Model

EventModel

build classmethod

build(
    preproc: EventPreproc,
    size: str | Size | TabularModelSize,
    block: str | BlockType = ATTN,
    dropout: float | None = 0.12,
) -> EventModel

Event model to generate synthetic event data.

Parameters:

Name	Type	Description	Default
preproc	EventPreproc	An EventPreproc object.	required
size	str | Size | TabularModelSize	The size configuration of the model. Could be either a TabularModelSize object, a Size object, or a string representation of the latter.	required
block	str | BlockType	The block type. The possible values depend on whether the data is single table or multi table. For a single table, either 'free' (default), 'causal', or 'lstm'. For multi table data, either 'free' (default) or 'lstm'.	ATTN
dropout	float | None	The dropout probability.	0.12

Returns:

Type	Description
EventModel	An EventModel instance.

generate

generate(
    n_samples: int | None = None,
    ctx: dict[str, DataFrame] | None = None,
    max_n_events: int = 0,
    forbidden_events: Iterable[str] = (),
    force_final: bool = False,
    force_event: bool = False,
    batch_size: int = 0,
    temp: float = 1.0,
) -> RelationalData

Generate synthetic event data.

Parameters:

Name	Type	Description	Default
n_samples	int | None	Desired number of samples in the root table. Must be given if and only if ctx is not provided.	None
ctx	dict[str, DataFrame] | None	The context from where to start a conditional generation. If provided, n_samples should not be given. If some context columns were provided to the EventPreproc, at least these columns must be provided as context and the model will generate the remaining columns of the root table and the events. The context can take two forms: 1. Only some columns of the root table (provided to the EventPreproc). The model will generate the remaining columns of the root tabel and the events. 2. All columns of the root table, and some events. In this case the model will generate the following events.	None
max_n_events	int	Maximum number of events for each row of the root table. If 0, no limit is enforced.	0
forbidden_events	Iterable[str]	The tables containing events that should not be generated. May contain both final and non-final events.	()
force_final	bool	Whether to force the generation to end with a final table.	False
force_event	bool	Whether to force the generation of non-final events, until the max number of events is reached. If True, the parameter max_n_events must be provided.	False
batch_size	int	Batch size used during generation. If 0, all data is generated in a single batch.	0
temp	float	Temperature parameter for sampling.	1.0

Returns:

Type	Description
RelationalData	A RelationalData object with the generated synthetic tabular data.

save

save(path: Path | str) -> None

Save the EventModel to a checkpoint at the given path.

Parameters:

Name	Type	Description	Default
path	Path | str	The path where to sve the checkpoint.	required

load classmethod

load(path: Path | str) -> EventModel

Load the EventModel from the checkpoint at the given path.

Parameters:

Name	Type	Description	Default
path	Path | str	The path to the loaded checkpoint.	required

Returns:

Type	Description
EventModel	The loaded EventModel.