Update app.py

app.py

@@ -7,13 +7,17 @@ import gradio as gr
 CSV_PATH = "best_models_summary.csv"
 df = pd.read_csv(CSV_PATH)
 
-# ---------------- Generate Compatible Features ----------------
-def generate_features():
-    # Match your model input size (768)
-    return np.random.rand(1, 768).astype(np.float32)
-
 # ---------------- Prediction Function ----------------
-def predict_features(dataset_type, metric_priority):
+def predict_features(uploaded_file, dataset_type, metric_priority):
+
+    try:
+        features = np.load(uploaded_file)  # user uploads .npy feature
+    except Exception as e:
+        return f"❌ Error loading feature file: {e}"
+
+    # Ensure correct shape
+    if len(features.shape) == 1:
+        features = features.reshape(1, -1)
 
     # ---------------- Select Best Model ----------------
     subset = df[df['dataset'] == dataset_type]
@@ -34,9 +38,6 @@ def predict_features(dataset_type, metric_priority):
     except Exception as e:
         return f"❌ Error loading model: {e}"
 
-    # ---------------- Generate Features ----------------
-    features = generate_features()
-
     # ---------------- Prediction ----------------
     try:
         pred = model.predict(features)[0]
@@ -67,15 +68,12 @@ with gr.Blocks(css="""
     .gr-button {background-color: #ff6f61; color:white; font-weight:bold;}
 """) as demo:
 
-    gr.Markdown("<h1>🔥 Wildfire Classification 🔥</h1>")
-    gr.Markdown("Select dataset and metric. The app will automatically choose the best model.")
+    gr.Markdown("<h1>🔥 Wildfire Feature Classification 🔥</h1>")
+    gr.Markdown("Upload a feature vector (.npy file) extracted using Xception.")
 
     with gr.Row():
-        dataset_type = gr.Dropdown(
-            choices=['satellite','uav'], 
-            label="Dataset Type"
-        )
-
+        uploaded_file = gr.File(label="Upload Feature (.npy)", file_types=['.npy'])
+        dataset_type = gr.Dropdown(choices=['satellite','uav'], label="Dataset Type")
         metric_priority = gr.Dropdown(
             choices=['accuracy','precision','recall','f1_score','best_overall'],
             label="Metric Priority"
@@ -87,7 +85,7 @@ with gr.Blocks(css="""
 
     predict_btn.click(
         fn=predict_features,
-        inputs=[dataset_type, metric_priority],
+        inputs=[uploaded_file, dataset_type, metric_priority],
         outputs=output_text
     )