The Gaussian process algorithm for regression.

Overview

The Gaussian process regression (GPR) surrogate model expresses the model output as a weighted sum of kernel functions centered on the learning input data:

\[y = \mu + w_1\kappa(\|x-x_1\|;\epsilon) + w_2\kappa(\|x-x_2\|;\epsilon) + ... + w_N\kappa(\|x-x_N\|;\epsilon)\]

Details

The GPR model relies on the assumption that the original model \(f\) to replace is an instance of a Gaussian process (GP) with mean \(\mu\) and covariance \(\sigma^2\kappa(\|x-x'\|;\epsilon)\).

Then, the GP conditioned by the learning set \((x_i,y_i)_{1\leq i \leq N}\) is entirely defined by its expectation:

\[\hat{f}(x) = \hat{\mu} + \hat{w}^T k(x)\]

and its covariance:

\[\hat{c}(x,x') = \hat{\sigma}^2 - k(x)^T K^{-1} k(x')\]

where \([\hat{\mu};\hat{w}]=([1_N~K]^T[1_N~K])^{-1}[1_N~K]^TY\) with \(K_{ij}=\kappa(\|x_i-x_j\|;\hat{\epsilon})\), \(k_i(x)=\kappa(\|x-x_i\|;\hat{\epsilon})\) and \(Y_i=y_i\).

The correlation length vector \(\epsilon\) is estimated by numerical non-linear optimization.

Surrogate model

The expectation \(\hat{f}\) is the GPR surrogate model of \(f\).

Error measure

The standard deviation \(\hat{s}\) is a local error measure of \(\hat{f}\):

\[\hat{s}(x):=\sqrt{\hat{c}(x,x)}\]

Interpolation or regression

The GPR surrogate model can be regressive or interpolative according to the value of the nugget effect \(\\alpha\geq 0\) which is a regularization term applied to the correlation matrix \(K\). When \(\alpha = 0\), the surrogate model interpolates the learning data.

Dependence

The GPR model relies on the GaussianProcessRegressor class of the scikit-learn library.

Classes:

GaussianProcessRegression(data[, ...])

Gaussian process regression.

class gemseo.mlearning.regression.gpr.GaussianProcessRegression(data, transformer=None, input_names=None, output_names=None, kernel=None, alpha=1e-10, optimizer='fmin_l_bfgs_b', n_restarts_optimizer=10, random_state=None)[source]

Gaussian process regression.

learning_set

The learning dataset.

Type

Dataset

parameters

The parameters of the machine learning algorithm.

Type

Dict[str,MLAlgoParameterType]

transformer

The strategies to transform the variables. The values are instances of Transformer while the keys are the names of either the variables or the groups of variables, e.g. “inputs” or “outputs” in the case of the regression algorithms. If a group is specified, the Transformer will be applied to all the variables of this group. If None, do not transform the variables.

Type

Dict[str,Transformer]

algo

The interfaced machine learning algorithm.

Type

Any

input_names

The names of the input variables.

Type

List[str]

output_names

The names of the output variables.

Type

List[str]

input_space_center

The center of the input space.

Type

Dict[str,ndarray]

Initialize self. See help(type(self)) for accurate signature.

Parameters
  • data (Dataset) – The learning dataset.

  • transformer (Optional[TransformerType]) –

    The strategies to transform the variables. The values are instances of Transformer while the keys are the names of either the variables or the groups of variables, e.g. “inputs” or “outputs” in the case of the regression algorithms. If a group is specified, the Transformer will be applied to all the variables of this group. If None, do not transform the variables.

    By default it is set to None.

  • input_names (Optional[Iterable[str]]) –

    The names of the input variables. If None, consider all input variables mentioned in the learning dataset.

    By default it is set to None.

  • output_names (Optional[Iterable[str]]) –

    The names of the output variables. If None, consider all input variables mentioned in the learning dataset.

    By default it is set to None.

  • kernel (Optional[openturns.CovarianceModel]) –

    The kernel function. If None, use a Matern(2.5).

    By default it is set to None.

  • alpha (Union[float,ndarray]) –

    The nugget effect to regularize the model.

    By default it is set to 1e-10.

  • optimizer (Union[str,Callable]) –

    The optimization algorithm to find the hyperparameters.

    By default it is set to fmin_l_bfgs_b.

  • n_restarts_optimizer (int) –

    The number of restarts of the optimizer.

    By default it is set to 10.

  • random_state (Optional[int]) –

    The seed used to initialize the centers. If None, the random number generator is the RandomState instance used by numpy.random.

    By default it is set to None.

Return type

None

Classes:

DataFormatters()

Machine learning regression model decorators.

Attributes:

input_data

The input data matrix.

input_shape

The dimension of the input variables before applying the transformers.

is_trained

Return whether the algorithm is trained.

learning_samples_indices

The indices of the learning samples used for the training.

output_data

The output data matrix.

output_shape

The dimension of the output variables before applying the transformers.

Methods:

learn([samples])

Train the machine learning algorithm from the learning dataset.

load_algo(directory)

Load a machine learning algorithm from a directory.

predict(input_data, *args, **kwargs)

Evaluate 'predict' with either array or dictionary-based input data.

predict_jacobian(input_data, *args, **kwargs)

Evaluate 'predict_jac' with either array or dictionary-based data.

predict_raw(input_data)

Predict output data from input data.

predict_std(input_data)

Predict the standard deviation from input data.

save([directory, path, save_learning_set])

Save the machine learning algorithm.

class DataFormatters

Machine learning regression model decorators.

Methods:

format_dict(predict)

Make an array-based function be called with a dictionary of NumPy arrays.

format_dict_jacobian(predict_jac)

Wrap an array-based function to make it callable with a dictionary of NumPy arrays.

format_input_output(predict)

Make a function robust to type, array shape and data transformation.

format_samples(predict)

Make a 2D NumPy array-based function work with 1D NumPy array.

format_transform([transform_inputs, ...])

Force a function to transform its input and/or output variables.

transform_jacobian(predict_jac)

Apply transformation to inputs and inverse transformation to outputs.

classmethod format_dict(predict)

Make an array-based function be called with a dictionary of NumPy arrays.

Parameters

predict (Callable[[numpy.ndarray], numpy.ndarray]) – The function to be called; it takes a NumPy array in input and returns a NumPy array.

Returns

A function making the function ‘predict’ work with either a NumPy data array or a dictionary of NumPy data arrays indexed by variables names. The evaluation will have the same type as the input data.

Return type

Callable[[Union[numpy.ndarray, Mapping[str, numpy.ndarray]]], Union[numpy.ndarray, Mapping[str, numpy.ndarray]]]

classmethod format_dict_jacobian(predict_jac)

Wrap an array-based function to make it callable with a dictionary of NumPy arrays.

Parameters

predict_jac (Callable[[numpy.ndarray], numpy.ndarray]) – The function to be called; it takes a NumPy array in input and returns a NumPy array.

Returns

The wrapped ‘predict_jac’ function, callable with either a NumPy data array or a dictionary of numpy data arrays indexed by variables names. The return value will have the same type as the input data.

Return type

Callable[[Union[numpy.ndarray, Mapping[str, numpy.ndarray]]], Union[numpy.ndarray, Mapping[str, numpy.ndarray]]]

classmethod format_input_output(predict)

Make a function robust to type, array shape and data transformation.

Parameters

predict (Callable[[numpy.ndarray], numpy.ndarray]) – The function of interest to be called.

Returns

A function calling the function of interest ‘predict’, while guaranteeing consistency in terms of data type and array shape, and applying input and/or output data transformation if required.

Return type

Callable[[Union[numpy.ndarray, Mapping[str, numpy.ndarray]]], Union[numpy.ndarray, Mapping[str, numpy.ndarray]]]

classmethod format_samples(predict)

Make a 2D NumPy array-based function work with 1D NumPy array.

Parameters

predict (Callable[[numpy.ndarray], numpy.ndarray]) – The function to be called; it takes a 2D NumPy array in input and returns a 2D NumPy array. The first dimension represents the samples while the second one represents the components of the variables.

Returns

A function making the function ‘predict’ work with either a 1D NumPy array or a 2D NumPy array. The evaluation will have the same dimension as the input data.

Return type

Callable[[numpy.ndarray], numpy.ndarray]

classmethod format_transform(transform_inputs=True, transform_outputs=True)

Force a function to transform its input and/or output variables.

Parameters
  • transform_inputs (bool) –

    Whether to transform the input variables.

    By default it is set to True.

  • transform_outputs (bool) –

    Whether to transform the output variables.

    By default it is set to True.

Returns

A function evaluating a function of interest, after transforming its input data and/or before transforming its output data.

Return type

Callable[[numpy.ndarray], numpy.ndarray]

classmethod transform_jacobian(predict_jac)

Apply transformation to inputs and inverse transformation to outputs.

Parameters

predict_jac (Callable[[numpy.ndarray], numpy.ndarray]) – The function of interest to be called.

Returns

A function evaluating the function ‘predict_jac’, after transforming its input data and/or before transforming its output data.

Return type

Callable[[numpy.ndarray], numpy.ndarray]

property input_data

The input data matrix.

property input_shape

The dimension of the input variables before applying the transformers.

property is_trained

Return whether the algorithm is trained.

learn(samples=None)

Train the machine learning algorithm from the learning dataset.

Parameters

samples (Optional[Sequence[int]]) –

The indices of the learning samples. If None, use the whole learning dataset.

By default it is set to None.

Return type

None

property learning_samples_indices

The indices of the learning samples used for the training.

load_algo(directory)

Load a machine learning algorithm from a directory.

Parameters

directory (Union[str, pathlib.Path]) – The path to the directory where the machine learning algorithm is saved.

Return type

None

property output_data

The output data matrix.

property output_shape

The dimension of the output variables before applying the transformers.

predict(input_data, *args, **kwargs)

Evaluate ‘predict’ with either array or dictionary-based input data.

Firstly, the pre-processing stage converts the input data to a NumPy data array, if these data are expressed as a dictionary of NumPy data arrays.

Then, the processing evaluates the function ‘predict’ from this NumPy input data array.

Lastly, the post-processing transforms the output data to a dictionary of output NumPy data array if the input data were passed as a dictionary of NumPy data arrays.

Parameters
  • input_data (Union[numpy.ndarray, Mapping[str, numpy.ndarray]]) – The input data.

  • *args – The positional arguments of the function ‘predict’.

  • **kwargs – The keyword arguments of the function ‘predict’.

Returns

The output data with the same type as the input one.

Return type

Union[numpy.ndarray, Mapping[str, numpy.ndarray]]

predict_jacobian(input_data, *args, **kwargs)

Evaluate ‘predict_jac’ with either array or dictionary-based data.

Firstly, the pre-processing stage converts the input data to a NumPy data array, if these data are expressed as a dictionary of NumPy data arrays.

Then, the processing evaluates the function ‘predict_jac’ from this NumPy input data array.

Lastly, the post-processing transforms the output data to a dictionary of output NumPy data array if the input data were passed as a dictionary of NumPy data arrays.

Parameters
  • input_data – The input data.

  • *args – The positional arguments of the function ‘predict_jac’.

  • **kwargs – The keyword arguments of the function ‘predict_jac’.

Returns

The output data with the same type as the input one.

predict_raw(input_data)

Predict output data from input data.

Parameters

input_data (numpy.ndarray) – The input data with shape (n_samples, n_inputs).

Returns

The predicted output data with shape (n_samples, n_outputs).

Return type

numpy.ndarray

predict_std(input_data)[source]

Predict the standard deviation from input data.

The user can specify these input data either as a NumPy array, e.g. array([1., 2., 3.]) or as a dictionary, e.g. {'a': array([1.]), 'b': array([2., 3.])}.

If the NumPy arrays are of dimension 2, their i-th rows represent the input data of the i-th sample; while if the NumPy arrays are of dimension 1, there is a single sample.

Parameters

input_data (Union[numpy.ndarray, Mapping[str, numpy.ndarray]]) – The input data.

Returns

The standard deviation at the query points.

Return type

numpy.ndarray

Warning

The standard deviation at a query point is defined as a positive scalar, whatever the output dimension. By the way, if the output variables are transformed before the training stage, then the standard deviation is related to this transformed output space unlike predict() which returns values in the original output space.

save(directory=None, path='.', save_learning_set=False)

Save the machine learning algorithm.

Parameters
  • directory (Optional[str]) –

    The name of the directory to save the algorithm.

    By default it is set to None.

  • path (Union[str, pathlib.Path]) –

    The path to parent directory where to create the directory.

    By default it is set to ..

  • save_learning_set (bool) –

    Whether to save the learning set or get rid of it to lighten the saved files.

    By default it is set to False.

Returns

The path to the directory where the algorithm is saved.

Return type

str

Example