scaler module¶

Data scaler¶

The Scaler class implements the default scaling method applying to some parameter \(z\):

\[\bar{z} := \text{offset} + \text{coefficient}\times z\]

where \(\bar{z}\) is the scaled version of z. This scaling method is a linear transformation parameterized by an offset and a coefficient.

In this default scaling method, the offset is equal to 0 and the coefficient is equal to 1. Consequently, the scaling operation is the identity: \(\bar{z}=z\). This method has to be overloaded.

See also

min_max_scaler standard_scaler

class gemseo.mlearning.transform.scaler.scaler.Scaler(name='Scaler', offset=0.0, coefficient=1.0)[source]¶

Bases: gemseo.mlearning.transform.transformer.Transformer

Data scaler.

Constructor.

Parameters

name (str) – name of the scaler.
offset (float) – offset of the linear transformation. Default: 0.
coefficient (float) – coefficient of the linear transformation. Default: 1.

property coefficient¶: Coefficient.

compute_jacobian(data)[source]¶

Compute Jacobian of the scaler transform.

Parameters: data (ndarray) – data where the Jacobian is to be computed.
Returns: Jacobian matrix.
Return type: ndarray

compute_jacobian_inverse(data)[source]¶

Compute Jacobian of the scaler inverse_transform.

Parameters: data (ndarray) – data where the Jacobian is to be computed.
Returns: Jacobian matrix.
Return type: ndarray

fit(data)[source]¶

Fit scaler to data. Offset and coefficient terms are already defined in the constructor.

Parameters: data (ndarray) – data to be fitted.

inverse_transform(data)[source]¶

Unscale data using the offset and coefficient terms.

Parameters: data (ndarray) – data to be inverse transformed.
Returns: inverse transformed data.
Return type: ndarray

property offset¶: Offset.

transform(data)[source]¶

Scale data using the offset and coefficient terms.

Parameters: data (ndarray) – data to be transformed.
Returns: transformed data.
Return type: ndarray