diff --git a/TP2/selectionMethods/boltzmannSelection.py b/TP2/selectionMethods/boltzmannSelection.py
index 093ad17..573f02b 100644
--- a/TP2/selectionMethods/boltzmannSelection.py
+++ b/TP2/selectionMethods/boltzmannSelection.py
@@ -9,7 +9,6 @@ def __init__(self , T0 , Tc , k):
         self.initialT = T0
         self.finalT = Tc
         self.k = k
-        print("Corre Boltzmann")
 
 
     #Funcion de temperatura dada en clase
@@ -17,13 +16,11 @@ def __temperature(self):
         return self.finalT + (self.initialT - self.finalT) * np.exp( - self.k * self.generation )
         
     def apply(self,selectionIndividuals,targetPopulationSize,replacement=False):
-      #  print(self.__temperature())
         valuedIndividuals = []
         total = 0
         #Por cada individuo calculo su valor (el dividendo de la probabilidad)
         for individual in selectionIndividuals:
             value = np.exp(individual.fitness / self.__temperature())
-            #print("fitness: " + str(individual.fitness) + "value: " + str(value) )
             total += value
             valuedIndividuals.append((value, individual))
 
@@ -34,9 +31,7 @@ def apply(self,selectionIndividuals,targetPopulationSize,replacement=False):
         for valuedIndividual in valuedIndividuals:
             acumulated+= valuedIndividual[0] / total
             promediatedIndividuals.append((acumulated , valuedIndividual[1]))
-           # print("fitness: " + str(valuedIndividual[1].fitness) + "value: " + str(acumulated) )
-            
-       #print("total: " + str(valueAcum) )  
+
         selectedPopulation = []   
         #tiro la ruleta
         for i in range(0 , targetPopulationSize):
diff --git a/TP2/selectionMethods/eliteSelection.py b/TP2/selectionMethods/eliteSelection.py
index d45d185..f530bd1 100644
--- a/TP2/selectionMethods/eliteSelection.py
+++ b/TP2/selectionMethods/eliteSelection.py
@@ -1,6 +1,4 @@
 class  EliteSelection:
-    def __init__(self):
-        print("Hola TOR")
 
     def apply(self,selectionIndividuals,targetPopulationSize,replacement=False):
         #Ordenamos la poblacion por mayor fitness, y retornamos los primeros "targetPopulationSize"
diff --git a/TP2/selectionMethods/rankSelection.py b/TP2/selectionMethods/rankSelection.py
index e781cf5..57c003f 100644
--- a/TP2/selectionMethods/rankSelection.py
+++ b/TP2/selectionMethods/rankSelection.py
@@ -4,9 +4,6 @@
 
 class RankSelection:
 
-    def __init__(self):
-        print("Corre rank")
-
     def apply(self,selectionIndividuals,targetPopulationSize,replacement=False):
         #Ordenamos los individuos por fitness
         rankedIndividuals = sorted(selectionIndividuals,key=lambda x: x.fitness,reverse=True)
diff --git a/TP2/selectionMethods/rouletteSelection.py b/TP2/selectionMethods/rouletteSelection.py
index 66561f3..43572cc 100644
--- a/TP2/selectionMethods/rouletteSelection.py
+++ b/TP2/selectionMethods/rouletteSelection.py
@@ -4,9 +4,6 @@
 
 class RouletteSelection:
 
-    def __init__(self):
-        print("Corre roulette")
-
     def apply(self,selectionIndividuals,targetPopulationSize,replacement=False):
         #Sacamos el fitness total
         #return random.choices(selectionIndividuals , weights=[x.fitness for x in selectionIndividuals] , k=targetPopulationSize )