From 6600a0e7d5d629b8ece211b3d8cff56cdab099b2 Mon Sep 17 00:00:00 2001
From: George Marchment <georgemarchment@yahoo.fr>
Date: Mon, 14 Apr 2025 13:54:37 +0200
Subject: [PATCH] Added function to get the most uniform selction of clusters
---
src/workflow.py | 43 ++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 42 insertions(+), 1 deletion(-)
diff --git a/src/workflow.py b/src/workflow.py
index 4948649..0e156e0 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -469,11 +469,52 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
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):
+ 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
+ #reduction_beta is the maximum number of clusters depending on the number of processes given in a percentage
+ #For example if there are 10 processes and reduction_beta = 0.8 -> we want a maximum of 8 clusters
+ #In the same idea if reduction_beta = 0.6 -> we want a maximum of 6 clusters
+ #reduction_alpha is the same as above
+ def get_relevant_processes_which_uniformizes_cluster_distribution(self, reduction_alpha = 0.2, reduction_beta = 0.8, number_of_tries = 50):
+ import numpy as np
+ min_uniform_score, 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()
+ clusters_2_size = []
+ for c in clusters:
+ nb_processes = 0
+ for ele in c:
+ if(ele.get_type()=="Process"):
+ nb_processes+=1
+ clusters_2_size.append(nb_processes)
+ score = 0
+ average = np.mean(clusters_2_size)
+ for x in clusters_2_size:
+ score += ((average-x)/average)**2
+ if(len(clusters)>=reduction_alpha*len(self.get_processes_called()) and
+ len(clusters)<=reduction_beta*len(self.get_processes_called()) and
+ score<min_uniform_score):
+ min_relevant_processes = random_relevant_processes
+ min_uniform_score = score
+ return min_relevant_processes
+
+
#Method that returns the order of execution for each executor
def get_order_execution_executors(self):
dico = {}
--
GitLab