Data Conditions

class DataCondition(input, conditional_variables=None)

Bases: ConditionInterface

Condition defined by input data and conditional variables. It can be used in unsupervised learning problems. Based on the type of the input, different condition implementations are available:

• TensorDataCondition: For torch.Tensor or LabelTensor input data.

• GraphDataCondition: For Graph or Data input data.

Initialize the object by storing the input and conditional variables (if any).

Parameters:

• input (torch.Tensor | LabelTensor | Graph | Data | list[Graph] | list[Data] | tuple[Graph] | tuple[Data]) – Input data for the condition.

• conditional_variables (torch.Tensor | LabelTensor) – Conditional variables for the condition.

Note

If input consists of a list of Graph or Data, all elements must have the same structure (keys and data types)

class GraphDataCondition(input, conditional_variables=None)

Bases: DataCondition

DataCondition for Graph or Data input data

Initialize the object by storing the input and conditional variables (if any).

Parameters:

• input (torch.Tensor | LabelTensor | Graph | Data | list[Graph] | list[Data] | tuple[Graph] | tuple[Data]) – Input data for the condition.

• conditional_variables (torch.Tensor | LabelTensor) – Conditional variables for the condition.

Note

If input consists of a list of Graph or Data, all elements must have the same structure (keys and data types)

class TensorDataCondition(input, conditional_variables=None)

Bases: DataCondition

DataCondition for torch.Tensor or LabelTensor input data

Initialize the object by storing the input and conditional variables (if any).

Parameters:

• input (torch.Tensor | LabelTensor | Graph | Data | list[Graph] | list[Data] | tuple[Graph] | tuple[Data]) – Input data for the condition.

• conditional_variables (torch.Tensor | LabelTensor) – Conditional variables for the condition.

Note

If input consists of a list of Graph or Data, all elements must have the same structure (keys and data types)