Upload folder using huggingface_hub

backend/main.py

@@ -489,17 +489,41 @@ async def retrain(file: UploadFile = File(...)):
     data_path = '/app/data/patient_dataset.csv' if os.path.exists('/app/data') else '../data/patient_dataset.csv' if os.path.exists('../data') else 'data/patient_dataset.csv'
     os.makedirs(os.path.dirname(data_path), exist_ok=True)
     
-    content = await file.read()
-    with open(data_path, "wb") as f:
-        f.write(content)
-        
     try:
+        content = await file.read()
+        import io
+        new_df = pd.read_csv(io.BytesIO(content))
+        new_df.columns = [c.strip() for c in new_df.columns]
+        
+        if os.path.exists(data_path):
+            existing_df = pd.read_csv(data_path)
+            existing_df.columns = [c.strip() for c in existing_df.columns]
+            
+            # Validate schema
+            required_cols = set(existing_df.columns)
+            provided_cols = set(new_df.columns)
+            
+            if not required_cols.issubset(provided_cols):
+                missing = required_cols - provided_cols
+                return {"error": f"Schema mismatch. Missing columns: {list(missing)}"}
+            
+            # Ensure columns are in the same order and select only necessary ones
+            new_df = new_df[existing_df.columns]
+            
+            # Append data
+            combined_df = pd.concat([existing_df, new_df], ignore_index=True)
+        else:
+            combined_df = new_df
+            
+        # Save validated and combined dataset
+        combined_df.to_csv(data_path, index=False, encoding='utf-8')
+        
         from models import train_models
         await asyncio.to_thread(train_models)
         
         global ensemble_system
         ensemble_system = None
         
-        return {"status": "success", "message": "Ensemble retrained successfully!"}
+        return {"status": "success", "message": f"Dataset updated (now {len(combined_df)} records) and ensemble retrained successfully!"}
     except Exception as e:
-        return {"error": str(e)}
+        return {"error": f"Retraining failed: {str(e)}"}

frontend/pages/5_MLOps_Settings.py

@@ -8,9 +8,25 @@ if "hf.space" in os.getenv("SPACE_ID", ""):
     API_URL = "http://localhost:8000"
 
 st.title("🔄 MLOps & Retraining")
-st.markdown("Dynamically update the TinyML ensemble models by providing a new dataset.")
+st.markdown("Dynamically update the TinyML ensemble models by providing a new dataset. The system uses an **append-only** strategy to maintain data integrity.")
 
-st.info("Upload a CSV file with the standard clinical schema to retrain all models on the fly.")
+with st.expander("📊 Data Submission Guide (Required Schema)", expanded=True):
+    st.markdown("""
+    To ensure the retraining pipeline succeeds, your CSV **must** include the following columns (case-sensitive):
+    
+    1.  **Patient Number**: Unique identifier for the patient.
+    2.  **Heart Rate (bpm)**: Numeric value.
+    3.  **SpO2 Level (%)**: Numeric value.
+    4.  **Systolic Blood Pressure (mmHg)**: Numeric value.
+    5.  **Diastolic Blood Pressure (mmHg)**: Numeric value.
+    6.  **Body Temperature (°C)**: Numeric value.
+    7.  **Fall Detection**: 'Yes' or 'No'.
+    8.  **Predicted Disease**: The target label (e.g., Healthy, Heart Disease).
+    
+    *Note: If you submit a file with a different schema, the system will reject the update to prevent dashboard crashes.*
+    """)
+
+st.info("💡 **Safety Logic:** New data will be validated and appended to the existing dataset. The original records are always preserved.")
 
 uploaded_file = st.file_uploader("Upload New Patient Dataset (CSV)", type="csv")