Rotate columns to right by shift.

:param X: data points np array with (1, n_var) or (n_sample, n_var) :param W: weights np array with (1, n_var) or (n_sample, n_var) :pa

Construct SQL conditions for a query based on rowid and additional conditions. Parameters ---------- rowid: int/list

Global registry of hyperparams. Each entry is a (default, random) tuple. New algorithms / networks / etc. should add entries here.

Predict functions distribution(s) for given test point(s) without taking into account data normalization. If `self._normalize` is `False`, ret

Calculate pairwise distances between configurations. Parameters: X (np.ndarray): Encoded data matrix. Returns:

Check if a certain database table exists.

Convert maximization to minimization. Example usage: Y = np.array([[1, 4, 3], [2, 1, 4], [3, 2, 2]]) obj_type = ['min', 'max', 'min'

Returns a dictionary of hyperparameter spaces for the given algorithm and dataset. Each entry is a tuple of (type, range) where type is 'floa

Get the current state of the surrogate. Returns: current_state: A dictionary that represents the current

Loads dataset from OpenML in config_file.data_directory. Downloads data if necessary. Returns ------- X_trai

Helper function to replace nan values in categorical features / columns by a non-used value. Here: Min - 1.

Create the optimizer object.

The constructor for the DyHPO model. Args: configuration: The configuration to be used for the different

Helper function to cast ``rng`` from int to np.random.RandomState if necessary. Parameters ---------- rng : int, np.random.RandomSta

Check whether dir exists and if not create it

Determine the difference between given y-values and the sum of predicted values from the models in 'source_gps'. Args: da

Create the scikit-learn (training-)pipeline

Create the scikit-learn (training-)pipeline

Helper-function to load the data from the OpenML website.

Aggregates a list of importance dataframes by taking the mean of importance scores across all repetitions.

two lists y0,z0 are the same if the same patterns can be seen in all of them, as well as in 100s to 1000s sub-samples from each. From p220 t

Calculate hypervolume Example usage: Y = np.array([[1, 2], [2, 1], [1.5, 1.5]]) ref_point = np.array([2.5, 2.5]) hypervolume = c

calculate pareto hypervolume Parameters ---------- y : numpy.array output data w_ref : numpy.array reference poi

By pre-soring the lists, this cliffsDelta runs in NlogN time