Glum

------------------

**New features:**

- New argument ``max_inner_iter`` for classes :class:`~glum.GeneralizedLinearRegressor` and :class:`~glum.GeneralizedLinearRegressorCV` to control the maximum number of iterations of the inner solver in the IRLS-CD algorithm.
- New fitted attributes ``col_means_`` and ``col_stds_`` for classes :class:`~glum.GeneralizedLinearRegressor` and :class:`~glum.GeneralizedLinearRegressorCV`.
- :class:`~glum.GeneralizedLinearRegressor` now prints more informative logs when fitting with ``alpha_search=True`` and ``verbose=True``.

**Bug fixes:**

- Fixed a bug where :meth:`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.

------------------

**Bug fix:**

- Fixed :meth:`~glum.GeneralizedLinearRegressor.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.

------------------

**Bug fix:**

- We now support scikit-learn 1.5.

------------------

**Breaking changes:**

- All arguments to :class:`~glum.GeneralizedLinearRegressorBase`, :class:`~glum.GeneralizedLinearRegressor` and :class:`GeneralizedLinearRegressorCV` are now keyword-only.
- All arguments to public methods of :class:`~glum.GeneralizedLinearRegressorBase`, :class:`~glum.GeneralizedLinearRegressor` or :class:`GeneralizedLinearRegressorCV` except ``X``, ``y``, ``sample_weight`` and ``offset`` are now keyword-only.
- :class:`~glum.GeneralizedLinearRegressor`'s default value for ``alpha`` is now ``0``, i.e. no regularization.
- :class:`~glum.GammaDistribution`, :class:`~glum.InverseGaussianDistribution`, :class:`~glum.NormalDistribution` and :class:`~glum.PoissonDistribution` no longer inherit from :class:`~glum.TweedieDistribution`.
- The power parameter of :class:`~glum.TweedieLink` has been renamed from ``p`` to ``power``, in line with :class:`~glum.TweedieDistribution`.
- :class:`~glum.TweedieLink` no longer instantiates :class:`~glum.IdentityLink` or :class:`~glum.LogLink` for ``power=0`` and ``power=1``, respectively. On the other hand, :class:`~glum.TweedieLink` is now compatible with ``power=0`` and ``power=1``.

**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.
- :class:`~glum.InverseGaussianDistribution` gains a :meth:`~glum.InverseGaussianDistribution.log_likelihood` method.

------------------

**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 <https://numpy.org/neps/nep-0029-deprecation_policy.html#support-table>`.
- 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.

------------------

**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:**

- Fixed :meth:`~glum.GeneralizedLinearRegressorBase.covariance_matrix` mutating feature names when called with a data frame. See `here <https://github.com/Quantco/glum/issues/669>`_.

**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).