JUST WHATEVER

• Network Scale Up for estimating the size of hard-to-reach subpopulations: simulations and models for estimating population sizes via indirect survey
• GNU tools for data analysts: Introducing some of the GNU utilities in a Unix terminal by way of analogies to the verbs of SQL, dplyr, etc.
• Branch and bound using lazily evaluated lists: Implementing a branch-and-bound solver for the knapsack problem using lazily evaluated lists, and comparing performance of different approximation algorithms.
• Population inferences from incomplete and biased data: Using multiple systems estimation techniques to make defensible inferences about a population when our data is incomplete and/or biased.
• Searching for Ramanujan’s taxicab numbers: Trying to find numbers that can be expressed as the sum of two positive cubes in two different ways.
• Solving the 8-puzzle with lazy evaluation: Solving a popular tile-based game using lazily evaluated lists.
• Building a stack data structure with functions: Understanding functions, closures, and environments by implementing a stack.
• Grouping Stack Overflow question tags: Thinking of database tables as sparse matrices allows us to do big matrix multiplications without access to much memory. One use case is to group large numbers of user-generated tags.
• Creating dot-density plots: Using census demographic data to create dot-density plots of educational attainment in Alameda County.
• Generating fake names that sound real(ish): Building models to generate first names that don’t appear in the training data, but sound real.
• Playing the median game: Experimenting with strategies to play the median game.
• Learning from ants: Modeling a colony of ants in order to attack the Travelling Salesperson Problem.
• Estimating the number of jelly beans in the jar: Using the mark-and-recapture method to estimate the number of jelly beans in a jar.