Skip to content

omnipy.components.general.tasks

FUNCTION DESCRIPTION
convert_dataset
import_directory
split_dataset

convert_dataset 

convert_dataset(dataset: Dataset, dataset_cls: type[_DatasetT], **kwargs: object) -> _DatasetT
Source code in src/omnipy/components/general/tasks.py 
59
60
61
@TaskTemplate()
def convert_dataset(dataset: Dataset, dataset_cls: type[_DatasetT], **kwargs: object) -> _DatasetT:
    return dataset_cls(dataset, **kwargs)  # type: ignore[arg-type]

import_directory 

import_directory(
    directory: str | Path,
    exclude_prefixes: tuple[str, ...] = (".", "_"),
    include_suffixes: tuple[str, ...] = (),
    dataset_cls: type[_DatasetT] = Dataset[Model[str]],
    open_func: Callable[[str], IOBase] = open,
) -> _DatasetT
Source code in src/omnipy/components/general/tasks.py 
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
@TaskTemplate()
def import_directory(
        directory: str | Path,
        exclude_prefixes: tuple[str, ...] = ('.', '_'),
        include_suffixes: tuple[str, ...] = (),
        dataset_cls: type[_DatasetT] = Dataset[Model[str]],  # type: ignore
        open_func: Callable[[str], IOBase] = open) -> _DatasetT:
    dataset = dataset_cls()
    for import_filename in os.listdir(directory):
        if not exclude_prefixes or \
                not any(import_filename.startswith(prefix) for prefix in exclude_prefixes):
            if not include_suffixes or \
                    any(import_filename.endswith(suffix) for suffix in include_suffixes):
                with open_func(os.path.join(directory, import_filename)) as open_file:
                    dataset_name = '_'.join(import_filename.split('.')[:-1])
                    print(f"{import_filename} -> Dataset['{dataset_name}']")
                    dataset[dataset_name] = open_file.read()
    return dataset

split_dataset 

split_dataset(
    dataset: Dataset[Model[object]], datafile_names_for_b: list[str]
) -> tuple[Dataset[Model[object]], Dataset[Model[object]]]
Source code in src/omnipy/components/general/tasks.py 
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
@TaskTemplate()
def split_dataset(
        dataset: Dataset[Model[object]],
        datafile_names_for_b: list[str]) -> tuple[Dataset[Model[object]], Dataset[Model[object]]]:
    _type = dataset.get_type()
    datafile_names_for_a = set(dataset.keys()) - set(datafile_names_for_b)
    dataset_a = Dataset[_type](  # type: ignore[valid-type]
        {
            name: dataset[name] for name in dataset.keys() if name in datafile_names_for_a
        })
    dataset_b = Dataset[_type](  # type: ignore[valid-type]
        {
            name: dataset[name] for name in dataset.keys() if name in datafile_names_for_b
        })
    return dataset_a, dataset_b