app.py

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

# ----------------------------
# Load model from Hugging Face
# ----------------------------
HF_MODEL_REPO = "vihu21/adaboost-predictive-maintenance"
MODEL_FILE = "adaboost_pm.joblib"

model_path = hf_hub_download(
    repo_id="vihu21/adaboost-predictive-maintenance",
    filename="adaboost_pm.joblib",
    repo_type="model"
)

model = joblib.load(model_path)

# ----------------------------
# Streamlit UI
# ----------------------------
st.title("🔧 Engine Condition Prediction")
st.write("Fill in the engine parameters to predict engine condition.")

# ----------------------------
# User Inputs
# ----------------------------
engine_rpm = st.number_input("Engine RPM", min_value=50, max_value=6000, value=3000)
lub_oil_pressure = st.number_input("Lub Oil Pressure", min_value=0.0, value=7.25)
fuel_pressure = st.number_input("Fuel Pressure", min_value=0.0, value=21.4)
coolant_pressure = st.number_input("Coolant Pressure", min_value=0.0, value=7.5)
lub_oil_temp = st.number_input("Lub Oil Temperature", min_value=50.0, value=90.0)
coolant_temp = st.number_input("Coolant Temperature", min_value=60.0, value=195.0)

# ----------------------------
# Prepare input data
# ⚠️ Column names must EXACTLY match training
# ----------------------------
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
}])

# ----------------------------
# Prediction
# ----------------------------
if st.button("Predict Engine Condition"):
    prediction = model.predict(input_data)[0]

    st.subheader("Prediction Result")

    if prediction == 1 or prediction == "Good":
        st.success("✅ Engine Condition: GOOD")
    else:
        st.error("⚠️ Engine Condition: BAD")