Course Description
Covering a range of modern approaches for analyzing and interpreting structured and unstructured data commonly encountered in agricultural systems, this course serves as a foundation of descriptive and predictive analytics in the agri- food sciences and provides context for more specialized courses in data analytics.
Athena Title
Applied Agricultural Data Sci
Prerequisite
Permission of department
Semester Course Offered
Offered fall
Grading System
A - F (Traditional)
Course Objectives
Students will be able to: • Appreciate the diversity and value of structured and unstructured data streams in agriscience • Obtain, process, and transform data • Understand and apply diverse types of analytical approaches studying structured and unstructured data • Recognize the strengths and weaknesses of these different approaches • Select the appropriate analytical approach for a given data set • Use programming and software to design and implement data analyses for research questions • Critically evaluate analytical applications in the agriscience literature • Present and interpret analytical results in an ethically responsible and easily understandable manner
Topical Outline
1) The data science process 2) Data types and challenges in agriscience 3) Programming for data analytics 4) Loading, exploring, and managing data 5) Introduction to machine learning 6) Model selection and evaluation 7) Classification: kNN, decision trees, SVM 8) Ensemble methods: random forests 9) Naïve Bayes and logistic regression 10) Clustering: k-means, hierarchical clustering 11) Dimensionality reduction: PCA and SVD 12) Neural networks 13) Text mining and information retrieval 14) Network analysis 15) Procedure for data analysis and delivering results (putting it all together) 16) Applications to agriscience