Update app.py

app.py

@@ -6,7 +6,7 @@ from PIL import Image
 from tensorflow.keras.models import load_model
 
 # ---------------- Load CSV ----------------
-CSV_PATH = r"C:\Users\Ruchir\Downloads\Wildfire_classification\data\best_models_summary.csv"
+CSV_PATH = "best_models_summary.csv"  # Must be in the same folder
 df = pd.read_csv(CSV_PATH)
 
 # ---------------- Streamlit Page Config ----------------
@@ -37,6 +37,10 @@ h1 {
 .stMarkdown p {
     font-size:16px;
 }
+.stImage>div>div>img {
+    border: 2px solid #ff6f61;
+    border-radius: 10px;
+}
 </style>
 """, unsafe_allow_html=True)
 
@@ -59,16 +63,18 @@ with col2:
 if uploaded_file:
     img = Image.open(uploaded_file).convert('RGB')
     st.image(img, caption='Uploaded Image', use_container_width=True)
-    
+
     # ---------------- Select Model ----------------
     subset = df[df['dataset']==dataset_type]
+
     if metric_priority != "best_overall":
         subset = subset[subset['metric']==metric_priority]
     else:
+        # Best overall: max f1_score
         subset = subset.loc[subset['f1_score'].idxmax():subset['f1_score'].idxmax()+1]
 
     model_row = subset.iloc[0]
-    model_path = r"{}".format(model_row['model_path'])  # ensures backslashes handled
+    model_path = model_row['model_path']
     model_type = model_row['model_type']
 
     st.markdown(f"### Using Model: **{model_row['model_name']}** ({model_type})")
@@ -105,10 +111,13 @@ if uploaded_file:
     # ---------------- Display Results ----------------
     st.markdown("---")
     st.markdown("## Prediction Result")
-    st.success(f"Predicted Class: **{pred}** (class index for now)")
-    st.info(f"Metric Priority: **{metric_priority}**")
-    st.write(f"Model Accuracy: {model_row['accuracy']:.4f} | Precision: {model_row['precision']:.4f} | Recall: {model_row['recall']:.4f} | F1 Score: {model_row['f1_score']:.4f}")
+    if pred is not None:
+        st.success(f"Predicted Class: **{pred}** (class index for now)")
+        st.info(f"Metric Priority: **{metric_priority}**")
+        st.write(f"Model Accuracy: {model_row['accuracy']:.4f} | Precision: {model_row['precision']:.4f} | Recall: {model_row['recall']:.4f} | F1 Score: {model_row['f1_score']:.4f}")
+    else:
+        st.warning("Prediction could not be made. Check model compatibility.")
     
     # Optional style enhancements
     st.markdown("<hr style='border:2px solid #ff6f61'>", unsafe_allow_html=True)
-    st.balloons()
+    st.balloons()