9 projects
ferrum-viz
Ferrum is a statistical visualization library for Python: a grammar-first charting system that unifies exploratory plots, statistical graphics, interactive views, and model diagnostics, backed by a Rust engine.
imbalanced-losses
imbalanced-losses is a PyTorch library of training losses for class-imbalanced classification — including Focal Loss, Smooth-AP, and Recall-at-Quantile — with built-in DDP all-gather support for globally-correct rank estimation and normalization across multi-GPU training.
seq-explorer
Visualize hidden state evolution in sequence models
step-select
A SciKit-Learn style feature selector using best subsets and stepwise regression.
dpipes
dPipes - Pythonic Data Pipelines
dbrief
Python package for quickly creating lightweight HTML reports
wetsuit
A Scikit-learn style wrapper for H2O estimators.
tsfeast
A collection of Scikit-Learn compatible time series transformers and tools.
