The author discusses a shift in approach to clustering mixed data, advocating for starting with the simpler Gower distance metric before resorting to more complex embedding techniques like UMAP. They introduce 'Gower Express', an optimized and accelerated implementation of Gower.
This article details a hands-on approach to modeling rare events in time series data using Python. It covers data exploration, defining extreme events, fitting distributions (GEV, Weibull, Gumbel), and evaluating model performance using metrics like log-likelihood, AIC, and BIC. The example uses weather data and provides code snippets for implementation.
This article explores the impact of hyperparameters on random forests, both in terms of performance and visual representation. It compares the performance of a default random forest with tuned decision trees and examines the effects of various hyperparameters like `n_estimators`, `max_depth`, and `ccp_alpha` using visualizations of individual trees, predictions, and errors.
The fast, feature-rich, GPU based terminal emulator. It's capable, scriptable, composable, cross-platform, and innovative.
An open source web crawler that searches the internet. It's a minimal, real-time web search CLI that searches the internet for you. Enter a query and get search results as JSON (title, url, published_date), sorted by recency.
frozen-in-time version of our Paper Finder agent for reproducing evaluation results. This repo contains the code for the standalone Paper Finder agent. PaperFinder is our paper-seeking agent, which is intended to assist in locating sets of papers according to content-based and metadata criteria.
This GitHub repository directory contains resources for evaluating Large Language Models (LLMs), including a Jupyter Notebook demonstrating how to use LLM Arena as a judge and a Python script for the same purpose. It also includes a README file with instructions on how to view the notebook if it doesn't render correctly on GitHub.
Learn how to connect several essential tools to develop a simple yet intuitive dashboard using Streamlit, Plotly, DuckDB, and Pandas to visualize data from a JSON file.
A technical article explaining how a small change in async Python code—using a semaphore to limit concurrency—reduced LLM request volume and costs by 90% without sacrificing performance.
An extremely lightweight universal grammar implementation with provable recursion, based on Chomsky's Minimalist Grammar theory, fitting in under 50kB with zero runtime dependencies. It includes a probabilistic language model extension and formal verification.
