Update app.py

app.py

@@ -1,10 +1,13 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, HTTPException
 import joblib
 import pandas as pd
 from pydantic import BaseModel
 
 # Load the trained model
-model = joblib.load("slope_stability_model.pkl")
+try:
+    model = joblib.load("slope_stability_model.pkl")
+except Exception as e:
+    raise RuntimeError(f"Error loading model: {e}")
 
 # Initialize FastAPI
 app = FastAPI()
@@ -17,15 +20,32 @@ class SlopeStabilityInput(BaseModel):
     slope_angle: float
     slope_height: float
     water_pressure_ratio: float
-    reinforcement_type: str
+    reinforcement_type: str  # Categorical feature
+
+# Dummy mapping (You should replace this with actual mapping used during training)
+reinforcement_mapping = {
+    "Geogrid": 0,
+    "Anchors": 1,
+    "Shotcrete": 2,
+    "Gabions": 3
+}
 
-# Define API endpoint
 @app.post("/predict")
 def predict_slope_stability(data: SlopeStabilityInput):
-    # Convert input data into a DataFrame
-    input_data = pd.DataFrame([data.dict()])
+    try:
+        # Convert input data into a DataFrame
+        input_data = pd.DataFrame([data.dict()])
+
+        # Encode reinforcement_type (ensure consistency with training)
+        if data.reinforcement_type not in reinforcement_mapping:
+            raise HTTPException(status_code=400, detail="Invalid reinforcement type")
+
+        input_data["reinforcement_type"] = reinforcement_mapping[data.reinforcement_type]
+
+        # Make prediction using the model
+        prediction = model.predict(input_data)
 
-    # Make prediction using the model
-    prediction = model.predict(input_data)
+        return {"Factor of Safety": float(prediction[0])}
 
-    return {"Factor of Safety": float(prediction[0])}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))