Working with Numeric and Categorical Data

Learning Objective

Develop expertise in building advanced machine learning models for structured data, including numeric and categorical features.

Related Skills

1. Handling missing values and encoding categorical variables
2. Applying feature engineering techniques for numeric and categorical data
3. Evaluating model performance for mixed data types

Subtopics

1. Imputation methods for missing data
2. One-hot encoding, ordinal encoding, and target encoding
3. Feature selection and dimensionality reduction
4. Tree-based models (decision trees, random forests, gradient boosting)
5. Hyperparameter tuning and model selection

References and Resources

- "Feature Engineering for Machine Learning" by Alice Zheng and Amanda Casari
- "Hands-On Machine Learning with Scikit-Learn and TensorFlow" by Aurélien Géron
- Kaggle micro-course "Feature Engineering"