import requests
import streamlit as st
import pandas as pd

# Title of the Streamlit app
st.title("Product Sales Prediction for Stores")

# Section for single product prediction
st.subheader("Please fill details below for sales prediction")

# Input fields for user to provide single product/store details
Product_Weight = st.number_input("Product_Weight (Weight of the product)", min_value=1.0, max_value=50.0,value=10.0)
Product_Sugar_Content = st.selectbox("Product_Sugar_Content (Select the sugar content level of the product)", ['Low Sugar','Regular','No Sugar'])
Product_Allocated_Area = st.number_input("Product_Allocated_Area (Area allocated for the product)", min_value=0.001,max_value=0.5,value=0.1)
Product_Type = st.selectbox("Product_Type (Select the type of product)", ['Fruits and Vegetables','Snack Foods','Frozen Foods','Dairy','Household','Baking Goods','Canned','Health and Hygiene','Meat','Soft Drinks','Breads','Hard Drinks','Others','Starchy Foods','Breakfast','Seafood'])
Product_MRP = st.number_input("Product_MRP (Enter the price of the product)", min_value=1.0,max_value=1000.0,value=100.0)
Store_Id = st.selectbox("Store_Id (Select the Store ID)", ['OUT001','OUT002','OUT003','OUT004'])
Store_Establishment_Year = st.selectbox("Store_Establishment_Year (Select the year the store was established)", [2009,1987,1999,1998])
Store_Size = st.selectbox("Store_Size (Select the store size)", ["Medium", "High","Small"])
Store_Location_City_Type = st.selectbox("Store_Location_City_Type (Select the type of city where the store is located)", ["Tier 2", "Tier 1","Tier 3"])
Store_Type = st.selectbox("Store_Type (Select the type of store)",['Supermarket Type2','Supermarket Type1','Departmental Store','Food Mart'])

# Prepare the payload to send to the backend API
sales_data = {
    'Product_Weight': Product_Weight,
    'Product_Sugar_Content': Product_Sugar_Content,
    'Product_Allocated_Area': Product_Allocated_Area,
    'Product_Type': Product_Type,
    'Product_MRP': Product_MRP,
    'Store_Id': Store_Id,
    'Store_Size': Store_Size,
    'Store_Location_City_Type': Store_Location_City_Type,
}

# When the "Predict" button is clicked, send a POST request to the backend API
if st.button("Predict", type='primary'):
    response = requests.post("https://parthipan00410-salespredictionbackend.hf.space/v1/salesdata", json=sales_data)

    # If the request is successful, display the predicted sales
    if response.status_code == 200:
        result = response.json()
        sales_prediciton = result["predicted_sales"]
        st.write(f"Here is the predicted sales value for the product: {sales_prediciton}.")
    else:
        st.error("Error in API request. Please check the backend or payload format.")

# Section for batch prediction
st.subheader("Batch Prediction")

# File uploader to allow CSV upload for batch prediction
file = st.file_uploader("Upload CSV file", type=["csv"])

if file is not None:
    # When "Predict for Batch" button is clicked, send CSV to backend API
    if st.button("Predict for Batch", type='primary'):
        response = requests.post("https://parthipan00410-salespredictionbackend.hf.space/v1/salesdatabatch", files={"file": file})

        # Display the batch prediction results if successful
        if response.status_code == 200:
            result = response.json()
            st.header("Batch Prediction Results")
            st.write(result)
        else:
            st.error("Error in API request. Please check the backend or CSV format.")