app.py

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

# Downloading the model from the Model Hub
model_path = hf_hub_download(repo_id="skalpitin/Engine-Failure-Prediction", filename="Engine-Failure-Prediction_v1.joblib")

# Loading the model
model = joblib.load(model_path)

# Streamlit UI for Customer Churn Prediction
st.title("Engine Failure Prediction App")
st.write("The Engine Failure Prediction App is a tool that predicts Engine failures.")
st.write("Kindly enter the Engine parameter details to check whether the engine is running in a healthy state or a faulty state.")

# Collecting user input
Engine_RPM = st.number_input("RPM", min_value=50, value=2500)
Lub_oil_pressure = st.number_input("Lubrication Oil Pressure", min_value=0.0, value=5.0)
Fuel_pressure = st.number_input("Fuel Pressure", min_value=0.0, value=15.0)
Coolant_pressure = st.number_input("Coolant Pressure", min_value=0.0, value=5.0)
Lub_oil_temp = st.number_input("Lubrication Oil Temperature", min_value=50, value=100)
Coolant_temp = st.number_input("Coolant Temperature", min_value=60, value=150)

# Converting inputs to a dataframe to pass to the model
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
}])

# Setting the classification threshold
classification_threshold = 0.45

# Predict button -  Calling the model with input dataframe
if st.button("Predict"):
    prediction_proba = model.predict_proba(input_data)[0, 1]
    prediction = (prediction_proba >= classification_threshold).astype(int)
    result = "faulty" if prediction == 1 else "healthy"
    st.write(f"Based on the information provided, the engine is likely to to be running in {result} state.")