praneeth232/Machine-Failure-Prediction

1import streamlit as st2import pandas as pd3from huggingface_hub import hf_hub_download4import joblib5 6# Download and load the model7model_path = hf_hub_download(repo_id="praneeth232/machine_failure_model", filename="best_machine_failure_model_v1.joblib")8model = joblib.load(model_path)9 10# Streamlit UI for Machine Failure Prediction11st.title("Machine Failure Prediction App")12st.write("""13This application predicts the likelihood of a machine failing based on its operational parameters.14Please enter the sensor and configuration data below to get a prediction.15""")16 17# User input18Type = st.selectbox("Machine Type", ["H", "L", "M"])19air_temp = st.number_input("Air Temperature (K)", min_value=250.0, max_value=400.0, value=298.0, step=0.1)20process_temp = st.number_input("Process Temperature (K)", min_value=250.0, max_value=500.0, value=324.0, step=0.1)21rot_speed = st.number_input("Rotational Speed (RPM)", min_value=0, max_value=3000, value=1400)22torque = st.number_input("Torque (Nm)", min_value=0.0, max_value=100.0, value=40.0, step=0.1)23tool_wear = st.number_input("Tool Wear (min)", min_value=0, max_value=300, value=10)24 25# Assemble input into DataFrame26input_data = pd.DataFrame([{27    'Air temperature': air_temp,28    'Process temperature': process_temp,29    'Rotational speed': rot_speed,30    'Torque': torque,31    'Tool wear': tool_wear,32    'Type': Type33}])34 35 36if st.button("Predict Failure"):37    prediction = model.predict(input_data)[0]38    result = "Machine Failure" if prediction == 1 else "No Failure"39    st.subheader("Prediction Result:")40    st.success(f"The model predicts: **{result}**")41