.. currentmodule:: halerium ========= Release Notes ========= 3.3.1 ===== released on 2022-06-14 - fixed multiple bugs when using the distributions added in v. 3.3.0 with the `connect_via_regression` function. - fixed import bug for `print_child_tree` and `print_operand_tree`. - fixed a scoping error when supplying a variable as kernel to the `construct_gaussian_process` function. 3.3.0 ===== released on 2022-05-31 - new distributions (not all new distributions support all inference methods) - Catergorical distribution (Multinoulli) - Poisson distribution - Exponential distribution - Laplace distribution - models now accept initial values 3.2.1 ===== released on 2021-08-12 - fixed a bug that caused long model build times for deep graphs - technical adaptions of :func:`~show` function for the new halerium platform 3.2.0 ===== released on 2021-07-01 - Time Series modeling - introducing the :class:`~.core.operator.TimeShift` operator and the ``TimeIndex``, which allow the user to breach the conditional independence along the data axis to build time series graphs, where variables can depend on their own past. - Gaussian processes - introducing the :func:`~.core.template.construct_gaussian_process` factory to create correlated Gaussian processes. - Metric Gaussian Variational Inference - improved the convergence behavior of the :class:`~.core.model.MGVIModel` and added the methods :meth:`~.core.model.MGVIModel.update_lbfgs` and :meth:`~.core.model.MGVIModel.update_ngd` for better manual control of model solving. 3.1.0 ===== released on 2021-05-07 - Causal calculus - introducing the :func:`~.core.do_operation`, which transforms a :class:`~core.Graph` or other scopetor by applying the do operation to one or more of its variables. - introducing the :class:`InterventionPredictor` objective which calculates predictions for mixes of observations and interventions. - added features in the :class:`~CausalStructure` class - more convenient objective calls - every objective now has its own method in the CausalStructure class. The new methods are: - :meth:`~CausalStructure.estimate_influences` - :meth:`~CausalStructure.evaluate` - :meth:`~CausalStructure.detect_outliers` - :meth:`~CausalStructure.estimate_ranks` - :meth:`~CausalStructure.estimate_probabilities` - :meth:`~CausalStructure.predict_interventions` - CausalStructure instances can be saved and loaded as json specifications, see - :meth:`~CausalStructure.dump_dict` - :meth:`~CausalStructure.dump_file` - :meth:`~CausalStructure.dump_string` - :meth:`~CausalStructure.from_specification` - Gaussian process regression (:func:`~.core.regression.gaussian_process_regression`) - better construction of the posterior graph for Gaussian process regression - Bugfixes: - specification json files created in python 3.8 could not be loaded in python 3.7 due to the upgrade of the pickle version. The pickle version is now set to 4 to ensure compatibility. - fixed a bug that cause false alerts in cyclic dependency checks. - fixed a bug, where the ADVI model failed for Dirac distributed Variables. - fixed a bug in the conjugate gradient implementation that affected the performance of the MGVIModel and the MAPFisher model