# Import necessary libraries
import joblib
import pandas as pd
from flask import Flask, request, jsonify

# Initialize the Flask application
sales_predictor_api = Flask("Sales Predictor")

# Load the trained machine learning model
model = joblib.load("sales_prediction_model_v1_0.joblib")

# Home route
@sales_predictor_api.get("/")
def home():
    return "Welcome to the Sales Prediction API!"

# Single sales prediction
@sales_predictor_api.post("/v1/sales")
def predict_sales():

    sales_data = request.get_json()

    input_df = pd.DataFrame([{
        "Product_Weight": sales_data["Product_Weight"],
        "Product_Sugar_Content": sales_data["Product_Sugar_Content"],
        "Product_Allocated_Area": sales_data["Product_Allocated_Area"],
        "Product_Type": sales_data["Product_Type"],
        "Product_MRP": sales_data["Product_MRP"],
        "Store_Establishment_Year": sales_data["Store_Establishment_Year"],
        "Store_Size": sales_data["Store_Size"],
        "Store_Location_City_Type": sales_data["Store_Location_City_Type"],
        "Store_Type": sales_data["Store_Type"]
    }])

    prediction = model.predict(input_df)[0]

    return jsonify({"predicted_sales": float(prediction)})

# Batch prediction
@sales_predictor_api.post("/v1/salesbatch")
def predict_sales_batch():

    file = request.files["file"]
    input_df = pd.read_csv(file)

    predictions = model.predict(input_df)

    return jsonify({"predicted_sales": predictions.tolist()})

if __name__ == "__main__":
    sales_predictor_api.run(debug=True)