Update app.py

app.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI 
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 import joblib
 import numpy as np
@@ -6,31 +6,43 @@ import numpy as np
 app = FastAPI()
 
 class InputData(BaseModel):
-    input1 : float
-    input2 : float
-    input3 : float
-    input4 : float
-    input5 : float
-    input6 : float
-    input7 : float 
+    input1: float
+    input2: float
+    input3: float
+    input4: float
+    input5: float
+    input6: float
+    input7: float
 
-try: 
+# Load the model and handle potential errors gracefully
+try:
     model = joblib.load('random_forest_model.joblib')
     status = 'Loaded'
-    print(status)
-except:
-    status = "not loaded"
-    print(status)
+    print(f"Model {status}")
+except Exception as e:
+    status = f"not loaded: {e}"
+    print(f"Model {status}")
 
 @app.get('/')
 def health_check():
-    return {'status' : f'{status}'}
+    # Return the current status of the app (whether the model is loaded or not)
+    return {'status': f'{status}'}
 
 @app.post('/predict')
-def predict(input : InputData):
+def predict(input: InputData):
+    # Ensure the model is loaded before making predictions
+    if status != 'Loaded':
+        raise HTTPException(status_code=500, detail="Model not loaded. Please check the server logs.")
+    
+    # Prepare the input data for prediction
     data = np.array([[input.input1, input.input2,
-    input.input3, input.input4,
-    input.input5, input.input6,
-    input.input7]])
+                      input.input3, input.input4,
+                      input.input5, input.input6,
+                      input.input7]])
+    
+    # Make prediction using the loaded model
     prediction = model.predict(data).tolist()
-    return {'prediction' : prediction[0]}
+
+    # Return the prediction in JSON format
+    return {'prediction': prediction[0]}
+