app.py

import streamlit as st
import pandas as pd
import joblib
import numpy as np
import requests # Import the requests library

# Load the trained model
#@st.cache_resource
#def load_model():
    #return joblib.load("deployment_files/backend_files/product_sales_prediction_model_rf_tuned_v2_0.joblib")

#model = load_model()

# Streamlit UI for Price Prediction
st.title("Product Sales Prediction App")
st.write("This tool predicts the price of an products listing based on the given details.")

st.subheader("Enter the listing details:")

# Collect user input
Product_Sugar_Content = st.selectbox("Sugar Content", ["Regular", "Low Sugar", "No Sugar"])
Product_Weight = st.number_input("Product Weights (grams)", min_value=0.0, max_value=30.0, format="%.2f", value=15.0, step=0.01)
Product_Allocated_Area = st.number_input("Product Allocated Area (Sq.Ft)", min_value=0.0, max_value=0.3, step=0.01, value=0.20, format="%.2f")
Product_MRP = st.number_input("Product Price ($) ", min_value=0.0, max_value=300.0, step=1.0, value=100.0, format="%.2f")
Store_Size = st.selectbox("Store Size", ["High", "Medium", "Small"])
Store_Location_City_Type = st.selectbox("Store Location City Type", ["Tier 1", "Tier 2", "Tier 3"])
Store_Type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Food Mart", "Departmental Store"])
Product_Id_Code = st.selectbox("Product ID Code ", ["FD", "DR", "NC"])
Product_Type_Category = st.selectbox("Product Type Category ", ["Non Perishables", "Perishables"])
Store_Age_Years = st.number_input("Age of the store ? ", min_value=0, max_value=50, value=15, step=1)

# Convert user input into a DataFrame
input_data = pd.DataFrame([{
    'Product_Sugar_Content': Product_Sugar_Content,
    'Product_Weight': Product_Weight,
    'Product_Allocated_Area': Product_Allocated_Area,
    'Product_MRP': Product_MRP,
    'Store_Size': Store_Size,
    'Store_Location_City_Type': Store_Location_City_Type,
    'Store_Type': Store_Type,
    'Product_Id_Code': Product_Id_Code,
    'Product_Type_Category': Product_Type_Category,
    'Store_Age_Years': Store_Age_Years
}])

# Make prediction when the "Predict" button is clicked
if st.button("Predict"):
    response = requests.post("https://R-autowired-ProductSalesPredictionBackend.hf.space/v1/salespredict", json=input_data.to_dict(orient='records')[0])  # Send data to Flask API
    if response.status_code == 200:
        prediction = response.json()['Sales']
        st.success(f"Sales: {prediction}")
    else:
        st.error("Error making prediction.")