ontolearn.data_struct
Data structures.
Module Contents
Classes
An abstract class representing a |
|
An abstract class representing a |
|
A class to model experiences for Replay Memory. |
|
An abstract class representing a |
|
An abstract class representing a |
|
An abstract class representing a |
|
An abstract class representing a |
- class ontolearn.data_struct.PrepareBatchOfPrediction(current_state: torch.FloatTensor, next_state_batch: torch.FloatTensor, p: torch.FloatTensor, n: torch.FloatTensor)[source]
Bases:
torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.
- class ontolearn.data_struct.PrepareBatchOfTraining(current_state_batch: torch.Tensor, next_state_batch: torch.Tensor, p: torch.Tensor, n: torch.Tensor, q: torch.Tensor)[source]
Bases:
torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.
- class ontolearn.data_struct.Experience(maxlen: int)[source]
A class to model experiences for Replay Memory.
- class ontolearn.data_struct.NCESDataLoader(data: list, embeddings, vocab, inv_vocab, shuffle_examples, max_length, example_sizes=None, sorted_examples=True)[source]
Bases:
NCESBaseDataLoader
,torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.
- class ontolearn.data_struct.NCESDataLoaderInference(data: list, embeddings, vocab, inv_vocab, shuffle_examples, sorted_examples=True)[source]
Bases:
NCESBaseDataLoader
,torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.
- class ontolearn.data_struct.CLIPDataLoader(data: list, embeddings, shuffle_examples, example_sizes: list = None, k=5, sorted_examples=True)[source]
Bases:
torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.
- class ontolearn.data_struct.CLIPDataLoaderInference(data: list, embeddings, shuffle_examples, sorted_examples=True)[source]
Bases:
torch.utils.data.Dataset
An abstract class representing a
Dataset
.All datasets that represent a map from keys to data samples should subclass it. All subclasses should overwrite
__getitem__()
, supporting fetching a data sample for a given key. Subclasses could also optionally overwrite__len__()
, which is expected to return the size of the dataset by manySampler
implementations and the default options ofDataLoader
.Note
DataLoader
by default constructs a index sampler that yields integral indices. To make it work with a map-style dataset with non-integral indices/keys, a custom sampler must be provided.