Update app.py

app.py

@@ -1,99 +1,119 @@
-# Import necessary libraries
-import numpy as np
-import joblib  # For loading the serialized model
-import pandas as pd  # For data manipulation
-from flask import Flask, request, jsonify  # For creating the Flask API
+# ===============================
+# SuperKart Sales Prediction API
+# ===============================
 
-print("--- app.py: Starting Flask application setup ---")
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
 
-# Initialize the Flask application
-superkart_sales_api = Flask("SuperKart Sales Predictor")
-print("--- app.py: Flask app initialized ---")
+print("Starting SuperKart Sales Prediction API...")
 
-# Load the trained machine learning model
+# Initialize Flask app
+app = Flask(__name__)
+
+# Load trained model
 try:
     model = joblib.load("superkart_sales_model.pkl")
-    print("--- app.py: Model loaded successfully ---")
+    print("Model loaded successfully")
 except Exception as e:
-    print(f"--- app.py: ERROR loading model: {e} ---")
-    raise # Re-raise to ensure the error is visible
-
-# Define a route for the home page (GET request)
-@superkart_sales_api.get('/')
+    print("ERROR loading model:", e)
+    raise
+
+# Required columns expected by the trained pipeline
+REQUIRED_COLUMNS = [
+    "Product_Weight",
+    "Product_Allocated_Area",
+    "Product_MRP",
+    "Store_Current_Age",
+    "Product_Sugar_Content",
+    "Store_Id",
+    "Store_Size",
+    "Store_Location_City_Type",
+    "Store_Type",
+    "Product_Id",
+    "Product_Type"
+]
+
+# -------------------------------
+# Health Check / Home Route
+# -------------------------------
+@app.get("/")
 def home():
-    print("--- API: Home route accessed ---")
-    """
-    This function handles GET requests to the root URL ('/') of the API.
-    It returns a simple welcome message.
-    """
-    return "Welcome to the SuperKart Sales Prediction API!"
-
-# Define an endpoint for single sales prediction (POST request)
-@superkart_sales_api.post('/v1/sales')
+    return jsonify({
+        "message": "SuperKart Sales Prediction API is running",
+        "status": "OK"
+    })
+
+# -------------------------------
+# Single Prediction Endpoint
+# -------------------------------
+@app.post("/v1/sales")
 def predict_sales():
-    print("--- API: Single sales prediction route accessed ---")
-    """
-    This function handles POST requests to the '/v1/sales' endpoint.
-    It expects a JSON payload containing product and store details and returns
-    the predicted sales as a JSON response.
-    """
-    # Get the JSON data from the request body
-    input_data_json = request.get_json()
-
-    # Extract relevant features from the JSON data, matching x_train columns
-    # The model expects original feature names before one-hot encoding
-    sample = {
-        'Product_Id': input_data_json['Product_Id'],
-        'Product_Weight': input_data_json['Product_Weight'],
-        'Product_Sugar_Content': input_data_json['Product_Sugar_Content'],
-        'Product_Allocated_Area': input_data_json['Product_Allocated_Area'],
-        'Product_Type': input_data_json['Product_Type'],
-        'Product_MRP': input_data_json['Product_MRP'],
-        'Store_Id': input_data_json['Store_Id'],
-        'Store_Size': input_data_json['Store_Size'],
-        'Store_Location_City_Type': input_data_json['Store_Location_City_Type'],
-        'Store_Current_Age': input_data_json['Store_Current_Age']
-    }
-
-    # Convert the extracted data into a Pandas DataFrame
-    input_df = pd.DataFrame([sample])
-
-    # Make prediction
-    predicted_sales = model.predict(input_df)[0]
-
-    # Convert predicted_sales to Python float and round
-    predicted_sales = round(float(predicted_sales), 2)
-
-    # Return the predicted sales
-    return jsonify({'Predicted Sales': predicted_sales})
-
-
-# Define an endpoint for batch prediction (POST request)
-@superkart_sales_api.post('/v1/salesbatch')
+    try:
+        input_data = request.get_json()
+
+        if not input_data:
+            return jsonify({"error": "Invalid or empty JSON payload"}), 400
+
+        # Convert to DataFrame
+        df = pd.DataFrame([input_data])
+
+        # Ensure all required columns exist
+        for col in REQUIRED_COLUMNS:
+            if col not in df.columns:
+                df[col] = None  # handled by imputers
+
+        # Reorder columns to match training
+        df = df[REQUIRED_COLUMNS]
+
+        # Make prediction
+        prediction = model.predict(df)[0]
+
+        return jsonify({
+            "Predicted Sales": round(float(prediction), 2)
+        })
+
+    except Exception as e:
+        print("Prediction error:", str(e))
+        return jsonify({
+            "error": "Prediction failed",
+            "details": str(e)
+        }), 500
+
+# -------------------------------
+# Batch Prediction Endpoint
+# -------------------------------
+@app.post("/v1/salesbatch")
 def predict_sales_batch():
-    print("--- API: Batch sales prediction route accessed ---")
-    """
-    This function handles POST requests to the '/v1/salesbatch' endpoint.
-    It expects a CSV file containing product and store details for multiple entries
-    and returns the predicted sales as a list in the JSON response.
-    """
-    # Get the uploaded CSV file from the request
-    file = request.files['file']
-
-    # Read the CSV file into a Pandas DataFrame
-    input_df_batch = pd.read_csv(file)
-
-    # Make predictions for all entries in the DataFrame
-    predicted_sales_batch = model.predict(input_df_batch).tolist()
-
-    # Round each prediction and convert to float
-    predicted_sales_batch = [round(float(s), 2) for s in predicted_sales_batch]
-
-    # Return the predictions list as a JSON response
-    return jsonify({'Predicted Sales': predicted_sales_batch})
-
-# Run the Flask application in debug mode if this script is executed directly
-# When deploying with Gunicorn, this block is usually commented out or removed
-if __name__ == '__main__':
-    print("--- app.py: Running Flask app in debug mode ---")
-    superkart_sales_api.run(debug=True)
+    try:
+        if "file" not in request.files:
+            return jsonify({"error": "CSV file not provided"}), 400
+
+        file = request.files["file"]
+        df = pd.read_csv(file)
+
+        # Ensure required columns
+        for col in REQUIRED_COLUMNS:
+            if col not in df.columns:
+                df[col] = None
+
+        df = df[REQUIRED_COLUMNS]
+
+        predictions = model.predict(df)
+
+        return jsonify({
+            "Predicted Sales": [round(float(p), 2) for p in predictions]
+        })
+
+    except Exception as e:
+        print("Batch prediction error:", str(e))
+        return jsonify({
+            "error": "Batch prediction failed",
+            "details": str(e)
+        }), 500
+
+# -------------------------------
+# Local Run (Not used on HF)
+# -------------------------------
+if __name__ == "__main__":
+    app.run(dedug=True)