import streamlit as st
import pandas as pd
import requests

# ==================================
# Streamlit UI
# ==================================
st.set_page_config(page_title="Product Store Sales Prediction", layout="centered")
st.title("Product Store Sales Prediction App")
st.write("Predict total sales for a product in a store using machine learning.")

# ==================================
# Input Fields — Single Record
# ==================================
st.header("Single Prediction")

# --- Product Features ---
st.subheader("Product Details")
Product_Code = st.selectbox(
    "Product Code",
    ["NC", "FD", "RC"],
    index=0
)
Product_Weight = st.number_input("Product Weight (kg)", min_value=0.0, step=0.01, value=14.80)

Product_Sugar_Content = st.selectbox(
    "Sugar Content",
    ["Low Sugar", "No Sugar", "Regular"]
)

Product_Allocated_Area = st.number_input("Allocated Area (sq.m)", min_value=0.0, step=0.001, value=0.016)

Product_Type = st.selectbox(
    "Product Type",
    ["Food", "Health and Hygiene", "Household", "Soft Drinks"]
)

Product_MRP = st.number_input("Maximum Retail Price (MRP)", min_value=0.0, step=0.1, value=140.53)

# --- Store Features ---
st.subheader("Store Details")
Store_Id = st.selectbox(
    "Store ID",
    ["OUT001", "OUT002", "OUT003", "OUT004", "OUT005"]
)

Store_Age = st.number_input("Store Age (years)", min_value=0, step=1, value=20)

Store_Size = st.selectbox("Store Size", ["Small", "Medium", "High"])

Store_Location_City_Type = st.selectbox("City Type", ["Tier 1", "Tier 2", "Tier 3"])

Store_Type = st.selectbox(
    "Store Type",
    ["Supermarket Type1", "Supermarket Type2", "Food Mart", "Departmental Store"]
)

# ==================================
# Predict Button — Single
# ==================================
if st.button("Predict Sales", type="primary"):
    input_data = {
        "Product_Code": Product_Code,
        "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_Age": Store_Age,
        "Store_Size": Store_Size,
        "Store_Location_City_Type": Store_Location_City_Type,
        "Store_Type": Store_Type
    }

    API_URL = "https://abhishek1504-learning.hf.space/v1/sales"

    with st.spinner("Fetching prediction..."):
        response = requests.post(API_URL, json=input_data)

    if response.status_code == 200:
        result = response.json()
        if "Predicted_Product_Store_Sales_Total" in result:
            predicted_sales = result["Predicted_Product_Store_Sales_Total"]
            st.success(f"Predicted Total Sales: **{predicted_sales:.2f} units**")
        else:
            st.error(f"Unexpected response format: {result}")
    else:
        st.error(f"API Error {response.status_code}: {response.text}")

# ==================================
# Batch Prediction Section
# ==================================
st.header("Batch Prediction")
file = st.file_uploader("Upload CSV file (must include same column names as model)", type=["csv"])

if file is not None:
    if st.button("Predict for Batch", type="primary"):
        API_BATCH_URL = "https://abhishek1504-learning.hf.space/v1/salesbatch"
        with st.spinner("Processing batch predictions..."):
            response = requests.post(API_BATCH_URL, files={"file": file})
        if response.status_code == 200:
            result = response.json()
            try:
                df_result = pd.DataFrame(result)
                st.dataframe(df_result, use_container_width=True)
                st.success("Batch predictions completed successfully.")
            except Exception:
                st.write(result)
        else:
            st.error(f"API Error {response.status_code}: {response.text}")