Data Science (DS)
DS 101, +EXPLORING CAREERS IN DATA SCIENCE, 1 Credit
Explore the Data Science major and the interdisciplinary options within the major. Examine career goals and pathways to data science careers. Explore the concept of professional development. Expose students to data science applications in various fields and prepare them to be critical thinkers of future career paths.
Attributes: CSC1 – Core Ed - Beyond OSU Career Preparation
Prerequisite: SCI 100 (may be taken concurrently) with D- or better or SCI 300 (may be taken concurrently) with D- or better or CORE 100 (may be taken concurrently) with D- or better or CORE 300 (may be taken concurrently) with D- or better or BA 100 (may be taken concurrently) with D- or better or BA 300 (may be taken concurrently) with D- or better or ENGR 110 (may be taken concurrently) with D- or better or ENGR 110H (may be taken concurrently) with D- or better or ENGR 310 (may be taken concurrently) with D- or better or LA 100 (may be taken concurrently) with D- or better or LA 300 (may be taken concurrently) with D- or better or ED 100 (may be taken concurrently) with D- or better or ED 300 (may be taken concurrently) with D- or better or Baccalaureate Core Student with a score of 1
DS 201, INTRODUCTION TO DATA SCIENCE, 4 Credits
Explores the data life cycle which includes how data are created, collected, imported, described, used and analyzed. Considers how data are used properly and ethically. Examines regression and classification methods, experiments with basic tools in Python, and compares output between regression and classification models. Provides a brief overview of recent data science trends, including its societal impact and limitations.
Recommended: High School Algebra
DS 231, PYTHON PROGRAMMING FOR DATA SCIENCE, 4 Credits
Focuses on learning Python programming essential for data science. Explores Python's data types and associated methods. Learns to load, clean, merge, transform, and plot data. Develops skills to write Python functions to solve simple problems arising in data science. Gains proficiency with key libraries like Pandas, NumPy, and matplotlib. Adopts best practices for creating reproducible and efficient code.
Prerequisite: DS 201 with D- or better and MTH 267 [D-]
DS 431, STATISTICAL LEARNING FOR DATA SCIENCE, 3 Credits
Introduces supervised and unsupervised machine learning methods, including linear and nonlinear regression methods, model selection techniques, regularization, tree-based methods, support vector machines, and clustering. Situates these methods within a probabilistic statistical framework. Examines how to compare and assess the performance of prediction and classification methods. Provides the tools to apply these methods in the Python programming language and interpret their output.
Prerequisite: ST 412 with D- or better and ST 421 [D-] and DS 231 [D-]
DS 451, METHODS OF DATA ANALYSIS FOR COMPLEX AND NETWORK DATA, 3 Credits
Focuses on data analysis methods for complex, heterogeneous, and multi-modal data, including network, image, text, and dependent data. Covers building distributed data analysis pipelines, developing neural network models, and applying techniques for network and dependent data analysis. Explores key tools and frameworks in R and Python to design and implement comprehensive analysis pipelines for modern data challenges.
Prerequisite: DS 431 with D- or better
DS 453, BAYESIAN MODELS FOR DATA SCIENCE, 4 Credits
Introduces main concepts of Bayesian analysis from the statistical foundations to model implementation. Reviews and implements a variety of widely used models from a Bayesian perspective including linear regression, Poisson and Negative Binomial regression, and logistic regression. Emphasizes the computational implementation of these models and discusses numerical approximations for posterior inference, including Markov Chain Monte Carlo approaches.
DS 455, CAUSAL INFERENCE FOR EXPERIMENTAL AND OBSERVATIONAL DATA, 3 Credits
Imparts methods to make causal conclusions from data. Builds foundations of causal inference for randomized trials through the perspective of potential outcomes. Extends this foundation to causal inference for observational studies. Develops methodologies for causal inference using regression modeling of real and simulated data for randomized experiments and observational studies.
DS 553, BAYESIAN MODELS FOR DATA SCIENCE, 4 Credits
Introduces main concepts of Bayesian analysis from the statistical foundations to model implementation. Reviews and implements a variety of widely used models from a Bayesian perspective including linear regression, Poisson and Negative Binomial regression, and logistic regression. Emphasizes the computational implementation of these models and discusses numerical approximations for posterior inference, including Markov Chain Monte Carlo approaches.