Update app.py

app.py

@@ -130,6 +130,10 @@ LOS_PATH = "images_LoS"
 percentage_values_los = np.linspace(0.001, 1, 20) * 100  # 20 percentage values
 
 # Function to compute confusion matrix and plot it
+from sklearn.metrics import f1_score
+import seaborn as sns
+
+# Function to compute confusion matrix, F1-score and plot it with dark mode style
 def plot_confusion_matrix_from_csv(csv_file_path, title, save_path):
     # Load CSV file
     data = pd.read_csv(csv_file_path)
@@ -141,27 +145,29 @@ def plot_confusion_matrix_from_csv(csv_file_path, title, save_path):
     # Compute confusion matrix
     cm = confusion_matrix(y_true, y_pred)
     
-    # Plot the confusion matrix
+    # Compute F1-score
+    f1 = f1_score(y_true, y_pred, average='macro')  # Macro-average F1-score
+    
+    # Set dark mode styling
+    plt.style.use('dark_background')
     plt.figure(figsize=(5, 5))
-    plt.imshow(cm, interpolation='nearest', cmap='Blues')
-    plt.title(title)
-    plt.colorbar()
-    plt.xticks([0, 1], labels=['Class 0', 'Class 1'])
-    plt.yticks([0, 1], labels=['Class 0', 'Class 1'])
     
-    # Annotate the confusion matrix
-    thresh = cm.max() / 2
-    for i in range(cm.shape[0]):
-        for j in range(cm.shape[1]):
-            plt.text(j, i, format(cm[i, j], 'd'), ha="center", va="center", 
-                     color="white" if cm[i, j] > thresh else "black")
+    # Plot the confusion matrix with a dark-mode compatible colormap
+    sns.heatmap(cm, annot=True, fmt="d", cmap="magma", cbar=False, annot_kws={"size": 12}, linewidths=0.5, linecolor='white')
     
-    plt.ylabel('True label')
-    plt.xlabel('Predicted label')
+    # Add F1-score to the title
+    plt.title(f"{title} (F1 Score: {f1:.3f})", color="white", fontsize=14)
+    
+    # Customize tick labels for dark mode
+    plt.xticks([0.5, 1.5], labels=['Class 0', 'Class 1'], color="white", fontsize=10)
+    plt.yticks([0.5, 1.5], labels=['Class 0', 'Class 1'], color="white", fontsize=10)
+    
+    plt.ylabel('True label', color="white", fontsize=12)
+    plt.xlabel('Predicted label', color="white", fontsize=12)
     plt.tight_layout()
     
     # Save the plot as an image
-    plt.savefig(save_path)
+    plt.savefig(save_path, transparent=True)  # Use transparent to blend with the dark mode website
     plt.close()
     
     # Return the saved image
@@ -473,7 +479,8 @@ with gr.Blocks(css="""
         choice_radio = gr.Radio(choices=["Use Default Dataset", "Upload Dataset"], label="Choose how to proceed", value="Use Default Dataset")
         
         # 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=[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")
 
         # 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)