From 30ccf5a8e6d35079dd1b7695d6c936d72c7a0998 Mon Sep 17 00:00:00 2001
From: George Marchment <georgemarchment@yahoo.fr>
Date: Tue, 6 May 2025 16:21:53 +0200
Subject: [PATCH] Added small update
---
src/code_.py | 2 +-
src/constant.py | 2 +-
src/main.py | 2 +-
src/outils_graph.py | 2 +-
src/workflow.py | 24 ++++++++++++++----------
5 files changed, 18 insertions(+), 14 deletions(-)
diff --git a/src/code_.py b/src/code_.py
index e9eb67b..f8f4bb7 100644
--- a/src/code_.py
+++ b/src/code_.py
@@ -157,7 +157,7 @@ class Code:
while(searching and timeout<constant.WHILE_UPPER_BOUND):
searching = False
#TODO -> do the same with flatMap -> 668
- for word in ["map", "flatMap", "view"]:
+ for word in ["map", "flatMap", "view", "ifEmpty"]:
for end_char in ['{', '\(']:
pattern = fr"(\.|\|)\s*"+word+r"\s*"+end_char
for match in re.finditer(pattern, code):
diff --git a/src/constant.py b/src/constant.py
index a5cd310..c88a4e3 100644
--- a/src/constant.py
+++ b/src/constant.py
@@ -21,7 +21,7 @@ LIST_OPERATORS = ["distinct", "filter", "first", "last", "randomSample", "take",
"branch","choice","multiMap","into","separate","tap",
"count","countBy","min","max","sum","toInteger",
"close","dump","ifEmpty","print","println","set","view",
- "map_modified","reduce_modified", "flatMap_modified", "view_modified", #The articifiel operations
+ "map_modified","reduce_modified", "flatMap_modified", "view_modified", "ifEmpty_modified", #The articifiel operations
"empty", "of", "fromPath", "fromList", "subscribe", "value", "from"]#This last line is added by me:)
TOOLS = [
diff --git a/src/main.py b/src/main.py
index 5bfec99..b6514af 100644
--- a/src/main.py
+++ b/src/main.py
@@ -64,7 +64,7 @@ class Main(Nextflow_Building_Blocks):
if(new!=old):
temp = code
code = code.replace(old, new, 1)
- if(temp==code):
+ if(temp==code and old.split()!=new.split()):
print(exe)
print(code)
print("- old", f'"{old}"')
diff --git a/src/outils_graph.py b/src/outils_graph.py
index 303d088..4473d51 100644
--- a/src/outils_graph.py
+++ b/src/outils_graph.py
@@ -1002,7 +1002,7 @@ def relev_user_view_builder(dico_param, relevant_modules, alias_2_tools):
new_nodes[i].sort()
new_name = get_name_new_node(get_names_tab(dico, new_nodes[i]), relevant_modules, tag, alias_2_tools)
name_printed = new_name.split(tag)[0]
- shape = "ellipse"
+ shape = "rectangle"
if(name_printed==""):
shape = "point"
node = {"id": '_$$_'.join(new_nodes[i]).replace('<', '').replace('>', ''),
diff --git a/src/workflow.py b/src/workflow.py
index 4ca2a7c..bce20cb 100644
--- a/src/workflow.py
+++ b/src/workflow.py
@@ -572,16 +572,18 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
import copy
min_score, min_processes = np.inf, []
already_tried = []
- working_workflow = copy.deepcopy(self)
+ #working_workflow = copy.deepcopy(self)
- processes_called = working_workflow.get_processes_called()
+ processes_called = self.get_processes_called()
number_processes_called = len(processes_called)
all_process_as_relevant = []
for p in processes_called:
all_process_as_relevant.append(p.get_alias())
all_process_as_relevant = list(set(all_process_as_relevant))
- working_workflow.rewrite_workflow_remove_subworkflows(relevant_processes = all_process_as_relevant, render_graphs = False)
- w_save = copy.deepcopy(working_workflow)
+ #working_workflow.rewrite_workflow_remove_subworkflows(relevant_processes = all_process_as_relevant, render_graphs = False)
+ #w_save = copy.deepcopy(working_workflow)
+ w_save = copy.deepcopy(self)
+ w = copy.deepcopy(self)
scripts_2_tools = {}
print("Extracting the tools from the processes")
print('-'*len(processes_called)+">")
@@ -597,7 +599,7 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
for i in range(number_of_tries):
print('.', end='')
#print(i/number_of_tries*100)
- w = copy.deepcopy(w_save)
+ #w = copy.deepcopy(w_save)
if(process_pre_selection == "bioinfo"):
random_relevant_processes = w.get_random_relevant_processes_which_use_bioinformatics_tools(scripts_2_tools = scripts_2_tools)
@@ -644,7 +646,7 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
return nb_conditions_in_clusters
- def get_score_from_set_relevant_processes(w_save, random_relevant_processes):
+ def get_score_from_set_relevant_processes(w, random_relevant_processes):
#w = copy.deepcopy(w_save)
#_, cluster_organisation = w.convert_workflow_2_user_view(relevant_processes=random_relevant_processes, render_graphs = False)
#print(random_relevant_processes)
@@ -655,7 +657,7 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
# tab_nb_processes_per_cluster_1.append(cluster_organisation[c]["nb_processes"])
# tab_nb_conditions_per_cluster_1.append(cluster_organisation[c]["nb_conditions"])
- w = copy.deepcopy(w_save)
+ #w = copy.deepcopy(w_save)
w.generate_user_view(relevant_processes = random_relevant_processes, render_graphs=False, use_process_dependency_graph = False)
clusters = w.graph.get_clusters_from_user_view()
cluster_with_processes = []
@@ -671,7 +673,7 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
for cluster in cluster_with_processes:
tab_nb_executors_per_cluster.append(len(cluster))
- print(np.array(tab_nb_executors_per_cluster).sum())
+
#Number condtions per cluster
tab_nb_conditions_per_cluster = get_nb_conditions_in_clusters(cluster_with_processes)
#Number of processes per cluster
@@ -700,10 +702,12 @@ George Marchment, Bryan Brancotte, Marie Schmit, Frédéric Lemoine, Sarah Cohen
average_number_of_process_per_cluster = np.mean(tab_nb_processes_per_cluster)
for x in tab_nb_processes_per_cluster:
uniformity_variance += (average_number_of_process_per_cluster-x)**2/nb_clusters
- dico_results = {"min_nb_clusters":(nb_clusters / number_processes_called), "min_nb_non_relevant_cluster":(nb_non_relevant_clusters / nb_clusters), "uniformity":(uniformity_variance / number_processes_called), "concordance":np.max(np.array(tab_nb_conditions_per_cluster)/np.array(tab_nb_executors_per_cluster)) }
+
+ min_nb_clusters_value = (nb_clusters / number_processes_called)**2
+ dico_results = {"min_nb_clusters":min_nb_clusters_value, "min_nb_non_relevant_cluster":(nb_non_relevant_clusters / nb_clusters), "uniformity":(uniformity_variance / number_processes_called), "concordance":np.max(np.array(tab_nb_conditions_per_cluster)/np.array(tab_nb_executors_per_cluster)) }
score = concordance_factor * np.max(np.array(tab_nb_conditions_per_cluster)/np.array(tab_nb_executors_per_cluster)) + \
uniformity_factor * (uniformity_variance / number_processes_called) + \
- min_nb_clusters_factor * (nb_clusters / number_processes_called) + \
+ min_nb_clusters_factor * min_nb_clusters_value + \
min_nb_non_relevant_cluster_factor * (nb_non_relevant_clusters / nb_clusters)
return score, cluster_with_processes, dico_results
--
GitLab