import streamlit as st
import requests

# --- Streamlit App Configuration ---
st.set_page_config(
    page_title="Predictive Maintenance for Engine Health",
    page_icon="⚙️",
    layout="centered",
    initial_sidebar_state="expanded",
)

st.title("⚙️ Predictive Maintenance for Engine Health")
st.markdown("### Predict if an engine is Normal or Faulty based on sensor readings")

# --- Input Fields for Sensor Data ---
st.subheader("Engine Sensor Readings")

# Using st.number_input for numerical inputs with appropriate ranges and step
engine_rpm = st.number_input(
    "Engine RPM", min_value=0.0, max_value=3000.0, value=700.0, step=10.0,
    help="Revolutions per minute of the engine (RPM)"
)
lub_oil_pressure = st.number_input(
    "Lub Oil Pressure (bar/kPa)", min_value=0.0, max_value=10.0, value=2.5, step=0.1,
    help="Pressure of the lubricating oil"
)
fuel_pressure = st.number_input(
    "Fuel Pressure (bar/kPa)", min_value=0.0, max_value=30.0, value=12.0, step=0.1,
    help="Pressure at which fuel is supplied to the engine"
)
coolant_pressure = st.number_input(
    "Coolant Pressure (bar/kPa)", min_value=0.0, max_value=10.0, value=3.0, step=0.1,
    help="Pressure of the engine coolant"
)
lub_oil_temperature = st.number_input(
    "Lub Oil Temperature (°C)", min_value=0.0, max_value=150.0, value=85.0, step=0.5,
    help="Temperature of the lubricating oil"
)
coolant_temperature = st.number_input(
    "Coolant Temperature (°C)", min_value=0.0, max_value=150.0, value=80.0, step=0.5,
    help="Temperature of the engine coolant"
)

# --- Prediction Button and Logic ---

# Replace with the actual URL of your deployed backend API
# For local testing, it might be something like "http://localhost:5000"
# For Hugging Face Spaces, it will be the URL of your Docker Space
BACKEND_API_URL = "https://veerendramanikonda-predictivemaintenancebackend.hf.space/v1/engine_condition_prediction"

if st.button("Predict Engine Condition", type="primary"):
    # Prepare the data payload for the API request
    engine_data = {
        "Engine_RPM": engine_rpm,
        "Lub_Oil_Pressure": lub_oil_pressure,
        "Fuel_Pressure": fuel_pressure,
        "Coolant_Pressure": coolant_pressure,
        "Lub_Oil_Temperature": lub_oil_temperature,
        "Coolant_Temperature": coolant_temperature
    }

    try:
        # Make the POST request to the backend API
        response = requests.post(BACKEND_API_URL, json=engine_data)
        response.raise_for_status()  # Raise an exception for HTTP errors (4xx or 5xx)
        prediction = response.json()

        st.subheader("Prediction Results:")
        predicted_label = prediction['predicted_engine_condition_label']
        probability_faulty = prediction['probability_faulty']
        probability_normal = prediction['probability_normal']

        if predicted_label == "Faulty":
            st.error(f"The engine is predicted to be: **{predicted_label}**")
            st.write(f"Probability of Faulty: {probability_faulty:.2f}")
            st.write(f"Probability of Normal: {probability_normal:.2f}")
            st.warning("Immediate maintenance recommended!")
        else:
            st.success(f"The engine is predicted to be: **{predicted_label}**")
            st.write(f"Probability of Normal: {probability_normal:.2f}")
            st.write(f"Probability of Faulty: {probability_faulty:.2f}")
            st.info("Engine is operating normally.")

    except requests.exceptions.ConnectionError:
        st.error("Connection Error: Could not connect to the backend API. Please ensure the backend is running and the URL is correct.")
    except requests.exceptions.Timeout:
        st.error("Timeout Error: The request to the backend API timed out.")
    except requests.exceptions.RequestException as e:
        st.error(f"An error occurred during the API request: {e}")
    except Exception as e:
        st.error(f"An unexpected error occurred: {e}")