app.py

import streamlit as st
import pandas as pd
from huggingface_hub import hf_hub_download
import joblib

# Download and load the trained model
model_path = hf_hub_download(repo_id="KaushikBs/Predictive-Maintenance", filename="best_model_v1.joblib")
model = joblib.load(model_path)

# Streamlit UI
st.title("App for predicting Engine Failures")
st.write("""
This application predicts potential engine failures for vehicles
based on its characteristics such as engine RPM, fuel pressure, lub oil temperature and pressure, coolant temperature and pressure.
Please enter the sensor data below to get a failure prediction.
""")

# User input
engine_rpm = st.number_input("Engine RPM", min_value=1.0, max_value=2500.0, value=800.0, step=1.0)
lub_oil_pressure = st.number_input("Lub Oil Pressure (kPa)", min_value=0.0, max_value=8.0, value=3.3, step=0.01)
fuel_pressure = st.number_input("Fuel Pressure (kPa)", min_value=0.0, max_value=22.0, value=6.6, step=0.01)
coolant_pressure = st.number_input("Coolant Pressure (kPa)", min_value=0.0, max_value=8.0, value=2.3, step = 0.01)
lub_oil_temp = st.number_input("Lub Oil Temperature (C)", min_value=70.0, max_value=90.0, value=77.6, step=0.01)
coolant_temp = st.number_input("Coolant Temperature (C)", min_value=60.0, max_value=200.0, value=78.0, step=0.01)


# Assemble input into DataFrame
input_data = pd.DataFrame([{
    'Engine rpm': engine_rpm,
    'Lub oil pressure': lub_oil_pressure,
    'Fuel pressure': fuel_pressure,
    'Coolant pressure': coolant_pressure,
    'lub oil temp': lub_oil_temp,
    'Coolant temp': coolant_temp
}])

# Predict button
if st.button("Predict Failure"):
    prediction = model.predict(input_data)[0]
    if prediction >= 0.45:
      decision = "Failure predicted"
    else:
      decision = "No failure predicted"
    st.subheader("Prediction Result:")
    st.success(decision)