38 projects
reporoulette
Random sampling of GitHub repositories using multiple methods
get-weather-data
Get historical weather data for US ZIP codes from NOAA stations
allocator
Modern Python package for geographic task allocation, clustering, and routing optimization
preclink
High-precision record linkage library with multi-pass support
understudy
Simulation and trace-based evaluation for agentic systems
xyzzy123pkg-test-delete-me
Test package - please delete
hbw
Fast kernel bandwidth selection via analytic Hessian Newton optimization
setjoin
Set-aware record linkage with structure-preserving joins
onlinerake
Streaming survey raking via SGD and MWU
streamcal
Streaming probability calibration via multiplicative weights
rank-preserving-calibration
Rank-preserving calibration of multiclass probabilities via Dykstra's projections and ADMM.
stable-cart
Unified stable CART decision trees with 7 stability primitives and cross-method learning for enhanced prediction stability.
winference
Win rate calibration under non-transitivity via Hodge decomposition and heterogeneous group testing
slosizer
Capacity planning for reserved LLM throughput: latency, headroom, and synthetic workload simulation.
rmcp
Comprehensive Model Context Protocol server with 52 statistical analysis tools for Claude Desktop and Claude web, featuring HTTP transport, interactive documentation, and production deployment
fairlex
Leximin calibration for survey weights
lost-years
Get Expected Number of Years Lost
preen
An opinionated, agentic CLI for Python package hygiene and release
statqa
Automatically extract structured facts, insights, and Q/A pairs from tabular datasets
fewlab
Pick the fewest items to label for unbiased OLS on shares
calibre
Advanced probability calibration techniques for machine learning models
optimal-classification-cutoffs
Utilities for computing optimal classification cutoffs for binary and multiclass classification
hessband
Analytic-Hessian bandwidth selection for univariate kernel regression
layoutlens
AI-powered UI testing framework with natural language visual validation
pyppur
Advanced Projection Pursuit implementation with tied/untied weights, nonlinear/linear distance distortion, and comprehensive documentation
stagecoachml
A library for two-stage machine learning models with staggered feature arrival
incline
Estimate Trend at a Particular Point in a Noisy Time Series
indicate
Transliterations to/from Indian languages
notnews
Predict Soft News
softverse
Auto-compute Citations to Software From Replication Files
rowvoi
Interactive disambiguation of rows in a dataset using value-of-information policies
geo-sampling
Scripts for sampling Geo data sets by the specific region name
paper-voice
Convert academic papers to high-quality audio with precise mathematical explanations and intelligent content processing
zerottmm
Time‑to‑Mental‑Model: a local‑first code reading assistant (Phase A)
alsgls
Lightweight low-rank+diag GLS/SUR via ALS with EM baseline
pip-fund
Enumerate funding links for Python packages
repaper
Convert form based PDF documents to web based froms or editable pdf forms.
kahipwrapper
KaHIP Python Wrapper
