20 projects
ds-workspace-mcp
A Model Context Protocol server for safely inspecting and profiling local analytical datasets.
population-resemblance
Statistically principled monitoring of categorical population and distribution shifts.
abstract-extract
Typed Python utilities for retrieving and normalizing scholarly abstracts from Scopus and Crossref.
drift-or-shift
Label shift vs. concept drift: Bayes-optimal offset correction, calibration, and drift diagnostics.
subspaceknn
Interpretable k-nearest-neighbour classification by complementary selection of low-dimensional feature subspaces.
DataExcept
A Python package providing structured, easily-extendable custom exception types.
imputation-methods
A unified pandas API for 40+ missing-data imputation methods: statistical, time-series, regression, ensemble and matrix-completion.
pygeostats
Geostatistics for Python with a Rust-accelerated core: variograms, kriging, point patterns and spatial autocorrelation
industrialstats
Industrial statistics and design of experiments for Python
cfad
Research software for ECF-based distributional change analysis in financial returns
anomalybench
Benchmarking suite for anomaly detection algorithms.
oversampleqa
A diagnostic toolkit to validate oversampling methods.
heavytails
Heavy-tailed probability distributions for research, teaching, and simulation.
gen-surv
Simulate survival data with a known truth: twelve models spanning proportional hazards, accelerated failure time, competing risks, cure fractions, recurrent events and multi-state processes
sensor-modeling
Interpretable, probabilistic, privacy-preserving multimodal ambient sensing for behavioural research
wifi-activity-recognition
A comprehensive Python package for human activity recognition using WiFi CSI and computer vision
tscv-vision
Structured representation engineering for time series (NumPy-first).
pinnlab
Physics-Informed Neural Network implementations
setqca
Native Python toolkit for crisp-set and fuzzy-set Qualitative Comparative Analysis
pinn-rk
Runge–Kutta Physics-Informed Neural Networks with time-discrete losses (Gauss/Radau/Lobatto) in PyTorch.
