Update app.py

app.py

@@ -176,8 +176,8 @@ def plot_confusion_matrix_from_csv(csv_file_path, title, save_path):
     return Image.open(save_path)
 
 # Function to load confusion matrix based on percentage and input_type
-def display_confusion_matrices_los(percentage_idx):
-    percentage = percentage_values_los[percentage_idx]
+def display_confusion_matrices_los(percentage):
+    #percentage = percentage_values_los[percentage_idx]
     
     # Construct folder names
     raw_folder = os.path.join(LOS_PATH, f"raw_{percentage/100:.3f}_los_noTraining")
@@ -200,13 +200,13 @@ def display_confusion_matrices_los(percentage_idx):
     return raw_img, embeddings_img
 
 # Main function to handle user choice
-def handle_user_choice(choice, percentage_idx=None, uploaded_file=None):
+def handle_user_choice(choice, percentage=None, uploaded_file=None):
     if choice == "Use Default Dataset":
-        raw_img, embeddings_img = display_confusion_matrices_los(percentage_idx)
+        raw_img, embeddings_img = display_confusion_matrices_los(percentage)
         return raw_img, embeddings_img, ""  # Return empty string for console output
     elif choice == "Upload Dataset":
         if uploaded_file is not None:
-            raw_img, embeddings_img, console_output = process_hdf5_file(uploaded_file, percentage_idx)
+            raw_img, embeddings_img, console_output = process_hdf5_file(uploaded_file, percentage)
             return raw_img, embeddings_img, console_output
         else:
             return "Please upload a dataset", "Please upload a dataset", ""  # Return empty string for console output
@@ -227,8 +227,8 @@ class PrintCapture(io.StringIO):
         return ''.join(self.output)
 
 # Function to load and display predefined images based on user selection
-def display_predefined_images(percentage_idx):
-    percentage = percentage_values_los[percentage_idx]
+def display_predefined_images(percentage):
+    #percentage = percentage_values_los[percentage_idx]
     raw_image_path = os.path.join(RAW_PATH, f"percentage_{percentage}_complexity_16.png")
     embeddings_image_path = os.path.join(EMBEDDINGS_PATH, f"percentage_{percentage}_complexity_16.png")
     
@@ -245,12 +245,12 @@ def display_predefined_images(percentage_idx):
 
     return raw_image, embeddings_image
 
-def los_nlos_classification(file, percentage_idx):
+def los_nlos_classification(file, percentage):
     if file is not None:
-        raw_cm_image, emb_cm_image, console_output = process_hdf5_file(file, percentage_idx)
+        raw_cm_image, emb_cm_image, console_output = process_hdf5_file(file, percentage)
         return raw_cm_image, emb_cm_image, console_output  # Returning all three: two images and console output
     else:
-        raw_image, embeddings_image = display_predefined_images(percentage_idx)
+        raw_image, embeddings_image = display_predefined_images(percentage)
         return raw_image, embeddings_image, ""  # Return an empty string for console output when no file is uploaded
 
 # Function to create random images for LoS/NLoS classification results
@@ -268,10 +268,10 @@ def load_module_from_path(module_name, file_path):
     return module
 
 # Function to split dataset into training and test sets based on user selection
-def split_dataset(channels, labels, percentage_idx):
-    percentage = percentage_values_los[percentage_idx] / 100
+def split_dataset(channels, labels, percentage):
+    #percentage = percentage_values_los[percentage_idx] / 100
     num_samples = channels.shape[0]
-    train_size = int(num_samples * percentage)
+    train_size = int(num_samples * percentage/100)
     print(f'Number of Training Samples: {train_size}')
     
     indices = np.arange(num_samples)
@@ -330,14 +330,15 @@ def plot_confusion_matrix(y_true, y_pred, title):
     plt.savefig(f"{title}.png")
     return Image.open(f"{title}.png")
 
-def identical_train_test_split(output_emb, output_raw, labels, percentage_idx):
+def identical_train_test_split(output_emb, output_raw, labels, percentage):
     N = output_emb.shape[0]  # Get the total number of samples
     
     # Generate the indices for shuffling and splitting
     indices = torch.randperm(N)  # Randomly shuffle the indices
     
     # Calculate the split index
-    split_index = int(N * percentage_values_los[percentage_idx]/100)
+    #percentage = percentage_values_los[percentage_idx]
+    split_index = int(N * percentage/100)
     print(f'Training Size: {split_index}')
     
     # Split indices into train and test
@@ -359,7 +360,7 @@ def identical_train_test_split(output_emb, output_raw, labels, percentage_idx):
 # Store the original working directory when the app starts
 original_dir = os.getcwd()
 
-def process_hdf5_file(uploaded_file, percentage_idx):
+def process_hdf5_file(uploaded_file, percentage):
     capture = PrintCapture()
     sys.stdout = capture  # Redirect print statements to capture
     
@@ -418,12 +419,13 @@ def process_hdf5_file(uploaded_file, percentage_idx):
         print(f"Output Embeddings Shape: {output_emb.shape}")
         print(f"Output Raw Shape: {output_raw.shape}")
 
-        print(f'percentage_idx: {percentage_idx}')
-        print(f'percentage_value: {percentage_values_los[percentage_idx]}')
+        #print(f'percentage_idx: {percentage_idx}')
+        #print(f'percentage_value: {percentage_values_los[percentage_idx]}')
+        print(f'percentage_value: {percentage}')
         train_data_emb, test_data_emb, train_data_raw, test_data_raw, train_labels, test_labels = identical_train_test_split(output_emb.view(len(output_emb),-1),
                                                                                                                              output_raw.view(len(output_raw),-1),
                                                                                                                              labels,
-                                                                                                                             percentage_idx)
+                                                                                                                             percentage)
         
         # Step 8: Perform classification using the Euclidean distance for both raw and embeddings
         print(f'train_data_emb: {train_data_emb.shape}')
@@ -483,11 +485,11 @@ with gr.Blocks(css="""
         # Dropdown for selecting percentage for predefined data
         #percentage_dropdown_los = gr.Dropdown(choices=[f"{value:.3f}" for value in percentage_values_los], value=f"{percentage_values_los[0]:.3f}", label="Percentage of Data for Training")
         #percentage_dropdown_los = gr.Dropdown(choices=list(range(20)), value=0, label="Percentage of Data for Training")
-        percentage_slider_los = gr.Slider(minimum=float(percentage_values_los[0]), 
-                                  maximum=float(percentage_values_los[-1]), 
-                                  step=float(percentage_values_los[1] - percentage_values_los[0]), 
-                                  value=float(percentage_values_los[0]), 
-                                  label="Percentage of Data for Training")
+        #percentage_slider_los = gr.Slider(minimum=float(percentage_values_los[0]), 
+        #                          maximum=float(percentage_values_los[-1]), 
+        #                          step=float(percentage_values_los[1] - percentage_values_los[0]), 
+        #                          value=float(percentage_values_los[0]), 
+        #                         label="Percentage of Data for Training")
 
         # File uploader for dataset (only visible if user chooses to upload a dataset)
         file_input = gr.File(label="Upload HDF5 Dataset", file_types=[".h5"], visible=False)