mendevi.models.base.Model

class mendevi.models.base.Model(title: str | None = None, **kwargs)

Common structure to all models.

Attributes

citestr

The latex bibtext model citation.

parameterstorch.Tensor | None

The trainable parameters of the model (read and write).

input_labelslist[str]

The name of all input parameters (readonly).

output_labelslist[str]

The name of all output parameters (readonly).

Initialise the model.

Parameters

titlestr, optional

The model title.

sourcesstr

All sources for the model, the conference paper, the authors, etc.

input_labelslist[str]

The name of all input parameters. The possibles values are :py:cst:`mendevi.plot.axis.Name`.

output_labelslist[str]

The name of all output parameters. The possibles values are :py:cst:`mendevi.plot.axis.Name`.

parameterstorch.Tensor, optional

The learnable parameters for regressive models.

property cite: str

Return the bibtex citation.

fit(database: Path | str, query: str | None = None) → Self

Fit the trainable hyper parameters of the models.

Parameters

databasepathlike

The training database.

querystr, optional

If provided, use this sql query to perform the request, otherwise (default) attemps to guess the query.

Return

self

A reference to the inplace fitted model.

property input_labels: list[str]

Return the name of all input parameters.

property output_labels: list[str]

Return the name of all output parameters.

property parameters: Tensor

Return the trainable parameters of the model.

predict(*input_args, **input_kwargs) → dict[str]

Perform the prediction(s) of this model.

Parameters

*input_args, **input_kwargs

The parameters values, with the keys defined during initialisation.

Returns

predictiondict[str]

Associate each ouput variable with the prediction.