Added to workflow function to create and save pos/neg data for each r…

…epitition and remove any pos/neg files not being used. Can either give files to run as repititions or generate all new pos/neg files.

classes/hypergeometric_distribution_class.py

@@ -31,6 +31,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         """
         Uses a Hypergeometric distribution to calculate a confidence value for the relationship between a protein of 
@@ -54,7 +55,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
 
         i = 1

classes/hypergeometric_distribution_class_V2.py

@@ -31,6 +31,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         """
         Uses a Hypergeometric distribution to calculate a confidence value for the relationship between a protein of 
@@ -54,7 +55,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
 
         i = 1

classes/overlapping_neighbors_class.py

@@ -30,6 +30,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         """
         evaluate overlapping neighbors method on a protein protein interaction network with go term annotation.
@@ -53,7 +54,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
         i = 1
         for positive_protein, positive_go, negative_protein, negative_go in zip(

classes/overlapping_neighbors_v2_class.py

@@ -28,6 +28,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         """
         evaluate overlapping neighbors method on a protein protein interaction network with go term annotation.
@@ -50,7 +51,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
 
         G = import_graph_from_pickle(graph_file_path)
         i = 1

classes/overlapping_neighbors_v3_class.py

@@ -28,6 +28,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         """
         evaluate overlapping neighbors method on a protein protein interaction network with go term annotation.
@@ -51,7 +52,7 @@ def predict(
         }
         i = 1
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
 
         for positive_protein, positive_go, negative_protein, negative_go in zip(

classes/protein_degree_class.py

@@ -31,6 +31,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         colorama_init()
         data = {
@@ -41,7 +42,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
 
         i = 1

classes/protein_degree_v2_class.py

@@ -35,6 +35,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         data = {
             "protein": [],
@@ -44,7 +45,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
         i = 1
         for positive_protein, positive_go, negative_protein, negative_go in zip(

classes/protein_degree_v3_class.py

@@ -36,6 +36,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_path,
+        rep_num,
     ):
         data = {
             "protein": [],
@@ -45,7 +46,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
         i = 1
         for positive_protein, positive_go, negative_protein, negative_go in zip(

classes/sample_algorithm.py

@@ -31,6 +31,7 @@ def predict(
         input_directory_path,
         graph_file_path,
         output_data_directory,
+        rep_num,
     ):
         """
         evaluate a random approach method on a protein protein interaction network with go term annotation.
@@ -44,7 +45,7 @@ def predict(
             "true_label": [],
         }
 
-        positive_dataset, negative_dataset = get_datasets(input_directory_path)
+        positive_dataset, negative_dataset = get_datasets(input_directory_path, rep_num)
         G = import_graph_from_pickle(graph_file_path)
 
         i = 1

main.py

@@ -48,6 +48,8 @@ def main():
     dataset_directory_path = Path("./output/dataset")
     graph_file_path = Path(dataset_directory_path, "graph.pickle")
     sample_size = 1000
+    repeats = 5
+    new_random_lists = False
 
     testing_output_data_path = Path("./output/data/")
     testing_output_image_path = Path("./output/images/")
@@ -85,8 +87,6 @@ def main():
         "HypergeometricDistributionV2": HypergeometricDistributionV2,
     }
 
-    repeats = 20
-
     run_workflow(
         algorithm_classes,
         go_protein_pairs,
@@ -97,6 +97,7 @@ def main():
         output_data_path,
         output_image_path,
         repeats,
+        new_random_lists,
     )
 
     sys.exit()