Update main.py

main.py

@@ -166,11 +166,78 @@ async def your_continuous_function(page: int,paginate: int,Tenant: str):
     
     train_the_model(data)
 
-    return "model trained with page number: "+str(page)+" data count :"+str(data_count)
+    return {"model trained details":{"page_number":page,"data_count":data_count}}
+
+
+    
 
 @app.get("/get_latest_model_updated_time")
 async def model_updated_time():
-    m_time_encoder = os.path.getmtime('encoders.joblib')
-    m_time_model = os.path.getmtime('xgb_model.joblib')
-    return {"base model created time ":datetime.datetime.fromtimestamp(m_time_encoder),
-            "last model updated time":datetime.datetime.fromtimestamp(m_time_model)}
+    try:
+        m_time_encoder = os.path.getmtime('encoders.joblib')
+        m_time_model = os.path.getmtime('xgb_model.joblib')
+        return {"base model created time ":datetime.datetime.fromtimestamp(m_time_encoder),
+                "last model updated time":datetime.datetime.fromtimestamp(m_time_model)}
+    except:
+        return {"no model found so first trained the model using data fecther"}
+
+
+
+
+
+# Endpoint for making predictions
+@app.post("/predict")
+def predict(customer_name: str,
+    customer_address: str,
+    customer_phone: str,
+    customer_email: str,
+    cod:str,
+    weight: str,
+    pickup_address: str,
+    origin_city_name: str,
+    destination_city_name: str,
+    origin_country: str):
+
+    try:
+        # Load your trained model and encoders
+        xgb_model = load('xgb_model.joblib')
+        encoders = load('encoders.joblib')
+    except:
+        return {"no model found so first trained the model using data fecther"}
+
+    
+    # Function to handle unseen labels during encoding
+    def safe_transform(encoder, column):
+        classes = encoder.classes_
+        return [encoder.transform([x])[0] if x in classes else -1 for x in column] 
+        
+    # Convert input data to DataFrame
+    input_data = {
+        'customer_name': customer_name,
+        'customer_address': customer_address,
+        'customer_phone': customer_phone,
+        'customer_email': customer_email,
+        'cod': float(cod),
+        'weight': float(weight),
+        'origin_city.name':origin_city_name,
+        'destination_city.name':destination_city_name
+    }
+    input_df = pd.DataFrame([input_data])
+
+    # Encode categorical variables using the same encoders used during training
+    for col in input_df.columns:
+        if col in encoders:
+            input_df[col] = safe_transform(encoders[col], input_df[col])
+
+    # Predict and obtain probabilities
+    pred = xgb_model.predict(input_df)
+    pred_proba = xgb_model.predict_proba(input_df)
+
+    # Output
+    predicted_status = "Unknown" if pred[0] == -1 else encoders['status.name'].inverse_transform([pred])[0]
+    probability = pred_proba[0][pred[0]] * 100 if pred[0] != -1 else "Unknown"
+
+    if predicted_status == "RETURN TO CLIENT":
+       probability = 100 - probability
+
+    return {"Probability": round(probability,2)}