Week 1: R Programming
Prerequisites
- Install R, Positron or RStudio
- Create an account on GitHub, if you don’t have one already
- Join bootcamp GitHub repository (provided via email), say hello in Discussions
- Use Discussions to ask questions
Day 1: Introduction to R
- What to look forward to at the end of the bootcamp
- Introduction to R, Positron IDE
- Basic operations
Day 2: Data types & structures
- Data types & structures
- Indexing
Day 3: Factors & I/O
- Categorical data using factors
- Data I/O: CSV, XLSX, RDS
Day 4: Vectorization & control flow
- Vectorized operations
- Control flow: if/else, for-loops
Day 5: Data summarization & functions
- Data summarization and aggregation
- Functions & scoping
- Apply functions
- 2nd week preview
Week 2: Data Science
Day 1: Terminal & Version control
- Working across interfaces: IDE, terminal, remote shell/SSH into CoreHPC
- Core shell commands (ls, cd, pwd, mkdir, cp, mv, rm)
- RScript
- Project management and collaboration on GitHub
- Intro to git basics: clone, add, commit, push, pull, branch, rebase
Day 2: Probability and Statistics
- Probability
- Statistics
- Hypothesis testing
- Visualization
Day 3: Introduction to Machine Learning
- From hypothesis testing to predictive modeling: samples and resamples (glm -> glmnet)
- Core ML algorithms for classification and regression
- Linear models
- Decision trees and ensembles
- Deep learning (mention)
- Clustering (K-means, hierarchical, etc.)
- Decomposition / dimensionality reduction (PCA, tSNE, UMAP, etc.)
Day 4: Supervised learning
- Designing supervised learning pipelines: Question -> Model
- Preprocessing
- Hyperparameter tuning & resampling for model selection
- Resampling for model evaluation
- Assessing model performance
- Bias-variance tradeoff and model complexity
- Model interpretation (variable importance) and explainability
Day 5: AI
- Effective and responsible use of AI assistants
- Literature search
- Plan study
- Generate, fix, explain code