Review: Build Your Own LLM Workshop
Last Saturday I attended a full-day “How to Build Your Own LLM Workshop,” hosted by Rally SF at The Commons. The course was taught by Justin Angel. Here’s my review.
Emily Hough-Kovacs
Data Scientist
Latest posts
Probability: Expectation, Variance, and Conditional Probability
Welcome back! Today we’ll dive into some basic probability concepts, like expectation and variance, and explore conditional probability. I’ll probably write further on more probability concepts in another post, but for now we’ll start with these foundational ones.
Hypothesis Testing: Assumptions and Non-Parametric Tests
Welcome back! Today we are going to go over some assumptions we’ve made so far which has allowed us to use the tests introduced in Parts 1, 2, and 3. Then, we’ll go over what to do when those assumptions are not met and some alternative tests we can use.
Hypothesis Testing: Proportion Tests Without Bootstrapping and Chi-Squared Tests
Welcome back! Today we are going to go back to the proportion testing we did in part 1, but use a workaround to avoid having to bootstrap. Then, we’ll extend our proportion tests to more than two groups using the Chi-Square test of independence. Finally, we’ll use the Chi-Square goodness-of-fit test to compare a distribution of proportions to a hypothesized distribution.
Hypothesis Testing: T-Tests, ANOVA, and Paired T-Tests
Welcome back! In this post, we are building on our previous knowledge to expand our hypothesis testing practices to three new types of tests: the t-test, ANOVA, and the paired t-test. I’ll go through how to perform each of these tests and when to use them.
Hypothesis Testing: Testing Proportions and Types of Errors
Welcome back! Today we are going through an introduction to hypothesis testing with an example use case of comparing a proportion to a hypothesized value. We will go over calculating the z-score, p-value, and evaluating whether the test was a success or not. We will also cover Type I and Type II errors.
Using LaTeX in Jekyll with MathJax
You may have noticed that my last blog post had some LaTeX-looking formulae formatted all nicely inline. This, sadly, took me the better part of the last few hours which only took away from my actual studying time, so I figured a blog post was in order to save everyone else the headache. To do this, I combed through multiple Stack Overflow pages and blog posts, but what ultimately saved me was…
Sampling and Bootstrapping
The first topic I wanted to review was sampling methods, particularly resampling. For the purposes of this post, I’ll be reviewing the entirety of the topics presented in the DataCamp course Sampling in Python, which touches on sampling, resampling (or sampling with replacement), selection bias, sample size and population parameters, the Central Limit Theorem, bootstrapping, standard error, and…
Prepping for the Google Product Analyst Interview
Well, it’s certainly been awhile (six years?!) since I’ve written in this blog. The last time I wrote, I was wrapping up my time at the data science bootcamp, Metis. Since then, I’ve worked at Spotify for five years with a short stint at Universal Music Group after that. Now I’m interviewing for the Product Analyst: Data Science role at Google and in preparation for the technical screen, I’d like…
Iterative Improvements
One takeaway that I really gained first-hand from working on my most recent project is the concept of iterative improvements. In the past, I have always seen iterative software development as a barrier to accomplishment, because I struggled to consider work ‘finished’ until it was packaged in a convenient, ready-to-go takeaway. Palantir’s guiding principle states it nicely by quoting Frederick P.…