Course Outline

🔹 Day 1: Machine Learning Fundamentals and Data Preparation

Session 1: Introduction to Machine Learning

• What is ML? Types: Supervised, Unsupervised, Reinforcement Learning
• Real-world applications across industries
• Key concepts: Features, labels, training vs testing, overfitting/underfitting

Session 2: Python Tools and Libraries for ML

• pandas and NumPy for data manipulation
• scikit-learn overview
• matplotlib and seaborn for data visualization

Session 3: Data Preprocessing Techniques

• Data cleaning and handling missing values
• Feature engineering and encoding categorical data
• Scaling and normalization

Lab Activities:

• Explore a dataset with pandas
• Clean and visualize data (e.g., Titanic or Iris dataset)
• Apply preprocessing steps using scikit-learn pipelines

🔹 Day 2: Building and Evaluating ML Models

Session 1: Supervised Learning – Classification

• Logistic Regression, Decision Trees, Random Forests
• Model training and prediction with scikit-learn
• Cross-validation techniques

Session 2: Supervised Learning – Regression

• Linear Regression, Ridge, Lasso
• Evaluation metrics (MAE, RMSE, R²)
• Practical regression example (e.g., predicting house prices)

Session 3: Model Evaluation and Tuning

• Confusion matrix, precision, recall, F1-score
• ROC curve and AUC
• Hyperparameter tuning with GridSearchCV

Lab Activities:

• Train and test multiple models on real datasets
• Evaluate using confusion matrix and ROC curve
• Tune model performance using cross-validation

🔹 Day 3: Unsupervised Learning and Deployment

Session 1: Unsupervised Learning

• Clustering with K-Means and DBSCAN
• Dimensionality reduction with PCA
• Use cases: Customer segmentation, anomaly detection

Session 2: Model Deployment and Real-World Use

• Exporting models with joblib or pickle
• Introduction to Flask for creating a simple ML API
• Using Streamlit for building ML apps

Session 3: Capstone Project + Next Steps

• Capstone project: End-to-end ML solution using a public dataset
• Presentation and feedback
• Overview of deep learning and ML in production

Lab Activities:

• Apply clustering on customer data
• Build and deploy a mini web app with Streamlit
• Present group/individual project