Timeplan 2024 Vår - lærer Daniel Kumazawa Morais -

• Course introduction – Data science: structure and use cases. - 1h theory
• BarentsWatch practical use in Norway’s aquaculture – Lecture by Alf-Martin Søllund from the Barents Watch Open Information System - 1h seminar

First assignment handout: build a basic Linux script (input and output)

• Statistics and data science (experimental statistics refresh) - 2h theory
• Introduction to basic R and R-Studio – 2h practice

2 hours practice

• Basic navigation inside the Linux environment
• Linux command syntax
• File and directory manipulation

Second assignment handout: Reproduce RStudio data treatment as a script in Linux.

• Structuring data. 2h theory
  • Main tidyverse functions for parsing and grouping data

• Types of data. Filtering and Reformatting - Tidyverse. 2h practice
• Using R scripts for data manipulation in Linux (TA) – 1.5h practice
  • Third assignment: Create a R-toolbox for filtering and reformatting tables and make a Linux pipeline.

• Plotting tools for exploring big data. Plot use cases for different types of data. 2h theory

• Plotting tools for exploring big data. Plot use cases for different types of data. 2h theory
• The Grammar of Graphics (ggplot2). 2h practice

• Apply plotting scripts to generate PDFs with useful graphs (TA) – 1.5h practice
  • Forth assignment: Create a R script for making PDF files with data exploration graphs and execute this script from the Linux command line.

• Descriptive vs inferential statistics. Correlation. Frequentist vs Bayesian inference. Introduction to Machine Learning approaches. 4h theory

• Introduction to tidy models and machine learning using R. 4h practice

• Export model assessment data using R and Linux (TA) - 1.5h practice
  • Fifth assignment: Create a Linux script for exporting the model quality information graphs and indices and interpret the outcomes.

• Knowledge base management – Lecture by Xavier Pivan, Data Scientist and Oceanographer at HUB Ocean

The role of genetics data in fisheries, aquaculture, and conservation.

• Defining management units.
• Decision-making in environmental management.