb = 0 ;
geninit_params.overinit = 1.5 ;
geninit_params.pcross = 0.8 ;
geninit_params.pmutate = 0.0001 ;
koh_params.normalization = 0 ; // 0=multiplicative, 1=Z
koh_params.learn_method = 1 ; // 0=additive, 1=subtractive
koh_params.rate = 0.4 ; // learning rate
koh_params.reduction = 0.99 ; // learning rate reduction
learn_params.ap = &anneal_params ;
learn_params.gp = &geninit_params ;
learn_params.kp = &koh_params ;
act_func_init () ; // Initialize interpolation table for activation function
MEMTEXT ( "NEURAL: control_line, msg" ) ;
if (((control_line = (char *) MALLOC ( CONTROL_LINE_LENGTH+1 )) == NULL)
|| ((msg = (char *) MALLOC ( CONTROL_LINE_LENGTH+1 )) == NULL)) {
printf ( "\nInsufficient memory" ) ;
exit ( 1 ) ;
}
/*
Main loop processes all commands
*/
for (;;) {
get_control_line ( control_line , &control_file_number, control_files ) ;
split_control_line ( control_line , &command , &n_command ,
&rest , &n_rest ) ;
if (! n_command) {
if (n_rest) {
sprintf ( msg , "No colon after command: %s", rest ) ;
error_message ( msg ) ;
}
continue ;
}
sprintf ( msg , "%s : %s", command, rest ) ;
normal_message ( msg ) ;
/*
Act on the command
*/
if (! strcmp ( command , "QUIT" ))
break ;
if (! strcmp ( command , "CONTROL" )) {
stack_control_file ( rest , &control_file_number , control_files ) ;
continue ;
}
if (! strcmp ( command , "NETWORK MODEL" )) {
if (! strcmp ( rest , "LAYER" ))
n = NETMOD_LAYER ;
else if (! strcmp ( rest , "KOHONEN" ))
n = NETMOD_KOH ;
else {
sprintf ( msg , "Illegal NETWORK MODEL: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (net_model == n)
continue ;
if (ok_to_clear_weights( &network )) {
net_model = n ;
learn_params.init = -1 ;
}
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "OUTPUT MODEL" )) {
if (! strcmp ( rest , "CLASSIFY" ))
n = OUTMOD_CLASSIFY ;
else if (! strcmp ( rest , "AUTO" ))
n = OUTMOD_AUTO ;
else if (! strcmp ( rest , "GENERAL" ))
n = OUTMOD_GENERAL ;
else {
sprintf ( msg , "Illegal OUTPUT MODEL: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (out_model == n)
continue ;
if ((ok_to_clear_tset( &tset )) && (ok_to_clear_weights( &network)))
out_model = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N INPUTS" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n <= 0) || (n > MAX_INPUTS)) {
sprintf ( msg , "Illegal N INPUTS: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_inputs == n)
continue ;
if ((ok_to_clear_tset( &tset)) && (ok_to_clear_weights(&network)))
n_inputs = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N OUTPUTS" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n <= 0) || (n > MAX_OUTPUTS)) {
sprintf ( msg , "Illegal N OUTPUTS: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_outputs == n)
continue ;
if ((ok_to_clear_tset( &tset)) && (ok_to_clear_weights(&network)))
n_outputs = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N HIDDEN1" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0) || (n > MAX_HIDDEN)) {
sprintf ( msg , "Illegal N HIDDEN1: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n_hidden1 == n)
continue ;
if (ok_to_clear_weights( &network ))
n_hidden1 = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "N HIDDEN2" )) {
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0) || (n > MAX_HIDDEN)) {
sprintf ( msg , "Illegal N HIDDEN2: %s", rest ) ;
error_message ( msg ) ;
continue ;
}
if (n && ! n_hidden1) {
error_message ( "N HIDDEN2 must be 0 if N HIDDEN1 IS 0." ) ;
continue ;
}
if (n_hidden2 == n)
continue ;
if (ok_to_clear_weights( &network ))
n_hidden2 = n ;
else
warning_message ( "Command aborted" ) ;
continue ;
}
if (! strcmp ( command , "TRAIN" )) {
if ((out_model == OUTMOD_AUTO) && (n_outputs != n_inputs)) {
warning_message ( "Setting N OUTPUTS = N INPUTS" ) ;
n_outputs = n_inputs ;
}
if (out_model <= 0)
error_message ( "TRAIN used before OUTPUT MODEL set." ) ;
else if (n_inputs <= 0)
error_message ( "TRAIN used before N INPUTS set." ) ;
else if (n_outputs <= 0)
error_message ( "TRAIN used before N OUTPUTS set." ) ;
else if ((net_model != NETMOD_KOH) && (out_model == OUTMOD_CLASSIFY)
&& (classif_output < 0))
error_message( "CLASSIFY output mode but CLASSIFY OUTPUT not set.");
else if ((net_model == NETMOD_KOH) && (out_model != OUTMOD_CLASSIFY))
error_message( "KOHONEN network requires CLASSIFY output mode.");
else {
if (tset == NULL) {
MEMTEXT ( "NEURAL: new tset" ) ;
tset = new TrainingSet ( out_model , n_inputs , n_outputs ) ;
}
tset->train ( rest , classif_output ) ;
}
continue ;
}
if (check_anneal ( command , rest , &anneal_params ))
continue ;
if (check_genetic ( command , rest , &geninit_params ))
continue ;
if (check_kohonen ( command , rest , &koh_params , &network ))
continue ;
if (check_learn_params ( command , rest , &learn_params , net_model ))
continue ;
if (! strcmp ( command , "LEARN" )) {
if ((tset == NULL) || (tset->ntrain == 0)) {
error_message ( "Cannot LEARN; No training set exists." ) ;
continue ;
}
if ((net_model == NETMOD_KOH) && (out_model != OUTMOD_CLASSIFY)) {
error_message( "KOHONEN network requires CLASSIFY output mode.");
continue ;
}
if (learn_params.init < 0) {
error_message( "Initialization method not set.");
continue ;
}
if (network == NULL) {
if (net_model == NETMOD_LAYER) {
if (n_hidden1 < 0) {
error_message ( "LEARN used before N HIDDEN1 set." ) ;
continue ;
}
else if (n_hidden2 < 0) {
error_message ( "LEARN used before N HIDDEN2 set." ) ;
continue ;
}
else {
MEMTEXT ( "NEURAL: new LayerNet" ) ;
network = new LayerNet ( out_model , n_inputs , n_hidden1 ,
n_hidden2 , n_outputs , 1 , 1 ) ;
}
}
else if (net_model == NETMOD_KOH) {
MEMTEXT ( "NEURAL: new KohNet" ) ;
network = new KohNet ( n_inputs , n_outputs ,
&koh_params , 1 , 1 ) ;
}
}
if ((network == NULL) || (! network->ok)) { // Malloc failure?
memory_message ( "to create network." ) ;
if (network != NULL) {
delete network ;
network = NULL ;
}
continue ;
}
network->learn ( tset , &learn_params ) ;
if (network->neterr > 0.999999) { // Indicates massive failure
MEMTEXT ( "NEURAL: learn failure delete network" ) ;
delete network ;
network = NULL ;
}
else {
sprintf ( msg , "Final error = %.4lf%% of max possible",
100.0 * network->neterr ) ;
normal_message ( msg ) ;
}
continue ;
}
if (! strcmp ( command , "SAVE WEIGHTS" )) {
if (network == NULL)
error_message ( "There are no learned weights to save." ) ;
else
wt_save ( network , net_model , 0 , rest ) ;
continue ;
}
if (! strcmp ( command , "RESTORE WEIGHTS" )) {
if (network != NULL) {
MEMTEXT ( "NEURAL: delete network for restore" ) ;
delete network ;
network = NULL ;
}
network = wt_restore ( rest , &net_model ) ;
if (network == NULL)
continue ;
if (tset != NULL) {
if ((tset->nin != network->nin)
|| (tset->nout != network->nout)
|| (tset->outmod != network->outmod)) {
error_message ( "Network conflicts with existing training set.");
continue ;
}
}
out_model = network->outmod ;
n_inputs = network->nin ;
n_outputs = network->nout ;
if (net_model == NETMOD_LAYER) {
n_hidden1 = ((LayerNet*) network)->nhid1 ;
n_hidden2 = ((LayerNet*) network)->nhid2 ;
}
if (net_model == NETMOD_KOH)
koh_params.normalization = ((KohNet *) network)->normalization ;
learn_params.init = -1 ;
continue ;
}
if (! strcmp ( command , "CLEAR TRAINING" )) {
if (tset != NULL) {
MEMTEXT ( "NEURAL: delete tset" ) ;
delete tset ;
tset = NULL ;
}
continue ;
}
if (! strcmp ( command , "CLEAR WEIGHTS" )) {
if (network != NULL) {
MEMTEXT ( "NEURAL: delete network" ) ;
delete network ;
network = NULL ;
}
continue ;
}
if (! strcmp ( command , "CLASSIFY OUTPUT" )) {
if (net_model == NETMOD_KOH) {
error_message ( "Cannot specify output for KOHONEN model." ) ;
continue ;
}
if (n_outputs < 0) {
error_message ( "CLASSIFY OUTPUT used before N OUTPUTS set." ) ;
continue ;
}
if (out_model != OUTMOD_CLASSIFY) {
error_message
( "CLASSIFY OUTPUT only valid when OUTPUT MODEL:CLASSIFY" ) ;
continue ;
}
m = sscanf ( rest , "%d" , &n ) ;
if ((m <= 0) || (n < 0)) {
sprintf ( msg , "Illegal CLASSIFY OUTPUT: %s", rest ) ;
error_message ( msg ) ;
}
else if (n > n_outputs) {
sprintf ( msg , "CLASSIFY OUTPUT (%d) exceeds N OUTPUTS (%d)",
n, n_outputs ) ;
error_message ( msg ) ;
}
else
classif_output = n ;
continue ;
}
if (! strcmp ( command , "OUTPUT FILE" )) {
strcpy ( out_file , rest ) ;
continue ;
}
if (! strcmp ( command , "EXECUTE" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else
network->execute_from_file ( rest , out_file ) ;
continue ;
}
if (! strcmp ( command , "CLASSIFY" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CLASSIFY valid only in CLASSIFY output mode" ) ;
else
network->classify_from_file ( rest , threshold ) ;
continue ;
}
if (! strcmp ( command , "RESET CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else
network->reset_confusion () ;
continue ;
}
if (! strcmp ( command , "CONFUSION THRESHOLD" )) {
p = atof ( rest ) ;
if ((p < 0.0) || (p > 100.0)) {
sprintf ( msg , "Illegal CONFUSION THRESHOLD: %s", rest ) ;
error_message ( msg ) ;
}
else
threshold = p / 100.0 ;
continue ;
}
if (! strcmp ( command , "SHOW CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CONFUSION valid only in CLASSIFY output mode" ) ;
else
network->show_confusion () ;
continue ;
}
if (! strcmp ( command , "SAVE CONFUSION" )) {
if (network == NULL)
error_message ( "There is no trained network" ) ;
else if (out_model != OUTMOD_CLASSIFY)
error_message ( "CONFUSION valid only in CLASSIFY output mode" ) ;
else
network->save_confusion ( rest ) ;
continue ;
}
sprintf ( msg , "Unknown command: %s", command ) ;
error_message ( msg ) ;
} // Endless command loop
MEMTEXT ( "NEURAL: control_line, msg" ) ;
FREE ( control_line ) ;
FREE ( msg ) ;
MEMCLOSE () ;
return 0 ;
}
int main (
int argc , // Number of command line arguments (includes prog name)
char *argv[] // Arguments (prog name is argv[0])
)
{
int i, j, k, nvars, ncases, irep, nreps, nbins, nbins_dep, nbins_indep, *count ;
int n_indep_vars, idep, icand, *index, *mcpt_max_counts, *mcpt_same_counts, *mcpt_solo_counts ;
short int *bins_dep, *bins_indep ;
double *data, *work, dtemp, *save_info, criterion, *crits ;
double *ab, *bc, *b ;
char filename[256], **names, depname[256] ;
FILE *fp ;
/*
Process command line parameters
*/
#if 1
if (argc != 6) {
printf ( "\nUsage: TRANSFER datafile n_indep depname nreps" ) ;
printf ( "\n datafile - name of the text file containing the data" ) ;
printf ( "\n The first line is variable names" ) ;
printf ( "\n Subsequent lines are the data." ) ;
printf ( "\n Delimiters can be space, comma, or tab" ) ;
printf ( "\n n_indep - Number of independent vars, starting with the first" ) ;
printf ( "\n depname - Name of the 'dependent' variable" ) ;
printf ( "\n It must be AFTER the first n_indep variables" ) ;
printf ( "\n nbins - Number of bins for all variables" ) ;
printf ( "\n nreps - Number of Monte-Carlo permutations, including unpermuted" ) ;
exit ( 1 ) ;
}
strcpy ( filename , argv[1] ) ;
n_indep_vars = atoi ( argv[2] ) ;
strcpy ( depname , argv[3] ) ;
nbins = atoi ( argv[4] ) ;
nreps = atoi ( argv[5] ) ;
#else
strcpy ( filename , "..\\SYNTH.TXT" ) ;
n_indep_vars = 7 ;
strcpy ( depname , "SUM1234" ) ;
nbins = 2 ;
nreps = 1 ;
#endif
_strupr ( depname ) ;
/*
These are used by MEM.CPP for runtime memory validation
*/
_fullpath ( mem_file_name , "MEM.LOG" , 256 ) ;
fp = fopen ( mem_file_name , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open MEM.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
fclose ( fp ) ;
mem_keep_log = 1 ; // Change this to 1 to keep a memory use log (slows execution!)
mem_max_used = 0 ;
/*
Open the text file to which results will be written
*/
fp = fopen ( "TRANSFER.LOG" , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open TRANSFER.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
/*
Read the file and locate the index of the dependent variable
*/
if (readfile ( filename , &nvars , &names , &ncases , &data ))
return EXIT_FAILURE ;
for (idep=0 ; idep<nvars ; idep++) {
if (! strcmp ( depname , names[idep] ))
break ;
}
if (idep == nvars) {
printf ( "\nERROR... Dependent variable %s is not in file", depname ) ;
return EXIT_FAILURE ;
}
if (idep < n_indep_vars) {
printf ( "\nERROR... Dependent variable %s must be beyond independent vars",
depname ) ;
return EXIT_FAILURE ;
}
/*
Allocate scratch memory
crits - Transfer Entropy criterion
index - Indices that sort the criterion
save_info - Ditto, this is univariate criteria, to be sorted
*/
MEMTEXT ( "TRANSFER work allocs" ) ;
work = (double *) MALLOC ( ncases * sizeof(double) ) ;
assert ( work != NULL ) ;
crits = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( crits != NULL ) ;
index = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( index != NULL ) ;
bins_indep = (short int *) MALLOC ( ncases * sizeof(short int) ) ;
assert ( bins_indep != NULL ) ;
bins_dep = (short int *) MALLOC ( ncases * sizeof(short int) ) ;
assert ( bins_dep != NULL ) ;
mcpt_max_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_max_counts != NULL ) ;
mcpt_same_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_same_counts != NULL ) ;
mcpt_solo_counts = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( mcpt_solo_counts != NULL ) ;
save_info = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( save_info != NULL ) ;
count = (int *) MALLOC ( nbins * nbins * nbins * sizeof(int) ) ;
assert ( count != NULL ) ;
ab = (double *) MALLOC ( nbins * nbins * sizeof(double) ) ;
assert ( ab != NULL ) ;
bc = (double *) MALLOC ( nbins * nbins * sizeof(double) ) ;
assert ( bc != NULL ) ;
b = (double *) MALLOC ( nbins * sizeof(double) ) ;
assert ( b != NULL ) ;
/*
Get the dependent variable and partition it
*/
for (i=0 ; i<ncases ; i++) // Get the 'dependent' variable
work[i] = data[i*nvars+idep] ;
nbins_dep = nbins ;
partition ( ncases , work , &nbins_dep , NULL , bins_dep ) ;
/*
Replication loop is here
*/
for (irep=0 ; irep<nreps ; irep++) {
/*
Compute and save the transfer entropy of the dependent variable
with each individual independent variable candidate.
*/
for (icand=0 ; icand<n_indep_vars ; icand++) { // Try all candidates
for (i=0 ; i<ncases ; i++)
work[i] = data[i*nvars+icand] ;
// Shuffle independent variable if in permutation run (irep>0)
if (irep) { // If doing permuted runs, shuffle
i = ncases ; // Number remaining to be shuffled
while (i > 1) { // While at least 2 left to shuffle
j = (int) (unifrand () * i) ;
if (j >= i)
j = i - 1 ;
dtemp = work[--i] ;
work[i] = work[j] ;
work[j] = dtemp ;
}
}
nbins_indep = nbins ;
partition ( ncases , work , &nbins_indep , NULL , bins_indep ) ;
criterion = trans_ent ( ncases , nbins_indep , nbins_dep ,
bins_indep , bins_dep ,
0 , 1 , 1 , count , ab , bc , b ) ;
save_info[icand] = criterion ; // We will sort this when all candidates are done
if (irep == 0) { // If doing original (unpermuted), save criterion
index[icand] = icand ; // Will need original indices when criteria are sorted
crits[icand] = criterion ;
mcpt_max_counts[icand] = mcpt_same_counts[icand] = mcpt_solo_counts[icand] = 1 ; // This is >= itself so count it now
}
else {
if (criterion >= crits[icand])
++mcpt_solo_counts[icand] ;
}
} // Initial list of all candidates
if (irep == 0) // Find the indices that sort the candidates per criterion
qsortdsi ( 0 , n_indep_vars-1 , save_info , index ) ;
else {
qsortd ( 0 , n_indep_vars-1 , save_info ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) {
if (save_info[icand] >= crits[index[icand]])
++mcpt_same_counts[index[icand]] ;
if (save_info[n_indep_vars-1] >= crits[index[icand]]) // Valid only for largest
++mcpt_max_counts[index[icand]] ;
}
}
} // For all reps
fprintf ( fp , "\nTransfer entropy of %s", depname);
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nPredictors, in order of decreasing transfer entropy" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n Variable Information Solo pval Min pval Max pval" ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) { // Do all candidates
k = index[n_indep_vars-1-icand] ; // Index of sorted candidate
fprintf ( fp , "\n%31s %11.5lf %12.4lf %10.4lf %10.4lf", names[k], crits[k],
(double) mcpt_solo_counts[k] / nreps,
(double) mcpt_same_counts[k] / nreps,
(double) mcpt_max_counts[k] / nreps ) ;
}
MEMTEXT ( "TRANSFER: Finish" ) ;
fclose ( fp ) ;
FREE ( work ) ;
FREE ( crits ) ;
FREE ( index ) ;
FREE ( bins_indep ) ;
FREE ( bins_dep ) ;
FREE ( mcpt_max_counts ) ;
FREE ( mcpt_same_counts ) ;
FREE ( mcpt_solo_counts ) ;
FREE ( save_info ) ;
FREE ( count ) ;
FREE ( ab ) ;
FREE ( bc ) ;
FREE ( b ) ;
free_data ( nvars , names , data ) ;
MEMCLOSE () ;
printf ( "\n\nPress any key..." ) ;
_getch () ;
return EXIT_SUCCESS ;
}
int main (
int argc , // Number of command line arguments (includes prog name)
char *argv[] // Arguments (prog name is argv[0])
)
{
int i, j, k, nvars, ncases, ndiv, maxkept, ivar, nties, ties ;
int n_indep_vars, idep, icand, iother, ibest, *sortwork, nkept, *kept ;
double *data, *work ;
double *save_info, *univar_info, *pair_info, bestredun, redun, bestcrit ;
double criterion, relevance, redundancy, *crits, *reduns ;
char filename[256], **names, depname[256] ;
char trial_name[256], *pair_found ;
FILE *fp ;
MutualInformationParzen *mi_parzen ;
MutualInformationAdaptive *mi_adapt ;
/*
Process command line parameters
*/
#if 1
if (argc != 6) {
printf ( "\nUsage: MI_CONT datafile n_indep depname ndiv maxkept" ) ;
printf ( "\n datafile - name of the text file containing the data" ) ;
printf ( "\n The first line is variable names" ) ;
printf ( "\n Subsequent lines are the data." ) ;
printf ( "\n Delimiters can be space, comma, or tab" ) ;
printf ( "\n n_indep - Number of independent vars, starting with the first" ) ;
printf ( "\n depname - Name of the 'dependent' variable" ) ;
printf ( "\n It must be AFTER the first n_indep variables" ) ;
printf ( "\n ndiv - Normally zero, to employ adaptive partitioning" ) ;
printf ( "\n Specify 5 (for very few cases) to 15 (for an" ) ;
printf ( "\n enormous number of cases) to use Parzen windows" ) ;
printf ( "\n maxkept - Stepwise will allow at most this many predictors" ) ;
exit ( 1 ) ;
}
strcpy ( filename , argv[1] ) ;
n_indep_vars = atoi ( argv[2] ) ;
strcpy ( depname , argv[3] ) ;
ndiv = atoi ( argv[4] ) ;
maxkept = atoi ( argv[5] ) ;
#else
strcpy ( filename , "..\\VARS.TXT" ) ;
n_indep_vars = 8 ;
strcpy ( depname , "DAY_RETURN" ) ;
ndiv = 0 ;
maxkept = 5 ;
#endif
_strupr ( depname ) ;
/*
These are used by MEM.CPP for runtime memory validation
*/
_fullpath ( mem_file_name , "MEM.LOG" , 256 ) ;
fp = fopen ( mem_file_name , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open MEM.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
fclose ( fp ) ;
mem_keep_log = 1 ;
mem_max_used = 0 ;
/*
Open the text file to which results will be written
*/
fp = fopen ( "MI_CONT.LOG" , "wt" ) ;
if (fp == NULL) { // Should never happen
printf ( "\nCannot open MI_CONT.LOG file for writing!" ) ;
return EXIT_FAILURE ;
}
/*
Read the file and locate the index of the 'dependent' variable
*/
if (readfile ( filename , &nvars , &names , &ncases , &data ))
return EXIT_FAILURE ;
for (idep=0 ; idep<nvars ; idep++) {
if (! strcmp ( depname , names[idep] ))
break ;
}
if (idep == nvars) {
printf ( "\nERROR... Dependent variable %s is not in file", depname ) ;
return EXIT_FAILURE ;
}
if (idep < n_indep_vars) {
printf ( "\nERROR... Dependent variable %s must be beyond independent vars",
depname ) ;
return EXIT_FAILURE ;
}
/*
If adaptive partitioning is specified, check each variable for ties.
This is not needed for the algorithm, but it is good to warn the
user, because more than a very few tied values in any variable seriously
degrades performance of the adaptive partitioning algorithm.
*/
MEMTEXT ( "MI_CONT: Work" ) ;
work = (double *) MALLOC ( ncases * sizeof(double) ) ;
assert ( work != NULL ) ;
if (ndiv == 0) { // If adaptive partitioning, check for ties
ties = 0 ;
assert ( work != NULL ) ;
for (ivar=0 ; ivar<nvars ; ivar++) {
if (ivar > n_indep_vars && ivar != idep)
continue ; // Check only the variables selected by the user
for (i=0 ; i<ncases ; i++)
work[i] = data[i*nvars+ivar] ;
qsortd ( 0 , ncases-1 , work ) ;
nties = 0 ;
for (i=1 ; i<ncases ; i++) {
if (work[i] == work[i-1])
++nties ;
}
if ((double) nties / (double) ncases > 0.05) {
++ties ;
fprintf ( fp , "\nWARNING... %s has %.2lf percent ties!",
names[ivar], 100.0 * nties / (double) ncases ) ;
}
} // For all variables
if (ties) {
fprintf ( fp , "\nThe presence of ties will seriously degrade" ) ;
fprintf ( fp , "\nperformance of the adaptive partitioning algorithm\n\n" ) ;
}
} // If adaptive partitioning, so testing for ties in the data
/*
Allocate scratch memory and create the MutualInformation object using the
dependent variable
kept - Array of indices of variables kept so far
crits - Ditto, criterion
reduns - Ditto, redundancy
sortwork - Temporary use for printing variable's information sorted
save_info - Ditto, this is univariate information, to be sorted
univar_info - Also univariate information, but not sorted, for use in stepwise
pair_found - Flag: is there valid info in the corresponding element of the next array
pair_info - Preserve pairwise information of indeps to avoid expensive recalculation
mi_parzen - The MutualInformation object, constructed with the 'dependent' variable
mi_adapt - Ditto, but used if adaptive partitioning
*/
MEMTEXT ( "MI_CONT 6 allocs plus MutualInformation" ) ;
kept = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( kept != NULL ) ;
crits = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( crits != NULL ) ;
reduns = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( reduns != NULL ) ;
sortwork = (int *) MALLOC ( n_indep_vars * sizeof(int) ) ;
assert ( sortwork != NULL ) ;
save_info = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( save_info != NULL ) ;
univar_info = (double *) MALLOC ( n_indep_vars * sizeof(double) ) ;
assert ( univar_info != NULL ) ;
pair_found = (char *) MALLOC ( (n_indep_vars * (n_indep_vars+1) / 2) * sizeof(char) ) ;
assert ( pair_found != NULL ) ;
pair_info = (double *) MALLOC ( (n_indep_vars * (n_indep_vars+1) / 2) * sizeof(double) ) ;
assert ( pair_info != NULL ) ;
for (i=0 ; i<ncases ; i++) // Get the 'dependent' variable
work[i] = data[i*nvars+idep] ;
if (ndiv > 0) {
mi_parzen = new MutualInformationParzen ( ncases , work , ndiv ) ;
mi_adapt = NULL ;
assert ( mi_parzen != NULL ) ;
}
else {
mi_adapt = new MutualInformationAdaptive ( ncases , work , 0 , 6.0 ) ;
mi_parzen = NULL ;
assert ( mi_adapt != NULL ) ;
}
memset ( pair_found , 0 , (n_indep_vars * (n_indep_vars+1) / 2) * sizeof(char) ) ;
if (ndiv > 0)
fprintf ( fp , "\nParzen mutual information of %s (ndiv=%d)", depname, ndiv);
else
fprintf ( fp , "\nAdaptive partitioning mutual information of %s", depname);
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n---------------------------------------------------------------" ) ;
fprintf ( fp , "\n" ) ;
/*
Compute and save the mutual information for the dependent variable with
each individual independent variable candidate. Print the results,
sort them, and print them again, this time sorted.
*/
fprintf ( fp , "\nInitial candidates, in order of appearance in data file" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n Variable Information" ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) { // Try all candidates
for (i=0 ; i<ncases ; i++)
work[i] = data[i*nvars+icand] ;
if (ndiv > 0)
criterion = mi_parzen->mut_inf ( work ) ;
else
criterion = mi_adapt->mut_inf ( work , 0 ) ;
printf ( "\n%s = %.5lf", names[icand], criterion ) ;
fprintf ( fp , "\n%31s %.5lf", names[icand], criterion ) ;
sortwork[icand] = icand ;
save_info[icand] = univar_info[icand] = criterion ;
} // Initial list of all candidates
if (mi_parzen != NULL) {
delete mi_parzen ;
mi_parzen = NULL ;
}
if (mi_adapt != NULL) {
delete mi_adapt ;
mi_adapt = NULL ;
}
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nInitial candidates, in order of decreasing mutual information" ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n Variable Information" ) ;
qsortdsi ( 0 , n_indep_vars-1 , save_info , sortwork ) ;
for (icand=0 ; icand<n_indep_vars ; icand++) { // Do all candidates
k = sortwork[n_indep_vars-1-icand] ; // Index of sorted candidate
fprintf ( fp , "\n%31s %.5lf", names[k], save_info[n_indep_vars-1-icand] ) ;
}
/*
Initialize the 'kept' set to be the best variable, and then begin the
main outer loop that adds variables one at a time
*/
kept[0] = sortwork[n_indep_vars-1] ; // Index of best single candidate
crits[0] = save_info[n_indep_vars-1] ;
reduns[0] = 0.0 ;
nkept = 1 ;
if (maxkept > n_indep_vars) // Guard against silly user
maxkept = n_indep_vars ;
while (nkept < maxkept) {
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nVariables so far Relevance Redundancy Criterion" ) ;
for (i=0 ; i<nkept ; i++)
fprintf ( fp , "\n%31s %10.5lf %10.5lf %10.5lf",
names[kept[i]], crits[i] + reduns[i], reduns[i], crits[i] ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nSearching for an additional candidate..." ) ;
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\n Variable Relevance Redundancy Criterion" ) ;
bestcrit = -1.e60 ;
for (icand=0 ; icand<n_indep_vars ; icand++) { // Try all candidates
for (i=0 ; i<nkept ; i++) { // Is this candidate already kept?
if (kept[i] == icand)
break ;
}
if (i < nkept) // If this candidate 'icand' is already kept
continue ; // Skip it
strcpy ( trial_name , names[icand] ) ; // Its name for printing
for (i=0 ; i<ncases ; i++) // Get its cases
work[i] = data[i*nvars+icand] ;
if (ndiv > 0) {
mi_parzen = new MutualInformationParzen ( ncases , work , ndiv ) ;
mi_adapt = NULL ;
assert ( mi_parzen != NULL ) ;
}
else {
mi_adapt = new MutualInformationAdaptive ( ncases , work , 0 , 6.0 ) ;
mi_parzen = NULL ;
assert ( mi_adapt != NULL ) ;
}
relevance = univar_info[icand] ; // We saved it during initial printing
printf ( "\n%s relevance = %.5lf", trial_name, relevance ) ;
// Compute the redundancy of this candidate
// This is the mean of its redundancy with all kept variables
redundancy = 0.0 ;
for (iother=0 ; iother<nkept ; iother++) { // Process entire kept set
j = kept[iother] ; // Index of a variable in the kept set
if (icand > j) // pair_found and pair_info are
k = icand*(icand+1)/2+j ; // symmetric, so k is the index
else // into them
k = j*(j+1)/2+icand ;
if (pair_found[k]) // If we already computed it
redun = pair_info[k] ; // Don't do it again
else { // First time for this pair, so compute
for (i=0 ; i<ncases ; i++) // Get its cases
work[i] = data[i*nvars+j] ; // Variable already in kept set
if (ndiv > 0)
redun = mi_parzen->mut_inf ( work ) ;
else
redun = mi_adapt->mut_inf ( work , 0 ) ;
pair_found[k] = 1 ; // Flag that this pair has been computed
pair_info[k] = redun ; // And save the MI for this pair
} // Else must compute redundancy
redundancy += redun ;
printf ( "\n %s <-> %s redundancy = %.5lf", names[icand], names[j], redun ) ;
} // For all kept variables, computing mean redundancy
if (mi_parzen != NULL) {
delete mi_parzen ;
mi_parzen = NULL ;
}
if (mi_adapt != NULL) {
delete mi_adapt ;
mi_adapt = NULL ;
}
redundancy /= nkept ; // It is the mean across all kept
printf ( "\nRedundancy = %.5lf", redundancy ) ;
criterion = relevance - redundancy ;
fprintf ( fp , "\n%31s %10.5lf %10.5lf %10.5lf",
trial_name, relevance, redundancy, criterion ) ;
if (criterion > bestcrit) { // Did we just set a new record?
bestcrit = criterion ; // If so, update the record
bestredun = redundancy ; // Needed for printing results later
ibest = icand ; // Keep track of the winning candidate
}
} // For all candidates
// We now have the best candidate
if (bestcrit <= 0.0)
break ;
kept[nkept] = ibest ;
crits[nkept] = bestcrit ;
reduns[nkept] = bestredun ;
++nkept ;
} // While adding new variables
fprintf ( fp , "\n" ) ;
fprintf ( fp , "\nFinal set Relevance Redundancy Criterion" ) ;
for (i=0 ; i<nkept ; i++)
fprintf ( fp , "\n%31s %10.5lf %10.5lf %10.5lf",
names[kept[i]], crits[i] + reduns[i], reduns[i], crits[i] ) ;
MEMTEXT ( "MI_CONT: Finish" ) ;
fclose ( fp ) ;
FREE ( work ) ;
FREE ( kept ) ;
FREE ( crits ) ;
FREE ( reduns ) ;
FREE ( sortwork ) ;
FREE ( save_info ) ;
FREE ( univar_info ) ;
FREE ( pair_found ) ;
FREE ( pair_info ) ;
if (mi_parzen != NULL)
delete mi_parzen ;
if (mi_adapt != NULL)
delete mi_adapt ;
free_data ( nvars , names , data ) ;
MEMCLOSE () ;
printf ( "\n\nPress any key..." ) ;
_getch () ;
return EXIT_SUCCESS ;
}
