Skip to content

Changelog

Unreleased

Bug fix:

  • Fixed the check that P2 is positive semi-definite rejecting valid matrices, such as graph Laplacians, whose smallest eigenvalue is zero. The tolerance for eigenvalues that are negative due to rounding errors now scales with the size and magnitude of P2. Also fixed the check crashing for sparse P2 matrices with 2000 or more rows.
  • Fixed the line search of the IRLS solvers rejecting good steps near the optimum of L1-penalized or bounded problems. When the change in the objective was too small to measure, it compared the L1 norm of the gradient, which does not vanish at the optimum of such problems. It now compares the minimum-norm subgradient, the quantity the convergence check uses.

Other changes:

  • Sped up the inner coordinate descent of the irls-cd solver about 3x for float64 and 5x for float32 data, with bitwise identical results. The gradient update after each coordinate move now runs on a contiguous copy of the active set's gradient instead of indexing through the active set, so the compiler vectorizes it.
  • Sped up the irls-cd solver for problems with collinear features, most commonly full one-hot encoded categoricals (drop_first=False, the default) next to an intercept or to each other. Coordinate descent could only creep along the directions in which the model does not change, so inner solves often ran up to max_inner_iter. If an inner solve has not converged after 20 cycles, it now looks for such directions and moves along them exactly. On a Poisson lasso with three 50-level categoricals, this cuts the fit time from 32 seconds to 1.7 seconds, and from 220 seconds to 1.7 seconds with an elastic net penalty. Problems without such directions are not affected.
  • Coordinate descent did not converge warnings now come from the solver instead of the Cython kernel and show the value of max_inner_iter.
  • Declared the Cython extensions free-threading compatible, built free-threaded wheels, and added a py314t test environment.

3.5.0 - 2026-11-16

Bug fix:

  • Fixed categorical_levels_ for polars Categorical columns not matching the design matrix columns. This could cause wrong predictions or errors in predict.
  • Fixed monotonic_constraints raising ValueError when a formula term contains square brackets, e.g. bs(x, knots=[15, 20, 30]).
  • Fixed monotonic_constraints not giving a monotone fitted effect when the first spline basis or categorical level is dropped, e.g. for bs() without include_intercept=True or C() with drop_first=True. Detecting the dropped bs() basis requires tabmat 4.3.0, which records spans_intercept, so the minimum tabmat version is now 4.3.0.
  • Fixed a pandas deprecation warning being emitted before the "unseen categories" ValueError when predicting on data with unseen categories.
  • Fixed the solver for monotonic_constraints comparing objective values computed with different constraint penalties in its line search. This caused spurious "Line search failed" convergence warnings and extra iterations.
  • The "Line search failed" ConvergenceWarning is no longer emitted when the loss no longer changes up to machine precision, since users cannot act on it.
  • Replaced the "Sigmoid function too close to 0 or 1. Clipping." warning of the logit and cloglog links by a warning after the final fit. The old warning was emitted for single observations and intermediate solver iterations, which users cannot act on. The new warning is only emitted if more than 1% of the fitted values are numerically 0 or 1, which typically indicates (quasi-)perfect separation (for the cloglog link, only fitted values of 0 count, because values of 1 are routine). It suggests more regularization or removing the separating features.
  • Fixed tabmat's "Input array is not contiguous; making a copy." warning being emitted for row slices of pandas data frames, e.g. df.iloc[:n], in fit, predict and score. tabmat itself no longer emits this warning after 4.3.1.
  • Fixed monotonic_constraints ordering the levels of an ordered categorical by their label (e.g. alphabetically) instead of by the category order.
  • monotonic_constraints now raises a ValueError for unordered categoricals, and for cr() and cs() splines, instead of silently failing to enforce monotonicity.

Other changes:

  • Removed scikit-learn from build dependencies.
  • Warnings are now treated as errors in the test suite and in the README doctest in CI, except in the nightly and oldies environments.
  • The documentation build now treats warnings as errors and runs in CI. Fixed the docstring formatting of cat_missing_method and get_link and several broken links in the tutorials and the changelog.
  • Require Python>=3.11, since conda-forge no longer supports Python 3.10. No Python 3.10 wheels are built or uploaded to PyPI any more.
  • Added py314 and py315 test environments, and a conda package build for Python 3.15.
  • Removed the py310 test environment and moved the oldies environment and the conda package builds from Python 3.10 to 3.11, since conda-forge no longer supports Python 3.10. The oldies pins for pandas (1.5), scikit-learn (1.1.3) and scipy (1.9) were raised to the oldest releases with Python 3.11 builds.

3.4.1 - 2026-05-06

Bug fix:

  • Fixed monotonic_constraints raising ValueError with drop_first=True on categorical factors.
  • Fixed pickle compatibility for models saved before monotonic_constraints was added.

3.4.0 - 2026-04-27

New feature:

  • Added monotonic_constraints parameter to GeneralizedLinearRegressor and GeneralizedLinearRegressorCV for enforcing monotonic effects on splines, ordered categoricals, and interactions via the formula interface. Uses a new irls-ls-monotonic solver (5-20× faster than trust-constr on insurance benchmark).

3.3.0 - 2026-04-14

New feature:

  • GeneralizedLinearRegressorCV now exposes train_deviance_path_, an array of shape (n_folds, n_l1_ratios, n_alphas) with the training-set deviance.

Other changes:

  • Replaced the hess="2-point" finite-difference Hessian in the trust-constr solver with SR1() (quasi-Newton), significantly speeding up convergence when the number of features is large relative to the number of rows.

3.2.3 - 2026-03-18

Bug fix:

  • Fixed incorrect call in log_likelihood. The previous implementation always returned NaN.

3.2.2 - 2026-03-17

Bug fix:

  • Fixed incorrect formula in inverse_derivative2. This affected observed information matrix computation and robust/clustered standard errors for models using the complementary log-log link.

3.2.1 - 2026-03-16

Bug fix:

  • Fixed an error when predicting at a specific alpha with categorical features.

Other changes:

  • Downgraded log messages in align_df_categories and add_missing_categories from INFO to DEBUG, and deduplicated them so they are emitted only once per column per fitted model.

3.2.0 - 2026-03-10

New features:

  • Add solver="closed-form" for Gaussian identity-link models, using an analytical normal-equations solution for ridge/OLS, auto-selecting it under solver="auto" for unconstrained no-L1 cases, and falling back to least-squares for singular or ill-conditioned systems.
  • GeneralizedLinearRegressor and GeneralizedLinearRegressorCV now accept Polars DataFrames as input, in addition to pandas DataFrames and numpy arrays.

Bug fixes:

  • Fixed predict(X, alpha_index=...) and predict(X, alpha=...) on GeneralizedLinearRegressorCV, which previously raised an error. The CV estimator now refits on the full data over the entire alpha path for the best l1_ratio_.
  • Fixed alpha path computation in GeneralizedLinearRegressorCV: the alpha grid is now computed from the properly standardized feature matrix and per-feature P1 penalties (matching the base class), and accounts for offset when present.

3.1.3 - 2025-02-18

Bug fixes:

Other changes:

  • We disabled fast math to avoid invalid results (e.g., when dividing by zero).
  • The default alpha_max for the regularization path in the pure ridge case (l1_ratio=0) is now computed from the null model gradient, matching glmnet's behavior. Previously it was hardcoded to 10.
  • When min_alpha_ratio is not set and n_samples < n_features, the default is now 1e-2 instead of 1e-6, matching glmnet's convention.

3.1.2 - 2025-01-30

Other changes:

  • Linux-aarch64 wheels are now uploaded to PyPI.

3.1.1 - 2025-01-13

Bug fixes:

  • Fixed a bug where _rowwise_gradient_hessian and _eta_mu_deviance would call functions with wrong arguments in the p = 3 case.
  • Fixed glum.InverseGaussianDistribution not using the optimized gradient, Hessian and deviance implementations, as well as those derivatives having the wrong sign.

Other changes:

  • Build and test with Python 3.13 in CI.

3.1.0 - 2024-11-11

New features:

Bug fixes:

  • Fixed a bug where glum.GeneralizedLinearRegressor.fit would raise a dtype mismatch error if fit with alpha_search=True.
  • Use data type (float64 or float32) dependent precision in solvers.

Other changes:

3.0.2 - 2024-06-25

Bug fix:

  • Fixed wald_test when using terms and no intercept.

Other changes:

  • Moved the development infrastructure to pixi.
  • Moved the linting and formatting to ruff.
  • Removed libblas MKL from the development environment.
  • Replaced deprecated 'oldest-supported-numpy' dependency with 'numpy' to support 2.0 release.

3.0.1 - 2024-05-23

Bug fix:

  • We now support scikit-learn 1.5.

3.0.0 - 2024-04-27

Breaking changes:

New features:

  • Added a formula interface for specifying models.
  • Improved feature name handling. Feature names are now created for non-pandas input matrices too. Furthermore, the format of categorical features can be specified by the user.
  • Term names are now stored in the model's attributes. This is useful for categorical features, where they refer to the whole variable, not just single levels.
  • Added more options for treating missing values in categorical columns. They can either raise a ValueError ("fail"), be treated as all-zero indicators ("zero") or represented as a new category ("convert").
  • meth:GeneralizedLinearRegressor.wald_test can now perform tests based on a formula string and term names.
  • InverseGaussianDistribution gains a log_likelihood method.

2.7.0 - 2024-02-19

Bug fix:

  • Added cython compiler directive legacy_implicit_noexcept = True to fix performance regression with cython 3.

Other changes:

  • Require Python>=3.9 in line with NEP 29.
  • Build and test with Python 3.12 in CI.
  • Added line search stopping criterion for tiny loss improvements based on gradient information.
  • Added warnings about breaking changes in future versions.

2.6.0 - 2023-09-05

New features:

  • Added the complementary log-log (cloglog) link function.
  • Added the option to store the covariance matrix after estimating it. In this case, the covariance matrix does not have to be recomputed when calling inference methods.
  • Added methods for performing Wald tests based on a restriction matrix, feature names or term names.
  • Added a method for creating a coefficient table with confidence intervals and p-values.

Bug fix:

Other changes:

  • When computing the covariance matrix, check whether the design matrix is ill-conditioned for all types of input. Furthermore, do it in a more efficient way.
  • Pin tabmat<4.0.0 (the new release will bring breaking changes).

2.5.2 - 2023-06-02

Bug fix

  • Fix the glm_benchmarks_analyze command line tool. See here.
  • Fixed a bug in GeneralizedLinearRegressor when fit on a data set with a constant column and warm_start=True. See here.

Other changes:

  • Remove dev dependency on dask_ml.
  • We now pin llvm-openmp=11 when creating the wheel for macOS in line with what scikit-learn does.

2.5.1 - 2023-05-19

Other changes:

  • Better error message when the number of input features is different between the fit and predict methods.

Bug fix:

  • We fixed a bug in the computation of log_likelihood. Previously, this method just returned None.

2.5.0 - 2023-04-28

New feature:

2.4.1 - 2023-03-14

Bug fixes:

  • Fixed an issue with _score_matrix which failed when called with a tabmat matrix input.

Other changes:

  • Removes unused scikit-learn cython imports.

2.4.0 - 2023-01-31

Other changes:

  • LogitLink has been made public.
  • Apple Silicon wheels are now uploaded to PyPI.

2.3.0 - 2023-01-06

Bug fixes:

  • A data frame with dense and sparse columns was transformed to a dense matrix instead of a split matrix by _set_up_and_check_fit_args. Fixed by calling tabmat.from_pandas on any data frame.

New features:

2.2.1 - 2022-11-25

Other changes:

  • Fixing pypi upload issue. Version 2.2.0 will not be available through the standard distribution channels.

2.2.0 - 2022-11-25

New features:

Bug fixes:

  • Setting bounds for constant columns was not working (bounds were internally modified to 0). A similar issue was preventing inequalities from working with constant columns. This is now fixed.

Other changes:

  • No more builds for 32-bit systems with python >= 3.8. This is due to scipy not supporting it anymore.

2.1.2 - 2022-07-01

Other changes:

  • Next attempt to build wheel for PyPI without --march=native.

2.1.1 - 2022-07-01

Other changes:

  • We are now building the wheel for PyPI without --march=native to make it more portable across architectures.

2.1.0 - 2022-06-27

New features:

Bug fixes:

Other:

  • The CI now runs daily unit tests against the nightly builds of numpy, pandas and scikit-learn.
  • The minimally required version of tabmat is now 3.1.0.

2.0.3 - 2021-11-05

Other:

  • We are now specifying the run time dependencies in setup.py, so that missing dependencies are automatically installed from PyPI when installing glum via pip.

2.0.2 - 2021-11-03

Bug fix:

  • Fixed the sign of the log likelihood of the Gaussian distribution (not used for fitting coefficients).
  • Fixed the wide benchmarks which had duplicated columns (categorical and numerical).

Other:

  • The CI now builds the wheels and upload to pypi with every new release.
  • Renamed functions checking for qc.matrix compliance to refer to tabmat.

2.0.1 - 2021-10-11

Bug fix:

  • Fixed pyproject.toml. We now support installing through pip and pep517.

2.0.0 - 2021-10-08

Breaking changes:

New features:

Bug fix:

Other:

  • A major overhaul of the documentation. Everything is better!
  • The methods of the link classes will now return scalars when given scalar inputs. Under certain circumstances, they'd return zero-dimensional arrays.
  • There is a new benchmark available glm_benchmarks_run based on the Boston housing dataset. See here.
  • glm_benchmarks_analyze now includes offset in the index. See here.
  • glmnet_python was removed from the benchmarks suite.
  • The innermost coordinate descent was optimized. This speeds up coordinate descent dominated problems like LASSO by about 1.5-2x. See here.

1.5.1 - 2021-07-22

Bug fix:

1.5.0 - 2021-07-15

New features:

Other:

  • Methods of Link now consistently return NumPy arrays, whereas they used to preserve pandas series in special cases.
  • Don't list sparse_dot_mkl as a runtime requirement from the conda recipe.
  • The minimal numpy pin should be dependent on the numpy version in host and not fixed to 1.16.

1.4.3 - 2021-06-25

Bug fix:

  • copy_X = False will now raise a value error when X has dtype int32 or int64. Previously, it would only raise for dtype int64.

1.4.2 - 2021-06-15

Tutorials and documentation improvements:

  • Adding tutorials to the documentation.
  • Additional documentation improvements.

Bug fix:

  • Verbose progress bar now working again.

Other:

  • Small improvement in documentation for the alpha_index argument to predict.
  • Pinned pre-commit hooks versions.

1.4.1 - 2021-05-01

We now have Windows builds!

1.4.0 - 2021-04-13

Deprecations:

  • Fusing the alpha and alphas arguments for GeneralizedLinearRegressor. alpha now also accepts array like inputs. alphas is now deprecated but can still be used for backward compatibility. The alphas argument will be removed with the next major version.

Bug fix:

  • We removed entry points to functions in glum_benchmarks from the conda package.

1.3.1 - 2021-04-12

Bug fix:

  • glum._distribution.unit_variance_derivative is evaluating a proper numexpr expression again (regression in 1.3.0).

1.3.0 - 2021-04-12

New features:

  • We added a new solver based on scipy.optimize.minimize(method='trust-constr').
  • We added support for linear inequality constraints of type A_ineq.dot(coef_) <= b_ineq.

1.2.0 - 2021-02-04

We removed glum_benchmarks from the conda package.

1.1.1 - 2021-01-11

Maintenance release to get a fresh build for OSX.

1.1.0 - 2020-11-23

New feature:

  • Direct support for pandas categorical types in fit and predict. These will be converted into a CategoricalMatrix.

1.0.1 - 2020-11-12

This is a maintenance release to be compatible with tabmat>=1.0.0.

1.0.0 - 2020-11-11

Other:

0.0.15 - 2020-11-11

Other:

  • Pin tabmat<1.0.0 as we are expecting a breaking change with version 1.0.0.

0.0.14 - 2020-08-06

New features:

  • Add Tweedie Link.
  • Allow infinite bounds.

Bug fixes:

  • Unstandardize regularization path.
  • No copying in predict.

Other:

  • Various memory and performance improvements.
  • Update pre-commit hooks.

0.0.13 - 2020-07-23

See git history.

0.0.12 - 2020-07-07

See git history.

0.0.11 - 2020-07-02

See git history.

0.0.10 - 2020-06-30

See git history.

0.0.9 - 2020-06-26

See git history.

0.0.8 - 2020-06-24

See git history.

0.0.7 - 2020-06-17

See git history.

0.0.6 - 2020-06-16

See git history.

0.0.5 - 2020-06-10

See git history.

0.0.4 - 2020-06-08

See git history.

0.0.3 - 2020-06-08

See git history.