| Instructor | [Charlie Liu] |
|---|---|
| [yli3444@emory.edu] | |
| Office Hours | See Canvas for info |
| Meeting day/time | MW 8:30-09:45am |
ECON 725 equips students with essential programming and computational data science skills tailored for economic analysis. Students will learn to use tools like Python, Git, Docker, and Cloud Computing to create reproducible workflows, analyze data, and present results through dashboards and visualizations. The course also covers machine learning techniques and practical methods for deploying models in real-world scenarios. Additionally, students will develop proficiency in SQL and Tableau for data manipulation and visualization. A key component of the course is its hands-on practice with data analysis challenges, where students apply the tools and techniques learned to manipulate and analyze datasets effectively.
This course will equip students with the skills to create fully reproducible data analysis pipelines. Upon completing this course, students will be able to acquire, organize, explore, and construct basic statistical models to analyze economic data and present reports in a dashboard. By the end of the course, students will be proficient in:
- Developing collaborative, reproducible workflows using Git and GitHub for version control.
- Running these workflows on a local and remote computers with tools like command line operations and Github Codespaces.
- Executing workflows in a containerized environment using Docker for comprehensive reproducibility.
- Implementing workflows in a virtual environment with cloud computing tools.
- Developing dashboards and data visualizations with appropriate software.
- Implementing efficient code in Python and R following best coding practices.
Grades will be based on the categories listed below with the corresponding weights. More information on Canvas.
| Component | Percent |
|---|---|
| Class Participation | 10% |
| Online Learning | 25% |
| In-class Assessments | 25% |
| Mini-Projects | 40% |
| Total points | 100% |
- Part 1: Command Line and Version Control
- Set up
- Command line
- Git and Github for version control
- Docker, Images and containers for reproducible research
- Part 2: Programming Essentials and Best Practices
- Python and R basics
- Pandas, Mathematical operations with NumPy
- Getting data from different sources: Public data, APIs
- Web scrapping
- Data Ingestion and transformation with SQL: SQLite
- Part 3: Applied Data Science and Machine Learning
- Supervised Learning concepts
- Experiment tracking and Model Management
- Developing ML models for Production environments
- Developing Large Language Models (LLMs)
- ML in Economics: Debiased/Orthogonal Machine Learning
- ML in Economics: Heterogeneous Treatment Effects and Personalization
- Part 4: Analytics Engineering and Data Visualization
- Big Data environments with Databricks and Spark
- Data Visualizations and reporting in Dashboards
- Time Series Forecasting (Optional)