updated main

src/main.py

@@ -99,21 +99,64 @@ def load_fv(path_to_training_data = os.path.abspath(os.path.join(__file__, "..",
     
     return training_data
 
+
+from concurrent.futures import ProcessPoolExecutor
+output = os.path.abspath(os.path.join(__file__, "..", "output.csv"))
+def process_epoch(input, epoch, all_vectors):
+    """Function to process a single epoch."""
+    l = []
+    for i in range(0, 101):
+        training_set = random.sample(all_vectors, input)
+        testing_set_size = int(input*0.15) # 15% test daten
+        testing_set = random.sample(list(set(all_vectors) - set(training_set)), testing_set_size)
+        
+        # Replace `neural_network` with your actual function
+        correct, false, ammount = neural_network(training_set, testing_set, epoch)
+        #print(f"run {i} for epoch {epoch}: correct_percentage={(correct / ammount) * 100}%")
+        l.append(false / ammount)
+
+    print(f"finished {input} | {epoch}")
+    avg = np.mean(l)
+    with open(output, 'a') as csv_file: 
+        writer = csv.writer(csv_file, delimiter=";", lineterminator="\n")
+        writer.writerow([input, testing_set_size, epoch, avg, l])
+    return avg
+
 if __name__ == "__main__":
     all_vectors = load_fv()
+    with open(output, 'w') as csv_file: 
+        writer =csv.writer(csv_file, delimiter=";", lineterminator="\n")
+        writer.writerow(["num_train_vectors", "num_test_vectors","num_epochs", "epochs_avg", "epochs_results"])
 
-    for input in range(40000, len(all_vectors), 400): 
+    for input in range(1000, int(len(all_vectors)*0.85), 5000):
         inp_res = []
-        for epoch in range(10, 1000, 10):
+        # Use ProcessPoolExecutor for parallelism
-            l = []
+        with ProcessPoolExecutor(max_workers=12) as executor:
-            for test in range(0, 1):
+            # Submit tasks for parallel execution
-                training_set = random.sample(all_vectors, input)
+            futures = [
-                testing_set = list(set(all_vectors)-set(training_set))
+                executor.submit(process_epoch, input, epoch, all_vectors)
+                for epoch in range(1, 21, 1)
+            ]
+            # Collect results as they complete
+            for future in futures:
+                inp_res.append(future.result())
 
-                # print(f"Start for {input} trainingsdata and test number {test} with epoch {epoch}")
+# if __name__ == "__main__":
-                correct, false, ammount = neural_network(training_set, testing_set, epoch)
+#     all_vectors = load_fv()
-                print(f"Epoch {epoch}: correct_percentage={(correct/ammount)*100}%")
-                l.append(false/ammount)
 
-            inp_res.append(np.mean(l))
+#     for input in range(40000, len(all_vectors), 400): 
+#         inp_res = []
+#         for epoch in range(10, 1000, 10):
+#             l = []
+#             multiprocessing.Process
+#             for test in range(0, 1):
+#                 training_set = random.sample(all_vectors, input)
+#                 testing_set = list(set(all_vectors)-set(training_set))
+
+#                 # print(f"Start for {input} trainingsdata and test number {test} with epoch {epoch}")
+#                 correct, false, ammount = neural_network(training_set, testing_set, epoch)
+#                 print(f"Epoch {epoch}: correct_percentage={(correct/ammount)*100}%")
+#                 l.append(false/ammount)
+
+#             inp_res.append(np.mean(l))