glum 2.0.0

Breaking changes:

• Renamed the package to glum!!! Hurray! Celebration.
• GeneralizedLinearRegressor and GeneralizedLinearRegressorCV lose the fit_dispersion parameter.
  Please use the dispersion method of the appropriate family instance instead.
• All functions now use sample_weight as a keyword instead of weights, in line with scikit-learn.
• All functions now use dispersion as a keyword instead of phi.
• Several methods GeneralizedLinearRegressor and GeneralizedLinearRegressorCV that should have been private have had an underscore prefixed on their names: tear_down_from_fit, _set_up_for_fit, _set_up_and_check_fit_args, _get_start_coef, _solve and _solve_regularization_path.
• glum.GeneralizedLinearRegressor.report_diagnostics and glum.GeneralizedLinearRegressor.get_formatted_diagnostics are now public.

New features:

• P1 and P2 now accepts 1d array with the same number of elements as the unexpanded design matrix. In this case,
  the penalty associated with a categorical feature will be expanded to as many elements as there are levels,
  all with the same value.
• ExponentialDispersionModel gains a dispersion method.
• BinomialDistribution and TweedieDistribution gain a log_likelihood method.
• The fit method of GeneralizedLinearRegressor and GeneralizedLinearRegressorCV
  now saves the column types of pandas data frames.
• GeneralizedLinearRegressor and GeneralizedLinearRegressorCV gain two properties: family_instance and link_instance.
• GeneralizedLinearRegressor.std_errors and GeneralizedLinearRegressor.covariance_matrix have been added and support non-robust, robust (HC-1), and clustered
  covariance matrices.
• GeneralizedLinearRegressor and GeneralizedLinearRegressorCV now accept family='gaussian' as an alternative to family='normal'.

Bug fix:

• The score method of GeneralizedLinearRegressor and GeneralizedLinearRegressorCV now accepts data frames.
• Upgraded the code to use tabmat 3.0.0.

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.

quantcore.glm 1.5.1

1.5.1 - 2021-07-22

Bug fix:

• Have the linear_predictor and predict methods of GeneralizedLinearRegressor and GeneralizedLinearRegressorCV honor the offset when alpha is None.

quantcore.glm 1.5.0

1.5.0 - 2021-07-15

New features:

• The linear_predictor and predict methods of quantcore.glm.GeneralizedLinearRegressor and quantcore.glm.GeneralizedLinearRegressorCV gain an alpha parameter (in complement to alpha_index). Moreover, they are now able to predict for multiple penalties.

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.

quantcore.glm 1.4.3

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.

quantcore.glm 1.4.2

1.4.2 - 2021-06-15

Tutorials and documenation 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 :func:quantcore.glm.GeneralizedLinearRegressor.predict.
• Pinned pre-commit hooks versions.

quantcore.glm 1.4.1

1.4.1 - 2021-05-01

We now have Windows builds 🚀

quantcore.glm 1.4.0

1.4.0 - 2021-04-13

Deprecations:

• Fusing the alpha and alphas arguments for quantcore.glm.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.

Other:

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

quantcore.glm 1.3.1

1.3.1 - 2021-04-12

Bug fix:

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

quantcore.glm 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.

quantcore.glm 1.2.0

1.2.0 - 2021-02-04

We removed quantcore.glm_benchmarks from the conda package.