app.py

from flask import Flask, request, jsonify
import joblib
import numpy as np
import pandas as pd # Import pandas

# Load model
model = joblib.load('superkart_model_v1.0_joblib')

app = Flask(__name__)

@app.route("/")
def welcome():
    return "SuperKart Sales Forecasting API is running."

@app.route("/predict", methods=["POST"])
def predict():
    # Expect JSON with keys matching model input feature order
    data = request.json
    # The input data from the request needs to be in the correct order and format
    # as expected by the preprocessor and model pipeline.
    # Assuming the input JSON keys match the original feature names and order:

    # Create a pandas DataFrame from the input data
    # Ensure the column names match the features used during training
    feature_names = [
        'Product_Weight', 'Product_Sugar_Content','Product_Allocated_Area', 'Product_Type',
        'Product_MRP', 'Store_Establishment_Year', 'Store_Size',
        'Store_Location_City_Type', 'Store_Type'
    ]
    input_df = pd.DataFrame([data.values()], columns=feature_names) # Convert data to DataFrame

    # Note: The loaded model includes the preprocessor, so we don't need to
    # manually preprocess the input here. The pipeline handles it.
    prediction = model.predict(input_df) # Pass DataFrame to predict
    return jsonify({'prediction': float(prediction[0])})

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860, debug=True)