deephyper.skopt.utils#
Submodule of utility functions for skopt.
Functions
Check whether all dimensions have names. |
|
Check whether all elements of a list x are of the correct type(s). |
|
Cook a default estimator. |
|
Cook a default initial point generator. |
|
Prepare a Scikit-Learn preprocessing pipeline to transform the objective. |
|
Initialize an OptimizeResult object. |
|
Deep copy operation on arbitrary Python objects. |
|
Convert a dict representation of a search space into a list of dimensions. |
|
Store an skopt optimization result into a file. |
|
Evaluate list of callbacks on result. |
|
Compute the minimum over the predictions of the last surrogate model. |
|
Minimum search by doing naive random sampling. |
|
Check if an estimator's |
|
Reconstruct a skopt optimization result from a file persisted with |
|
Create a |
|
Convert a list representation of a point from a search space to a dictionary representation. |
|
Convert a dictionary representation of a point from a search space to a list representation. |
|
Decorator. |
|
Decorator factory to apply update_wrapper() to a wrapper function |
Classes
Base class for search space dimensions. |
|
ExtraTreesRegressor that supports conditional standard deviation. |
|
GaussianProcessRegressor that allows noise tunability. |
|
Predict several quantiles with one estimator. |
|
Generate samples from a regular grid. |
|
Creates Halton sequence samples. |
|
Creates Hammersley sequence samples. |
|
The HammingKernel is used to handle categorical inputs. |
|
Latin hypercube sampling |
|
Dictionary that remembers insertion order |
|
RandomForestRegressor that supports conditional std computation. |
|
Generates a new quasirandom Sobol' vector with each call. |
|
Initialize a search space from given specifications. |