import streamlit as st
import pandas as pd
import joblib
import requests


# Streamlit UI for Product Sales Prediction
st.title("Product Sales Prediction")
st.subheader("Please fill details below for sales prediction")

# Collect user input
ProductWeight = st.number_input("Product Weight (weight of the product)", min_value=4.0, max_value=22.0, value=10.0)
ProductSugarContent = st.selectbox("Product Sugar Content(sugar content of the product)", ["Low Sugar", "Regular", "No sugar"])
ProductAllocatedArea = st.number_input("Product Allocated Area (ratio of the allocated display area of each product to the total display area )", min_value=0.00, max_value=0.29, value=0.06)
ProductType = st.selectbox("Product Type", ['Baking Goods', 'Breads', 'Breakfast', 'Canned',
                                              'Dairy', 'Frozen Food', 'Fruits and Vegetables',
                                              'Hard Drinks', 'Health and Hygiene', 'Household',
                                              'Meat', 'Others', 'Seafood', 'Snack foods',
                                              'Soft Drinks', 'Starchy Foods'])
ProductMRP = st.number_input("Product MRP(maximum retail price of each product)", min_value=31.0, max_value=266.0, value=120.0)
StoreID = st.selectbox("Store Id",['OUT001', 'OUT002', 'OUT003', 'OUT004'] )
StoreEstablishmentYear = st.number_input("Store Establishment Year (the year in which the store was established)", min_value=1987, max_value=2009, value=2000)
StoreSize= st.selectbox("Store Size", ['Small','Medium', 'High'])
StoreLocationCityType = st.selectbox("Store Location City Type", ['Tier 1', 'Tier 2', 'Tier 3'])
StoreType = st.selectbox("Store Type",['Departmental Store', 'Food Mart', 'Supermarket Type 1', 'Supermarket Type 2'])

# Convert categorical inputs to match model training
input_data = pd.DataFrame([{
    'Product_Weight': ProductWeight,
    'Product_Sugar_Content': ProductSugarContent,
    'Product_Allocated_Area': ProductAllocatedArea,
    'Product_Type': ProductType,
    'Product_MRP': ProductMRP,
    'Store_Id': StoreID,
    'Store_Establishment_Year': StoreEstablishmentYear,
    'Store_Size': StoreSize,
    'Store_Location_City_Type': StoreLocationCityType,
    'Store_Type': StoreType
}])


if st.button("Predict", type='primary'):
    headers = {'Content-Type': 'application/json'}
    response = requests.post("https://csankaran3-backend.hf.space/v1/product", json=input_data.to_dict(orient='records')[0],headers=headers)    # enter user name and space name before running the cell
    if response.status_code == 200:
        result = response.json()
        predicted_sales = result['Predicted Sales']  # Extract only the value
        st.success(f"Sales predictions completed!.. The predicted product sale is {predicted_sales}.")
    else:
        st.error("Error in API request")


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

# Allow users to upload a CSV file for batch prediction
uploaded_file = st.file_uploader("Upload CSV file for batch sales prediction", type=["csv"])



# Make batch prediction when the "Predict Batch" button is clicked
if uploaded_file is not None:
    if st.button("Predict Batch", type='primary'):
        response = requests.post("https://csankaran3-backend.hf.space/v1/productbatch", files={"file": uploaded_file})  # Send file to Flask API
        if response.status_code == 200:
            predictions = response.json()
            st.success("Batch predictions completed!")
            st.write(predictions)  # Display the predictions
        else:
            st.error("Error making batch prediction.")