New Makefile

EaseaLex.l

@@ -173,6 +173,7 @@ exponent  ([Ee][+-]?[0-9]+)
   if (bVERBOSE) printf ("Inserting initialisation function.\n");
   yyreset();
   yyin = fpGenomeFile;                                                     // switch to .ez file and analyser
+  lineCounter = 1;
   BEGIN COPY_INITIALISATION_FUNCTION;
  }
 
@@ -188,10 +189,14 @@ exponent  ([Ee][+-]?[0-9]+)
 <TEMPLATE_ANALYSIS>"\\INSERT_BEGIN_GENERATION_FUNCTION"  {
   //DEBUG_PRT_PRT("insert beg");
   if (bVERBOSE) printf ("Inserting at the begining of each generation function.\n");
+  if( bLINE_NUM_EZ_FILE )
+    fprintf(fpOutputFile,"#line %d \"%s.ez\"\n",lineCounter+1, sRAW_PROJECT_NAME);
+
   yyreset();
   yyin = fpGenomeFile;
   bBeginGeneration = true;
   bEndGeneration = false;
+  lineCounter = 1;
   BEGIN COPY_BEG_GENERATION_FUNCTION;
  }
 
@@ -559,6 +564,7 @@ exponent  ([Ee][+-]?[0-9]+)
   yyreset();
   yyin = fpGenomeFile;
   if (bVERBOSE) printf ("Evaluation population in a single function!!.\n");
+  lineCounter = 1;
   BEGIN COPY_INSTEAD_EVAL;
  }
 
@@ -900,6 +906,7 @@ exponent  ([Ee][+-]?[0-9]+)
 <TEMPLATE_ANALYSIS>"\\INSERT_INITIALISER"  {        
   yyreset();
   yyin = fpGenomeFile;                                                     // switch to .ez file and analyser
+  lineCounter = 1;
   BEGIN COPY_INITIALISER;   
  }
 
@@ -907,6 +914,7 @@ exponent  ([Ee][+-]?[0-9]+)
   if (bVERBOSE) printf ("Inserting Finalization function.\n");
   yyreset();
   yyin = fpGenomeFile;                                                     // switch to .ez file and analyser
+  lineCounter=1;
   BEGIN COPY_FINALIZATION_FUNCTION;
  }
 
@@ -1281,9 +1289,11 @@ if(OPERATING_SYSTEM=WINDOWS)
  }
 
 <COPY_INITIALISATION_FUNCTION>"\\Before"[ \t\n]+"everything"[ \t\n]+"else"[ \t\n]+"function"[ \t\n]*":" {
-    fprintf (fpOutputFile,"// Initialisation function\nvoid EASEAInitFunction(int argc, char *argv[]){");
+    fprintf (fpOutputFile,"// Initialisation function\nvoid EASEAInitFunction(int argc, char *argv[]){\n");
   bFunction=1; bInitFunction=1;
-      
+  if( bLINE_NUM_EZ_FILE )
+    fprintf(fpOutputFile,"#line %d \"%s.ez\"\n",lineCounter, sRAW_PROJECT_NAME);
+  
   BEGIN COPY;
  }
 <COPY_INITIALISATION_FUNCTION><<EOF>> {bInitFunction=0; // No before everything else function was found in the .ez file
@@ -1291,16 +1301,21 @@ if(OPERATING_SYSTEM=WINDOWS)
   fprintf(fpOutputFile,"\n// No before everything else function.\n");
   rewind(fpGenomeFile);
   yyin = fpTemplateFile;
+
   BEGIN TEMPLATE_ANALYSIS;
   bNotFinishedYet=1;
  }
-<COPY_INITIALISATION_FUNCTION>.|\n {}                                      
+<COPY_INITIALISATION_FUNCTION>. {}                                      
+<COPY_INITIALISATION_FUNCTION>\n {lineCounter++;} 
 
 //****************************************
 //  Easea GPGPU & EO Finalization function
 //****************************************
 <COPY_FINALIZATION_FUNCTION>"\\After"[ \t\n]+"everything"[ \t\n]+"else"[ \t\n]+"function"[ \t\n]*":" {
-  fprintf (fpOutputFile,"// Finalization function\nvoid EASEAFinalization(CPopulation* population){");
+  fprintf (fpOutputFile,"// Finalization function\nvoid EASEAFinalization(CPopulation* population){\n");
+  if( bLINE_NUM_EZ_FILE )
+    fprintf(fpOutputFile,"#line %d \"%s.ez\"\n",lineCounter, sRAW_PROJECT_NAME);
+
   bFunction=1; bFinalizationFunction=1;
   BEGIN COPY;
  }
@@ -1313,7 +1328,8 @@ if(OPERATING_SYSTEM=WINDOWS)
   BEGIN TEMPLATE_ANALYSIS;
   bNotFinishedYet=1;
  }
-<COPY_FINALIZATION_FUNCTION>.|\n {}                                      
+<COPY_FINALIZATION_FUNCTION>. {}                                      
+<COPY_FINALIZATION_FUNCTION>\n {lineCounter++;}                                      
 
 
 <COPY_END_GENERATION_FUNCTION>"\\At"[ \t\n]+"the"[ \t\n]+"end"[ \t\n]+"of"[ \t\n]+"each"[ \t\n]+"generation"[ \t\n]+"function"[ \t\n]*":" {
@@ -1347,6 +1363,8 @@ if(OPERATING_SYSTEM=WINDOWS)
     bFunction=1;
     bBeginGeneration = 0;
     bBeginGenerationFunction = 1;
+    if( bLINE_NUM_EZ_FILE )
+      fprintf(fpOutputFile,"#line %d \"%s.ez\"\n",lineCounter, sRAW_PROJECT_NAME);
     BEGIN COPY_USER_GENERATION;
   }
  }
@@ -1356,11 +1374,15 @@ if(OPERATING_SYSTEM=WINDOWS)
   if( (TARGET==CUDA || TARGET==STD)){
     fprintf (fpOutputFile,"{\n");
     bFunction=1;
+    if( bLINE_NUM_EZ_FILE )
+    fprintf(fpOutputFile,"#line %d \"%s.ez\"\n",lineCounter, sRAW_PROJECT_NAME);
+
     BEGIN COPY_USER_GENERATION;
   }
  }
 
-<COPY_INSTEAD_EVAL>.|\n {}                                      
+<COPY_INSTEAD_EVAL>. {}                                      
+<COPY_INSTEAD_EVAL>\n {lineCounter++;}                                      
 
 <COPY_INSTEAD_EVAL><<EOF>> {
   bBeginGenerationFunction=0; // No Generation function was found in the .ez file
@@ -1384,7 +1406,8 @@ if(OPERATING_SYSTEM=WINDOWS)
   BEGIN TEMPLATE_ANALYSIS;
   bNotFinishedYet=1;
  }
-<COPY_BEG_GENERATION_FUNCTION>.|\n {}                                      
+<COPY_BEG_GENERATION_FUNCTION>\n {lineCounter++;}
+<COPY_BEG_GENERATION_FUNCTION>. {}
 
 
 

Makefile

@@ -18,7 +18,7 @@ ifeq ($(UNAME), Darwin)
 	@echo "export EZ_PATH=\"$(PWD)/\"">>$(HOME)/.profile
 else
 	echo "this one"
-	@if [ $(EZ_PATH) != $(PWD)/ ] ; then echo -e "\nexport EZ_PATH=$(PWD)/">>$(HOME)/.bashrc ; fi
+	@if [ -z "$(EZ_PATH)" -a "$(EZ_PATH)" != $(PWD)/ ] ; then echo "\nexport EZ_PATH=$(PWD)/">>$(HOME)/.bashrc ; fi
 endif
 	#
 	# Congratulations !  It looks like you compiled EASEA successfully.

dev/c4.5/card.ez

-/*_________________________________________________________
-
-Test functions
-log normal adaptive mutation
-Selection operator: Tournament
-__________________________________________________________*/
-
-
-\User functions:
-\end
-
-\At the beginning of each generation function:
-\end
-
-\At the end of each generation function:
-\end
-
-\At each generation before reduce function:
-\end
-
-\GenomeClass::display:
-\end
-
-
-\User declarations :
-#include <base.h>
-#include <genome.h>
-#include <tree.h>
-#include <omp.h>
-
-
-#define X_MIN -1.
-#define X_MAX 1.
-#define ITER 120      
-#define Abs(x) ((x) < 0 ? -(x) : (x))
-#define MAX(x,y) ((x)>(y)?(x):(y))
-#define MIN(x,y) ((x)<(y)?(x):(y))
-#define SIGMA  1.                     /*  mutation parameter */
-#define PI 3.141592654
-
-#define G_SIZE 96 // fixme this size is defined in genome.h as GENOME_SIZE
-
- 
-float pMutPerGene=0.15;
-float pMutDesCard = 0.1;
-
-struct base* train_table = NULL;
-struct base* car_table = NULL;
-
-
-float* uniq_instances[2];
-unsigned uniq_cnt[2];
-
-
-
-\end
-
-\User classes :
-GenomeClass { 
-  float x[G_SIZE];
-}
-\end
-
-
-\Before everything else function:
-{
-  INSTEAD_EVAL_STEP = true;
-
-  cout << "Seed : " << globalRandomGenerator->get_seed() << endl;
-
-  //cout<<"Before everything else function called "<<endl;
-  train_table = ba_postgres_load_train();
-  car_table = ba_postgres_load_car();
-  ba_set_links(train_table,car_table);
-
-  ba_mix_instances(train_table);
-  //ba_print_db(train_table);
-  
-  uniq_instances[0] = ba_compute_uniq_values(car_table, 1, uniq_cnt+0);
-  uniq_instances[1] = ba_compute_uniq_values(car_table, 2, uniq_cnt+1);
-
-  printf("%d %d\n",uniq_cnt[0],uniq_cnt[1]);
-
-  for( unsigned i=0 ; i<uniq_cnt[0] ; i++ ){
-    printf("%f,",uniq_instances[0][i]);
-  }
-  printf("\n");
-
-  for( unsigned i=0 ; i<uniq_cnt[1] ; i++ ){
-    printf("%f,",uniq_instances[1][i]);
-  }
-  printf("\n");
-
-}
-\end
-
-\After everything else function:
-{
-
-  EA->population->sortParentPopulation();
-  IndividualImpl* best = (IndividualImpl*)EA->population->parents[0];
-    
-  printf("best fitness %f\n",best->evaluate());
-  for( unsigned i=0 ; i<G_SIZE ; i+=3 ){
-    printf("%f %f >= %f\n",best->x[i],best->x[i+1],best->x[i+2]);
-  }
-  printf("\n");
-
-  
-
-  cTreeNode* root = generate_tree(best->x,train_table,car_table);
-  struct base* tmp_table = table_from_genome(best->x,train_table,car_table);
-  show_tree(tmp_table,root);
-
-  struct base* tmp_learning_table, * tmp_test_table; // fixme
-
-  tmp_learning_table = (struct base*)malloc(sizeof(*tmp_learning_table));
-  tmp_test_table = (struct base*)malloc(sizeof(*tmp_test_table));
-  printf("depth of resulting tree %d\n",root->tree_depth());
-
-#if 0
-  // prepare learning and test table.
-  tmp_test_table->hdr = tmp_learning_table->hdr = tmp_table->hdr; // affect tmp hdr to every table.
-
-  tmp_learning_table->no_instances =  (unsigned)(tmp_table->no_instances*(2.f/3));
-  tmp_test_table->no_instances = (unsigned)(tmp_table->no_instances*(1./3));
-
-  tmp_learning_table->instances = new float*[tmp_learning_table->no_instances];
-  tmp_test_table->instances = new float*[tmp_test_table->no_instances];
-
-  memcpy(tmp_learning_table->instances,tmp_table->instances,
-	 sizeof(*tmp_learning_table->instances)*tmp_learning_table->no_instances);
-  
-  memcpy(tmp_test_table->instances,tmp_learning_table->no_instances+tmp_table->instances,
-	 sizeof(*tmp_learning_table->instances)*tmp_test_table->no_instances);
-
-  for( unsigned i=0 ; i<tmp_test_table->no_instances ; i++ ){
-    unsigned predicted_class = root->classify_instance(tmp_test_table->instances[i]);
-    unsigned real_class = (unsigned)tmp_test_table->instances[i][tmp_test_table->hdr->whichis_class];
-    printf("%d - %d\n",predicted_class,real_class);
-  }
-#endif
-
-  
-  delete root;
-  ba_delete( tmp_table );
-}
-\end
-
-\GenomeClass::initialiser : 
-{
-  for( unsigned i=0; i<G_SIZE ; i+=3 ) {
-    //Genome.x[i] = random(0,101);
-    //Genome.x[i+1] = random(0,101);
-    //Genome.x[i] = car_table->hdr->attributes[1]->threshold[random(0,car_table->hdr->attributes[1]->no_threshold)];
-    //Genome.x[i+1] = car_table->hdr->attributes[2]->threshold[random(0,car_table->hdr->attributes[2]->no_threshold)];
-    Genome.x[i] = car_table->instances[random(0,car_table->no_instances)][i+1];
-    Genome.x[i+1] = car_table->instances[random(0,car_table->no_instances)][i+2];
-
-    if( tossCoin(pMutDesCard))
-      Genome.x[i+2] = 0;
-    else
-      Genome.x[i+2] = random(1,11);
-  }
-}
-\end
-
-\GenomeClass::crossover :
-{
-  for (int i=0; i<G_SIZE; i++){
-    if( tossCoin(0.5) )
-      child.x[i] = parent1.x[i];
-    else
-      child.x[i] = parent2.x[i];
-  }
-}
-\end
-
-\GenomeClass::mutator : // Must return the number of mutations
-{
-  int NbMut=0;
-  for (int i=0; i<G_SIZE; i+=GENE_SIZE){
-    // mutate the cardinality
-    if( tossCoin(pMutPerGene) ){
-      if( tossCoin(pMutDesCard) ){
-	Genome.x[i+GENE_SIZE-1] = 0;
-	NbMut++;
-
-      }
-      else{
-	float value = random_gauss(Genome.x[GENE_SIZE*i+GENE_SIZE-1],2);
-	value = (value<0 ? 0 : value); //if value less than 0, then value is 0
-	value = (value>10 ? 10 :value); // if value grether than 10 then value is 10
-	
-	Genome.x[i+GENE_SIZE-1] = roundf(value);
-	NbMut++;
-
-      }
-    }
-
-    for( unsigned j=0 ; j<GENE_SIZE-1 ; j++ ){
-      if( tossCoin(pMutPerGene) ){
-	//Genome.x[i+j] = car_table->instances[random(0,car_table->no_instances)][j+1];
-	//Genome.x[i+j] = car_table->hdr->attributes[j+1]->threshold[random(0,car_table->hdr->attributes[j+1]->no_threshold)];
-	
-	
-	float value = random_gauss(Genome.x[i+j],2);
-	//value = (value<0 ? 0 : value); //if value less than 0, then value is 0
-	//value = (value>101 ? 101 :value); // if value grether than 10 then value is 10
-	//Genome.x[i+j] = value;
-
-	Genome.x[i+j] = ba_nearest_greather_table_value(car_table,j+1,value);
-	NbMut++;
-      }
-    } // for each threshold
-    
-  }// for each gene
-  return NbMut;
-}
-\end
-
-// The population evaluation.
-\Instead evaluation function: 
-{
-  ba_mix_instances(train_table);
-
-#pragma omp parallel for
-    for( unsigned i=0 ; i<popSize ; i++ ){
-      population[i]->evaluate();
-    }
-}
-\end
-
-\GenomeClass::evaluator : // Returns the score
-{
-  struct base* tmp_table = table_from_genome(Genome.x,train_table,car_table);
-  struct base* tmp_learning_table, * tmp_test_table; // fixme
-
-  float fitness_value = 0;
-
-  tmp_learning_table = (struct base*)malloc(sizeof(*tmp_learning_table));
-  tmp_test_table = (struct base*)malloc(sizeof(*tmp_test_table));
-
-  // prepare learning and test table.
-  tmp_test_table->hdr = tmp_learning_table->hdr = tmp_table->hdr; // affect tmp hdr to every table.
-
-  tmp_learning_table->no_instances =  (unsigned)(tmp_table->no_instances*(2.f/3));
-  tmp_test_table->no_instances = (unsigned)(tmp_table->no_instances*(1./3));
-
-  tmp_learning_table->instances = new float*[tmp_learning_table->no_instances];
-  tmp_test_table->instances = new float*[tmp_test_table->no_instances];
-  
-
-  memcpy(tmp_learning_table->instances,tmp_table->instances,
-	 sizeof(*tmp_learning_table->instances)*tmp_learning_table->no_instances);
-  
-  memcpy(tmp_test_table->instances,tmp_learning_table->no_instances+tmp_table->instances,
-	 sizeof(*tmp_learning_table->instances)*tmp_test_table->no_instances);
-  
-  cTreeNode* t = genereate_decision_tree(tmp_learning_table);
-  
-  for( unsigned i=0 ; i<tmp_test_table->no_instances ; i++ ){
-    unsigned predicted_class = t->classify_instance(tmp_test_table->instances[i]);
-    unsigned real_class = (unsigned)tmp_test_table->instances[i][tmp_test_table->hdr->whichis_class];
-
-    // here compute classification error, or any quality measurment
-    if( predicted_class!=real_class ){
-      fitness_value++;
-    }
-  }
-
-  fitness_value += ((float)t->tree_depth());
-  delete t;
-
-  delete[] tmp_learning_table->instances;
-  delete[] tmp_test_table->instances;
-  free( tmp_learning_table );
-  free( tmp_test_table );
-  ba_delete(tmp_table);
-  
-  return fitness_value;
-}
-\end
-
-\User Makefile options: 
-CXXFLAGS+=-I/home/maitre/sources/c4.5/include/ -fopenmp -O3 -pg
-LDFLAGS+= -lpq  -O3 -lm  -fopenmp libc45.a -pg
-\end
-
-\Default run parameters :        // Please let the parameters appear in this order
-  Number of generations : 100     	// NB_GEN
-  Time limit: 0 			// In seconds, 0 to deactivate
-  Population size : 100			//POP_SIZE
-  Offspring size : 100 // 40% 
-  Mutation probability : 0       // MUT_PROB
-  Crossover probability : 1      // XOVER_PROB
-  Evaluator goal : minimise      // Maximise
-  Selection operator: Tournament 2.0
-  Surviving parents: 100%//percentage or absolute  
-  Surviving offspring: 100%
-  Reduce parents operator: Tournament 2
-  Reduce offspring operator: Tournament 2
-  Final reduce operator: Tournament 2
-
-  Elitism: Strong			//Weak or Strong
-  Elite: 1
-  Print stats:1				//Default: 1
-  Generate csv stats file:0			
-  Generate gnuplot script:0
-  Generate R script:0
-  Plot stats:0				//Default: 0
-\end
-	

dev/c4.5_geo/card.ez

@@ -36,10 +36,10 @@ __________________________________________________________*/
 
 #define K 5
 #define GENE_SIZE 4
-#define GENOME_SIZE 32
+#define GENOME_SIZE 128
 
  
-float pMutPerGene=0.1;
+float pMutPerGene=0.01;
 float pMutDesCard = 0.05;
 float pMutDesThre = 0.5;
 
@@ -69,9 +69,10 @@ GenomeClass {
   cout << "Seed : " << globalRandomGenerator->get_seed() << endl;
   srand(globalRandomGenerator->get_seed());
 
-  t1 = ba_postgres_load_ilot(1);
-  t2 = ba_postgres_load_batiment(1);
+  t1 = ba_postgres_load_ilot(2);
+  t2 = ba_postgres_load_batiment(2);
   ba_set_links(t1,t2);
+  //ba_print_links(t1);
   
   //printf("+ %d - %d\n",t1->class_repartition[1],t1->class_repartition[0]);
   for( unsigned i=0 ; i<t1->hdr->attributes[t1->hdr->whichis_class]->no_values; i++ )
@@ -79,14 +80,14 @@ GenomeClass {
   
   uniq_instances[0] = ba_compute_uniq_values(t2, 1, uniq_cnt+0);
   uniq_instances[1] = ba_compute_uniq_values(t2, 2, uniq_cnt+1);
-
+  
   printf("%d %d\n",uniq_cnt[0],uniq_cnt[1]);
 
   // allocating K packets 
   generate_k_fold(K,packets_size,t1,k_tables);
+  
 
-
-#if 1
+#if 0
   // try the perfect solution
   IndividualImpl* i = new IndividualImpl();
   i->x[0] = 30;
@@ -104,7 +105,7 @@ GenomeClass {
   
   show_tree(tc,t,0);
 #endif
-  exit(-1);
+  //exit(-1);
 
 }
 \end
@@ -143,7 +144,6 @@ GenomeClass {
   printf(" error on the whole set : %d\n",error);
 #endif
 
-  
   delete root;
   ba_delete( tmp_table );
 }
@@ -153,11 +153,11 @@ GenomeClass {
 {
   for( unsigned i=0; i<GENOME_SIZE ; i+=GENE_SIZE ) {
     
-    Genome.x[i] = random(9,11364);
-    Genome.x[i+1] = random(77,999);
-    Genome.x[i+2] = random(569,1000);
+    Genome.x[i] = random(9.,11364.);
+    Genome.x[i+1] = random(77.,999.);
+    Genome.x[i+2] = random(569.,1000.);
     
-    Genome.x[i+GENE_SIZE-1] = random(0,5);
+    Genome.x[i+GENE_SIZE-1] = roundf(random(0.,10.));
   }
 }
 \end
@@ -206,15 +206,31 @@ GenomeClass {
     for( unsigned j=0 ; j<GENE_SIZE-1 ; j++ ){
       if( tossCoin(pMutPerGene) ){
 	if( tossCoin(pMutDesThre) ){
-	  Genome.x[i+j] = INFINITY;
+	  	  Genome.x[i+j] = INFINITY;
 	}
 	else{
+	  float value;
 	  if( __isinf(Genome.x[i+j]) ) Genome.x[i+j] = random(0,1000);
-	  float value = random_gauss(Genome.x[i+j],10);
-	  Genome.x[i+j] = roundf(value);
-	  //value = ba_nearest_table_value(t2,j+1,value);
+	  switch(j){
+	  case 0:
+	    value = random_gauss(Genome.x[i+j],100);
+	    Genome.x[i+j] = roundf(value);
+	    Genome.x[i+j] = ba_nearest_table_value(t2,j+1,value);
+	    break;
+	  case 1:
+	    value = random_gauss(Genome.x[i+j],20);
+	    Genome.x[i+j] = roundf(value);
+	    Genome.x[i+j] = ba_nearest_table_value(t2,j+1,value);
+	    break;
+	  case 2:
+	    value = random_gauss(Genome.x[i+j],10);
+	    Genome.x[i+j] = roundf(value);
+	    Genome.x[i+j] = ba_nearest_table_value(t2,j+1,value);
+	    break;	    
+	  }
+	  //}
+	  NbMut++;
 	}
-	NbMut++;
       }
     } // for each threshold
     
@@ -331,7 +347,7 @@ GenomeClass {
     
   }
 
-  fitness_value = (((float)error) / t1->no_instances)*100;// + ((float)tree_size)/K;
+  fitness_value = (((float)error) / t1->no_instances)*100 ;//+ ((float)tree_size)/K;
   
   for( unsigned i=0 ; i<K ; i++ ){
     ba_delete(k_tmp_tables[i]);
@@ -346,14 +362,14 @@ LDFLAGS+= -lpq  -lm  -fopenmp ../c4.5_common/libc45.a
 \end
 
 \Default run parameters :        // Please let the parameters appear in this order
-  Number of generations : 100     	// NB_GEN
+  Number of generations : 200     	// NB_GEN