added function "get_relevant_processes_which_minimize_nb_of_clusters" ->...

added function "get_relevant_processes_which_minimize_nb_of_clusters" -> started adding better ways to select the relevant processes

src/workflow.py

@@ -448,6 +448,32 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
         else:
             raise BioFlowInsightError("Trying to generate random relevant processes however option 'duplicate' is not activated.")
     
+    #The reduction alpha is the minimun number cluster depending on the percentage ofprocesses
+    #For example if there are 10 processes and reduction_alpha = 0.2 -> we want at least 2 clusters
+    #In the same idea if reduction_alpha = 0.4 -> we want at least 4 clusters
+    def get_relevant_processes_which_minimize_nb_of_clusters(self, reduction_alpha = 0.2, number_of_tries = 50):
+        import numpy as np
+        min_nb_clusters, min_relevant_processes = np.inf, []
+        already_tried = []
+        for i in range(number_of_tries):
+            random_relevant_processes = self.generate_random_relevant_processes()
+            escape = 0
+            while(escape<100 and set(random_relevant_processes) in already_tried):
+                escape+=1
+                random_relevant_processes = self.generate_random_relevant_processes()
+            #Cause it means we've already searched the majority of the possibilities
+            if(escape>=100):
+                return min_relevant_processes
+            already_tried.append(set(random_relevant_processes))
+            #Get the clusters and the code
+            self.generate_user_view(relevant_processes = random_relevant_processes, render_graphs=False)
+            clusters = self.graph.get_clusters_from_user_view()
+            #We want the number of clusters to be at least x% of the size of the workflows 
+            if(len(clusters)>=reduction_alpha*len(self.get_processes_called()) and len(clusters)<min_nb_clusters):
+                min_relevant_processes = random_relevant_processes
+                min_nb_clusters = len(clusters)
+        return min_relevant_processes
+
     #Method that returns the order of execution for each executor
     def get_order_execution_executors(self):
         dico = {}