| import streamlit as st | |
| def run(): | |
| st.title("6. Deployment & Testing") | |
| st.header("Introduction") | |
| st.write(""" | |
| Model Deployment is the process of integrating a machine learning model into a production environment where it can make predictions on new data. | |
| """) | |
| st.header("Objectives") | |
| st.write(""" | |
| - Integrate the model into production. | |
| - Monitor model performance. | |
| - Update the model as needed. | |
| """) | |
| st.write("## Overview") | |
| st.write("Deploying the model and testing its real-world performance.") | |
| st.write("## Key Concepts & Explanations") | |
| st.markdown(""" | |
| - **Deployment**: Making the model available for use (e.g., via an API). | |
| - **Testing**: Ensuring the model works in production environments. | |
| - **Model Monitoring**: Continuously tracking model performance in real-time. | |
| """) | |
| st.write("## Quiz: Conceptual Questions") | |
| q1 = st.radio("Which of the following is part of deployment?", ["Model Training", "Model Versioning", "Model Testing"]) | |
| if q1 == "Model Versioning": | |
| st.success("✅ Correct!") | |
| else: | |
| st.error("❌ Incorrect.") | |
| st.write("## Code-Based Quiz") | |
| code_input = st.text_area("Write code to save a model using joblib", value="import joblib\njoblib.dump(model, 'model.pkl')") | |
| if "joblib.dump" in code_input: | |
| st.success("✅ Correct!") | |
| else: | |
| st.error("❌ Try again.") | |
| st.write("## Learning Resources") | |
| st.markdown(""" | |
| - 📘 [Machine Learning Model Deployment](https://towardsdatascience.com/deploying-machine-learning-models-using-flask-285dbddedbfa) | |
| """) | |