Populate results with mean and std deviation

src/execution.py

@@ -12,41 +12,67 @@ def file_list(path):
     return file_list
 
 
-def create_dataframes(datasets):
-    greedy = DataFrame(columns=["dataset", "distancia"])
-    local = DataFrame(columns=["dataset", "distancia"])
-    greedy["dataset"] = datasets
-    local["dataset"] = datasets
+def create_dataframes():
+    greedy = DataFrame(columns=["dataset", "distancia", "desviacion"])
+    local = DataFrame(columns=["dataset", "distancia", "desviacion"])
     return greedy, local
 
 
 def process_output(results):
-    for line in results:
-        if line.startswith(bytes("Total distance:", encoding="utf-8")):
-            line_elements = line.split(sep=bytes(":", encoding="utf-8"))
-            distance = float(line_elements[1])
-    return distance
+    distances = []
+    for element in results:
+        for line in element:
+            if line.startswith(bytes("Total distance:", encoding="utf-8")):
+                line_elements = line.split(sep=bytes(":", encoding="utf-8"))
+                distances.append(float(line_elements[1]))
+    return distances
+
+
+def populate_dataframes(greedy, local, greedy_list, local_list, dataset):
+    greedy_results = process_output(greedy_list)
+    local_results = process_output(local_list)
+    greedy_dict = {
+        "dataset": dataset,
+        "distancia": mean(greedy_results),
+        "desviacion": std(greedy_results),
+    }
+    local_dict = {
+        "dataset": dataset,
+        "distancia": mean(local_results),
+        "desviacion": std(local_results),
+    }
+    greedy = greedy.append(greedy_dict, ignore_index=True)
+    local = local.append(local_dict, ignore_index=True)
+    return greedy, local
 
 
 def script_execution(filenames, greedy, local, iterations=3):
     script = "src/main.py"
     for dataset in filenames:
+        print(f"Running on dataset {dataset}")
         greedy_list = []
         local_list = []
         for _ in range(iterations):
             greedy_cmd = run(
                 [executable, script, dataset, "greedy"], capture_output=True
             ).stdout.splitlines()
-            greedy_list.append(greedy_cmd)
             local_cmd = run(
                 [executable, script, dataset, "local"], capture_output=True
             ).stdout.splitlines()
+            greedy_list.append(greedy_cmd)
             local_list.append(local_cmd)
-        greedy.loc[greedy["dataset"] == dataset, ["distancia"]] = mean(greedy_list)
-        local.loc[local["dataset"] == dataset, ["distancia"]] = mean(local_list)
+        greedy, local = populate_dataframes(
+            greedy, local, greedy_list, local_list, dataset
+        )
+    return greedy, local
+
+
+def export_results(greedy, local):
+    greedy.to_excel()
+    local.to_excel()
 
 
 if __name__ == "__main__":
     datasets = file_list(path="data/*.txt")
-    greedy, local = create_dataframes(datasets)
-    script_execution(filenames=datasets, greedy=greedy, local=local)
+    greedy, local = create_dataframes()
+    populated_greedy, populated_local = script_execution(datasets, greedy, local)