def __init__(self,
dataset_properties: Dict[str, BaseDatasetPropertiesType],
random_state: Optional[np.random.RandomState] = None):
super().__init__(dataset_properties=dataset_properties,
random_state=random_state)
self.run_summary: Optional[RunSummary] = None
self.writer: Optional[SummaryWriter] = None
self._fit_requirements: Optional[List[FitRequirement]] = [
FitRequirement("lr_scheduler", (_LRScheduler, ),
user_defined=False,
dataset_property=False),
FitRequirement("num_run", (int, ),
user_defined=False,
dataset_property=False),
FitRequirement("optimizer", (Optimizer, ),
user_defined=False,
dataset_property=False),
FitRequirement("train_data_loader",
(torch.utils.data.DataLoader, ),
user_defined=False,
dataset_property=False),
FitRequirement("val_data_loader", (torch.utils.data.DataLoader, ),
user_defined=False,
dataset_property=False)
]
self.checkpoint_dir: Optional[str] = None
def __init__(self, batch_size: int = 64,
random_state: Optional[np.random.RandomState] = None) -> None:
super().__init__(random_state=random_state)
self.batch_size = batch_size
self.train_data_loader: Optional[torch.utils.data.DataLoader] = None
self.val_data_loader: Optional[torch.utils.data.DataLoader] = None
self.test_data_loader: Optional[torch.utils.data.DataLoader] = None
# We also support existing datasets!
self.dataset = None
self.vision_datasets = self.get_torchvision_datasets()
# Save the transformations for reuse
self.train_transform: Optional[torchvision.transforms.Compose] = None
# The only reason we have val/test transform separated is to speed up
# prediction during training. Namely, if is_small_preprocess is set to true
# X_train data will be pre-processed, so we do no need preprocessing in the transform
# Regardless, test/inference always need this transformation
self.val_transform: Optional[torchvision.transforms.Compose] = None
self.test_transform: Optional[torchvision.transforms.Compose] = None
# Define fit requirements
self.add_fit_requirements([
FitRequirement("split_id", (int,), user_defined=True, dataset_property=False),
FitRequirement("Backend", (Backend,), user_defined=True, dataset_property=False),
FitRequirement("is_small_preprocess", (bool,), user_defined=True, dataset_property=True)])
def __init__(self, random_state: Optional[Union[np.random.RandomState, int]] = None):
super().__init__()
self.random_state = random_state
self.preprocessor: Optional[ColumnTransformer] = None
self.add_fit_requirements([
FitRequirement('numerical_columns', (List,), user_defined=True, dataset_property=True),
FitRequirement('categorical_columns', (List,), user_defined=True, dataset_property=True)])
def __init__(self) -> None:
super().__init__()
self.add_fit_requirements([
FitRequirement('X_train',
(np.ndarray, pd.DataFrame, csr_matrix),
user_defined=True, dataset_property=False),
FitRequirement('backend',
(Backend, ),
user_defined=True, dataset_property=False)])
def __init__(self, percent: float = 0.1,
random_state: Optional[Union[int, np.random.RandomState]] = None):
super().__init__()
self.random_state = random_state
self.percent = percent
self.pad_augmenter: Optional[Augmenter] = None
self.crop_augmenter: Optional[Augmenter] = None
self.add_fit_requirements([
FitRequirement('image_height', (int,), user_defined=True, dataset_property=True),
FitRequirement('image_width', (int,), user_defined=True, dataset_property=True)])
def __init__(self) -> None:
super().__init__()
self.add_fit_requirements([
FitRequirement('numerical_columns', (List, ),
user_defined=True,
dataset_property=True),
FitRequirement('categorical_columns', (List, ),
user_defined=True,
dataset_property=True)
])
def __init__(self) -> None:
super(BaseNormalizer, self).__init__()
self.add_fit_requirements([
FitRequirement('mean', (np.ndarray, ),
user_defined=True,
dataset_property=True),
FitRequirement('std', (np.ndarray, ),
user_defined=True,
dataset_property=True)
])
def __init__(self,
random_state: Optional[np.random.RandomState] = None) -> None:
super().__init__()
self.random_state = random_state
self.add_fit_requirements([
FitRequirement('is_small_preprocess', (bool, ),
user_defined=True,
dataset_property=True),
FitRequirement('X_train', (np.ndarray, pd.DataFrame, csr_matrix),
user_defined=True,
dataset_property=False)
])
def __init__(self,
use_augmenter: bool = True,
random_state: Optional[Union[int,
np.random.RandomState]] = None):
super().__init__(use_augmenter=use_augmenter)
self.random_state = random_state
self.add_fit_requirements([
FitRequirement('image_height', (int, ),
user_defined=True,
dataset_property=True),
FitRequirement('image_width', (int, ),
user_defined=True,
dataset_property=True)
])
def __init__(self, **kwargs: Any):
super().__init__()
self.add_fit_requirements([
FitRequirement('input_shape', (Iterable, ),
user_defined=True,
dataset_property=True),
FitRequirement('task_type', (str, ),
user_defined=True,
dataset_property=True),
FitRequirement('output_shape', (Iterable, int),
user_defined=True,
dataset_property=True),
])
self.head: nn.Module = None
self.config = kwargs
def __init__(self) -> None:
super().__init__()
self.optimizer: Optional[Optimizer] = None
self.add_fit_requirements([
FitRequirement('network', (torch.nn.Module, ),
user_defined=False,
dataset_property=False)
])
def __init__(self) -> None:
super().__init__()
self.scheduler = None # type: Optional[_LRScheduler]
self.add_fit_requirements([
FitRequirement('optimizer', (Optimizer, ),
user_defined=False,
dataset_property=False)
])
def __init__(self,
network: Optional[torch.nn.Module] = None,
random_state: Optional[np.random.RandomState] = None) -> None:
super(NetworkComponent, self).__init__()
self.random_state = random_state
self.device = None
self.add_fit_requirements([
FitRequirement("network_head", (torch.nn.Module, ),
user_defined=False,
dataset_property=False),
FitRequirement("network_backbone", (torch.nn.Module, ),
user_defined=False,
dataset_property=False),
FitRequirement("network_embedding", (torch.nn.Module, ),
user_defined=False,
dataset_property=False),
])
self.network = network
self.final_activation: Optional[torch.nn.Module] = None
def __init__(self,
dataset_properties: Dict[str, Any],
random_state: Optional[np.random.RandomState] = None
):
super().__init__(dataset_properties=dataset_properties,
random_state=random_state)
self.run_summary = None # type: Optional[RunSummary]
self.writer = None # type: Optional[SummaryWriter]
self._fit_requirements: Optional[List[FitRequirement]] = [
FitRequirement("lr_scheduler", (_LRScheduler,), user_defined=False, dataset_property=False),
FitRequirement("network", (torch.nn.Sequential,), user_defined=False, dataset_property=False),
FitRequirement(
"optimizer", (Optimizer,), user_defined=False, dataset_property=False),
FitRequirement("train_data_loader",
(torch.utils.data.DataLoader,),
user_defined=False, dataset_property=False),
FitRequirement("val_data_loader",
(torch.utils.data.DataLoader,),
user_defined=False, dataset_property=False)]
def __init__(
self,
random_state: Optional[np.random.RandomState] = None,
model: Optional[BaseTraditionalLearner] = None,
device: Optional[torch.device] = None
) -> None:
super(BaseModelComponent, self).__init__()
if random_state is None:
self.random_state = check_random_state(1)
else:
self.random_state = check_random_state(random_state)
self.fit_output: Dict[str, Any] = dict()
self.model: Optional[BaseTraditionalLearner] = model
self.add_fit_requirements([
FitRequirement('X_train', (np.ndarray, list, pd.DataFrame), user_defined=False, dataset_property=False),
FitRequirement('y_train', (np.ndarray, list, pd.Series,), user_defined=False, dataset_property=False),
FitRequirement('train_indices', (np.ndarray, list), user_defined=False, dataset_property=False),
FitRequirement('val_indices', (np.ndarray, list), user_defined=False, dataset_property=False)])
def __init__(self, **kwargs: Any):
super().__init__()
self.add_fit_requirements([
FitRequirement('is_small_preprocess', (bool, ),
user_defined=True,
dataset_property=True),
FitRequirement('X_train', (np.ndarray, pd.DataFrame, csr_matrix),
user_defined=True,
dataset_property=False),
FitRequirement('input_shape', (Iterable, ),
user_defined=True,
dataset_property=True),
FitRequirement('tabular_transformer', (BaseEstimator, ),
user_defined=False,
dataset_property=False),
FitRequirement('network_embedding', (nn.Module, ),
user_defined=False,
dataset_property=False)
])
self.backbone: nn.Module = None
self.config = kwargs
self.input_shape: Optional[Iterable] = None
def __init__(
self,
bias_strategy: str,
random_state: Optional[np.random.RandomState] = None,
) -> None:
super().__init__()
self.bias_strategy = bias_strategy
self.random_state = random_state
self.add_fit_requirements([
FitRequirement('network', (torch.nn.Module, ),
user_defined=False,
dataset_property=False)
])
def __init__(self, step_interval: Union[str, StepIntervalUnit]):
super().__init__()
self.scheduler: Optional[_LRScheduler] = None
self._step_interval: StepIntervalUnit
if isinstance(step_interval, str):
if step_interval not in StepIntervalUnitChoices:
raise ValueError('step_interval must be either {}, but got {}.'.format(
StepIntervalUnitChoices,
step_interval
))
self._step_interval = getattr(StepIntervalUnit, step_interval)
else:
self._step_interval = step_interval
self.add_fit_requirements([
FitRequirement('optimizer', (Optimizer,), user_defined=False, dataset_property=False)])
def __init__(self,
n_components: int = 10,
kernel: str = 'rbf',
degree: int = 3,
gamma: float = 0.01,
coef0: float = 0.0,
random_state: Optional[np.random.RandomState] = None):
self.n_components = n_components
self.kernel = kernel
self.degree = degree
self.gamma = gamma
self.coef0 = coef0
super().__init__(random_state=random_state)
self.add_fit_requirements([
FitRequirement('issparse', (bool, ),
user_defined=True,
dataset_property=True)
])