import streamlit as st
import pandas as pd
import numpy as np
import requests


# Streamlit UI for Price Prediction
st.title("SuperKart Sales Predictor")
st.write("This tool predicts the sales based on various store parameters.")

st.subheader("Enter the store details(Single Predication):")

# Collect user input
product_weight = st.number_input("Product Weight (in kg)", min_value=1.0, max_value=30.0)
product_sugar = st.selectbox("Sugar Content", ["Low Sugar", "Regular", "No Sugar"])
product_area = st.slider("Allocated Area (sq m)", min_value=0.0, max_value=1.0, step=0.01)
product_type = st.selectbox("Product Type", ["Fruits and Vegetables", "Snack Foods", "Frozen Foods", "Dairy", "Household","Baking Goods", "Canned", "Health and Hygiene", "Meat", "Breads","Hard Drinks", "Soft Drinks", "Seafood", "Starchy Foods", "Others"])
product_mrp = st.number_input("Product MRP", min_value=10.0, max_value=300.0)
store_year = st.number_input("Store Establishment Year", min_value=1980, max_value=2025)
store_size = st.selectbox("Store Size", ["Small", "Medium", "High"])
store_city = st.selectbox("City Type", ["Tier 1", "Tier 2", "Tier 3"])
store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Food Mart", "Departmental Store"])

# Prepare input
if st.button("Predict Sales"):
    input_df = {
        "Product_Weight": product_weight,
        "Product_Sugar_Content": product_sugar,
        "Product_Allocated_Area": product_area,
        "Product_Type": product_type,
        "Product_MRP": product_mrp,
        "Store_Establishment_Year": 2025 - store_year,  # we have modified this to get the  store age
        "Store_Size": store_size,
        "Store_Location_City_Type": store_city,
        "Store_Type": store_type
    }
    response = requests.post("https://harasar-SuperKartBackend.hf.space/v1/customer", json=input_df)    # enter user name and space name before running the cell
    if response.status_code == 200:
        result = response.json()
        churn_prediction = result["predicted_sales"]  # Extract only the value
        st.write(f"Based on the information provided, the sproject sales is likely to {churn_prediction}.")
    else:
        st.error("Error in API request")

#Batch Prediction
uploaded_file = st.file_uploader("Upload CSV file", type=["csv"])

if st.button("Predict for Batch"):
    if uploaded_file is not None:
        try:
            # Convert uploaded file to a DataFrame
            df = pd.read_csv(uploaded_file)

            # Convert DataFrame to CSV bytes like your working script
            csv_bytes = df.to_csv(index=False).encode('utf-8')

            # Send POST request with raw bytes
            response = requests.post(
                "https://harasar-SuperKartBackend.hf.space/v1/customerbatch",
                files={"file": ("SuperKart.csv", csv_bytes, "text/csv")}
            )

            if response.status_code == 200:
                st.success("Batch prediction successful!")
                st.write(response.json())
            else:
                st.error(f"Error {response.status_code}: {response.text}")

        except Exception as e:
            st.error(f"Upload failed: {e}")
    else:
        st.warning("Please upload a CSV file first.")