Skip to main content

Previous Courses Offered

Below is a list of courses and course descriptions offered during previous semesters.

DSC-495 Fall 2022 Sections

In Fall 2022, the DSA is offered 17 topics:

  1. Biomedical Data Sharing DSC-495-605
  2. Clustering Data Through Machine Learning DSC-495-600
  3. Data Communication DSC-495-012
  4. Data Science for Cybersecurity DSC-495-602
  5. Data Science for Social Good DSC-495-603
  6. Data Science for Sustainability DSC-495-003
  7. Data Wrangling and Web Scraping* DSC-495-004
  8. Exploratory Data Analysis for Big Data* DSC-405-002
  9. Epidemiology: BIG Data for Disease and Disparities DSC-495-607
  10. Machine Learning for Practitioners* DSC-495-010
  11. Reproducibility, Containers and the Cloud* DSC-495-020
  12. Introduction to R/Python (5 sections) DSC-495-001, DSC-495-006, DSC-495-009, DSC-495-016, and DSC-495-017)
  13. R for Data Science and Visualization DSC-495-007
  14. R for Social Sciences DSC-495-606
  15. Scientific Programming with Python (2 sections) DSC-495-014, DSC-495-015
  16. Social Media: Data, Ethics and Theory DSC-495-601
  17. Visualization: Tools and Techniques DSC-495-005

DSC-495 Spring 2022 Sections

In Spring 2022, the DSA offered 8 courses:

  1. Big Data*
  2. Data for Policy
  3. Ethics
  4. Machine Learning for Practitioners*
  5. NLP (Natural Language Processing)*
  6. Data Physicalization
  7. Introduction to R/Python (3 sections)
  8. Wrangling/Scraping*

DSC-495 Fall 2021 Sections

In Fall 2022, the DSA offered 5 courses:

  1. Big Data*
  2. Data for Policy
  3. Data Visualization
  4. R/Python
  5. Wrangling/Scraping*

All Course Descriptions

Some courses listed above are still being offered in the upcoming semester. Below is a list of both current and previously offered course descriptions.

Currently offered courses:

Students will learn to articulate the benefits and potential risks of biomedical data sharing and explore the evolution of data sharing policy, from initial conception to current and future considerations. Students will discuss FAIR principles of data sharing and the technical and ethical barriers to sharing present in many existing data sets, examine how private information (such as personal identifying information (PII) and personal health information (PHI)) are safeguarded in data sharing; and learn how data are collected, deposited, and how access to those sets is managed in federal repositories. Students will discuss the differences in domestic versus foreign data sharing policies and impacts on research and international collaboration. Students will investigate the role of the private sector in data sharing from research, discovery, and legal perspectives. Final project puts ideas into practice.

Employers want to hire people who can communicate to a wide variety of audiences. Many disciplines have their own specialized language or jargon. It is easy to fall into the habit of using that jargon to communicate data analysis results or concepts to the public, or to “cherry-pick” and selectively present data or results to convey a specific idea. Students will fine-tune their awareness regarding the use of discipline-specific language. Students will present scientific results and concepts clearly, unambiguously, and with a minimum of jargon.

What kind of data interests you? How can you communicate it in unexpected ways? To investigate these questions, students will communicate data and other information through movement. No prior dance experience is required. Students will collaborate with their peers – a mix of dancers and people interested in data, communication and moving. Students will both create movement and participate in movement created by others.

No prerequisites required

This course is designed to prepare students who want to make a difference in the world for a data science internship. Students will focus on internships for social good in non-profits, governmental organizations, and community organizations. Students will utilize a data maturity tool for possible preparation for a data science internship. Explorations of these areas include specific emphasis on developing and refining interviewing skills, professional and personal networks, and job application and selection.

Prerequisites: some data science related skills required (such as Python, R, data visualization, Excel for business or government, etc.)

Data in an enterprise is a strategic asset. Data can be valuable much more so in some industries than others. For enterprises where data is their “product” managing the data as an asset becomes more critical. The business model of such enterprises depends on monetizing the data and hence serves as the source of their revenues. Examples of such enterprises include Dunn & Bradstreet, Nielson Ratings, Google etc. Data landscapes can be complex with data often spread out among multiple source systems. In a typical global enterprise these source systems can be physically located in different continents. Data Management is a discipline that covers all aspects of how data gets produced, transformed and consumed. Data Management also covers Data Pipelines that act as a physical conduit that transports the data from the source systems, through the processing systems and ultimately to the systems that enable data consumption.

Data management skills are in high demand by potential employers since they allow a candidate to use available data to support an organization’s overall objectives. Employers from public, private, and nonprofit firms across the country need workers with expertise in this area. Working with data requires a data programming skill set and knowledge of statistics. This course is designed to develop practical data programming skills.

In the past year, a cyberattack occurred once every 39 seconds on average. Students will investigate the use of data to discover, explore, and address relevant cybersecurity use cases. Students will become familiar with fundamental approaches to tackle common cybersecurity problems using Python. No prior programming experience required.

No prerequisites required

Data science offers powerful tools for addressing a multitude of societal challenges, yet it is no panacea and will require collaboration and commitment from across society to fulfill its promise. Students will investigate the growing use of data science in the social impact space, drawing from real-world examples aligned with the United Nation’s Sustainable Development Goals. These examples will span practice areas and approaches, including machine learning, natural language processing, and image recognition. Students will discuss the challenges of implementing data science for social good solutions, including considerations of community involvement, bias, and equity and identify best practices.

No prerequisites required

Visualizations can be one of the most effective means to communicate quantitative information. Students will apply the principles of effective visualization and interpret data displays. Students will evaluate current examples in the media and learn tools for creating static, interactive, and dynamic data displays. No programming experience needed.

No prerequisites required

Finding, cleaning, and preparing data is often required prior to conducting any data analysis. These wrangling processes often account for the majority of the time spent working with data and learning these concepts is fundamental to the data science process. Students will learn how to manipulate and clean data for analyses and visualizations, read data from web pages, and merge multiple data sets of reasonable sizes. Requires knowledge of data structures, for and while loops, list comprehension, basic understanding of a programming language.

Prerequisites: knowledge of data structures, for and while loops, list comprehension, basic understanding of a programming language

Epidemiology is a data driven field driven by the past, current and future history of a population to develop resilient public health and other public policies. Students will manipulate data sets to understand the unequal distribution of disease, illness, injuries, disability, and death within a population. Students will utilize data sources, data retrieval and data scrubbing; and will investigate causality and data interpretation using the basic quantitative analyses of epidemiology. Using these skills, students will create their own study of interest on topics like gun violence and climate change disparities.

Prerequisites: basic understanding of statistical concepts, basic understanding of Microsoft Excel

Exploratory data analysis (EDA) focuses on summarizing the main characteristics of a dataset, often using visualization methods. The goal is not formal modeling or hypothesis testing, but understanding and exploring data to formulate hypotheses for further investigation. EDA techniques will be presented and students will apply these methods to large data sets. Requires knowledge of data structures, for and while loops, list comprehension, basic understanding of a programming language.

Prerequisites: knowledge of data structures, for and while loops, list comprehension, basic understanding of a programming language

Students will develop introductory skills in R and Python needed for data science. Topics include data types, data structures, control structures, good coding practices, and reproducible coding. Students will become acquainted with basic data science algorithms and their implementations in R and Python. Skills acquired in this course serve as a foundation for many of the Data Science Academy classes that suggest some experience with R or Python. No prior programming experience required.

No prerequisites required

TBD

Prerequisites: some programming experience, or familiarity with a programming language

A large part of data science is being able to manipulate the data you have for the analysis you wish to do. Students will format and clean data, extract relevant information from the data, and manipulate data for analysis. Students will also explore visualizations, how different types of visualizations convey different meanings, and how to pick the most accurate way to represent analyses that will interest the intended audience.

No prerequisites required

This course will provide a broad overview of text analysis and natural language processing (NLP), including a significant amount of introductory material but with extensions to state-of-the-art methods. All aspects of the text analysis pipeline will be covered including data preprocessing, converting text to numeric representations (from simple aggregation methods to more complex embeddings), and training supervised and unsupervised learning methods for standard text-based tasks such as named entity recognition (NER), sentiment analysis, and topic modeling. The course will alternate between presentation and hands-on exercises in Python. Translations from Python to R will be provided for students more comfortable in that language and students can create a project in the language of their choosing, however all illustrative examples will be in Python. Students should be familiar with Python (preferably), R, or both and have a basic understanding of statistics and/or machine learning concepts. In particular, students should have experience applying supervised and/or unsupervised methods, such as regression, classification, dimension reduction, and clustering, and understand how to assess model performance using appropriate metrics. Students will gain the practical skills necessary to begin using text analysis tools for their tasks, an understanding of the strengths and weaknesses of these tools, and an appreciation for the ethical considerations of using these tools in practice.

Previously offered courses:

Interested in using data science to study written information? This course will introduce students to a data science technique called topic modeling that is used in many different contexts to analyze data that is composed of words. Students will learn to preprocess words and texts to prepare them for machine learning models by turning words into numbers that an algorithm can take in and process. Then students will learn to use models that can help you decide how many clusters are appropriate for a particular dataset. Students will characterize clusters by identifying the main intents (actions) in each cluster and the most common entities (words) in that cluster. Finally students will use models to make decisions about how to label each cluster.

All students are welcome – no prerequisites required.

This course will provide a framework to analyze privacy and control of information/big data through the lens of ethical implications of data collection and management. Students will evaluate datasets and relevant case studies to evaluate the broader impact of data science on government policy and society using principles of fairness, accountability and open-data. Students will integrate web scraping and textual analysis to examine the need for transparency while also learning best practices for responsible data management.

No prerequisites required.

A data physicalization (or simply physicalization) is a physical artifact whose materiality encodes data. Data physicalization engages its audience and communicates data using tangible data representations. This course covers topics such as visualization aesthetics, the data-object, data sculptures, critical making and wearable/art technology. Students will analyze current examples of data physicalization, discuss visualization in the context of cultural and historical practice, and evaluate scholarship that recognizes intersections among physicalization, record keeping and data literacy.

No prerequisites required.

Data is a fundamental part of learning more about the most effective ways to improve communities, including learning about what policies work and why. Data Science for Policy will introduce students to the role of data as evidence in the policy process, including identifying cause and effect in complex social environments. Students will discuss the fundamental problem of causal inference, and explore the ways statistical modeling can assist policymakers in identifying effective public policy.

No prerequisites required.

Data science and sustainability are two buzzwords that dominate industry, academia and social sectors. This course will explore the intersectionality of data science and sustainability to solve existential problems facing the modern world. Data science for sustainability will introduce issues like missing data, data availability and small data sets as it relates to climate change, plastic waste, public health and related topics.

No previous programming is required, but it will be fine to use SQL if you have some experience.

In this course, participants will experience a practical approach to employing design thinking, computational thinking and problem solving through data science. Students will be able to enhance their 21st-century skills (communication, collaboration, critical thinking and creativity) and be able to incorporate problem-solving frameworks to solve global challenges that impact the society.

No prerequisites required.

Machine learning (ML) is the “field of study that gives computers the ability to learn without being explicitly programmed.” In this course we will deconstruct the fundamental ideas behind popular ML algorithms, such as logistic regression or k-means, using a projects-center approach. We will draw our projects from successful ML use cases like image recognition and anomaly detection. Each week students will be encouraged to build and tailor the ML projects discussed to their specific domains of interest. Students should have basic knowledge of a programming language, such as appropriate use of data structures, such as lists and matrices, and flow control mechanisms, such as loops. Students should also be familiar with matrix-vector multiplication and the norm of a vector.

Requires some basic programming experience.

This course will explore the methods that are useful for analyzing text as a data source. The course will survey the different goals and questions relating to text, including areas like text processing, morphological analysis, syntactic analysis, lexical analysis, semantics, discourse analysis and text summarization. Students should have basic knowledge of a programming language, such as appropriate use of data structures, such as lists and matrices, and flow control mechanisms, such as loops.

No prerequisites required.

Data analytics represents one of the most competitive and thriving fields within the social sciences. Employers from public, private and nonprofit firms across the country need workers with expertise in this area. In this course, you will learn basic statistical concepts and principles in an applied setting using R, one of the most common statistical software packages. You will run basic statistical analyses using R and, in doing so, you will also learn how to program in R and how to use R for effective data analysis. The course covers practical issues in statistical computing which includes programming in R, reading data into R, accessing R packages, writing R functions, debugging and organizing R code. Topics in statistical data analysis will provide working examples. The class will have mini-projects that lead to a final project.

No programming experience is expected but students are expected to have an understanding of basic descriptive statistics.

There are many layers to consider when trying to guarantee reproducibility of a given program (can you still run a program you wrote years ago without errors?). Package managers (apt-get, pip, etc.) solve part of that problem, but the next step is making a portable recreation of (part of) the OS environment. Docker images package software and their dependencies into just such portable containers. Containerization and container orchestration have become critical tools in software engineering, including machine learning engineering, and are heavily used in industry. In this course we’ll learn the basics of containerization and gain experience running containers locally and in the cloud.

Prerequisites: Familiarity with the Linux command line and bash scripting.

Python is a high-level, interpreted language that has emerged as a power ful tool for scientific computing. This 1-credit course includes exposure to tools in three different areas:

  1. General software development tools, including terminal commands and version control.
  2. Python programming basics, including syntax, object oriented structures, modules and exception handling.
  3. Scientific computing in Python.

Topics include

  • Basics (Variables/Loops/Conditionals/Data Structures)
  • Object-oriented programming
  • Plotting (matplotlib)
  • Scientific computing packages (NumPy/SciPy/Matplotlib/Pandas)

Some higher level programming background (e.g., C++/MATLAB) is desirable.

Social networking sites have quickly become some of the most visited sites on the internet and wield political and economic power that surpasses that of many traditional media institutions. Although these services have democratized expression and provided digital space to build virtual communities, they have also fundamentally modified media consumption and social behavior, potentially exposing users and non-users alike to myriad risks. Students will discuss the socio-cultural impacts of social media and explore the ways in which individual agency is influenced by social media systems and practices.

No prerequisites required.

Visualizations can be one of the most effective means to communicate quantitative information. This course will cover the principles of effective visualization and how to interpret data displays. Students will evaluate current examples in the media and learn tools (such as Excel, Tableau and Gephi) for creating static, interactive and dynamic data displays.

No prerequisites required.

Class Search

Find data science courses in the Class Search tool. Use DSC as the Course Subject.