4676447045

Build Type

github

Committed by GitHub

Commit Message

Merge 30b47daba into ce199d307

Pull Request Pull Request #48: Add the lint-code workflow and pypots-cli to help development

Run Details

79 of 79 new or added lines in 7 files covered. (100.0%)

2854 of 3389 relevant lines covered (84.21%)

0.84 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

53.33

/pypots/data/load_specific_datasets.py

"""
Functions to load supported open-source time-series datasets.
"""

# Created by Wenjie Du <wenjay.du@gmail.com>
# License: GLP-v3


import tsdb

from pypots.data.load_preprocessing import preprocess_physionet2012
from pypots.utils.logging import logger

# currently supported datasets
SUPPORTED_DATASETS = [
    "physionet_2012",
]

# preprocessing functions of the supported datasets
PREPROCESSING_FUNC = {
    "physionet_2012": preprocess_physionet2012,
}


def list_supported_datasets() -> list:
    """Return the datasets natively supported by PyPOTS so far.

    Returns
    -------
    SUPPORTED_DATASETS : list,
        A list including all supported datasets.

    """
    return SUPPORTED_DATASETS


def load_specific_dataset(dataset_name: str, use_cache: bool = True) -> dict:
    """Load specific datasets supported by PyPOTS.
    Different from tsdb.load_dataset(), which only produces merely raw data,
    load_specific_dataset here does some preprocessing operations,
    like truncating time series to generate samples with the same length.

    Parameters
    ----------
    dataset_name : str,
        The name of the dataset to be loaded, which should be supported, i.e. in SUPPORTED_DATASETS.

    use_cache :
        Whether to use cache. This is an argument of tsdb.load_dataset().

    Returns
    -------
    data : dict,
        A dict contains the preprocessed dataset.
        Users only need to continue the preprocessing steps to generate the data they want,
        e.g. standardizing and splitting.

    """
    logger.info(
        f"Loading the dataset {dataset_name} with TSDB (https://github.com/WenjieDu/Time_Series_Database)..."
    )
    assert dataset_name in SUPPORTED_DATASETS, (
        f"Dataset {dataset_name} is not supported. "
        f"If you believe this dataset is valuable to be supported by PyPOTS,"
        f"please create an issue on GitHub "
        f"https://github.com/WenjieDu/PyPOTS/issues"
    )
    logger.info(f"Starting preprocessing {dataset_name}...")
    data = tsdb.load_dataset(dataset_name, use_cache)
    data = PREPROCESSING_FUNC[dataset_name](data)
    return data

1	"""	1✔
2	Functions to load supported open-source time-series datasets.
3	"""
4
5	# Created by Wenjie Du <wenjay.du@gmail.com>
6	# License: GLP-v3
7
8
9	import tsdb	1✔
10
11	from pypots.data.load_preprocessing import preprocess_physionet2012	1✔
12	from pypots.utils.logging import logger	1✔
13
14	# currently supported datasets
15	SUPPORTED_DATASETS = [	1✔
16	"physionet_2012",
17	]
18
19	# preprocessing functions of the supported datasets
20	PREPROCESSING_FUNC = {	1✔
21	"physionet_2012": preprocess_physionet2012,
22	}
23
24
25	def list_supported_datasets() -> list:	1✔
26	"""Return the datasets natively supported by PyPOTS so far.
27
28	Returns
29	-------
30	SUPPORTED_DATASETS : list,
31	A list including all supported datasets.
32
33	"""
34	return SUPPORTED_DATASETS	×
35
36
37	def load_specific_dataset(dataset_name: str, use_cache: bool = True) -> dict:	1✔
38	"""Load specific datasets supported by PyPOTS.
39	Different from tsdb.load_dataset(), which only produces merely raw data,
40	load_specific_dataset here does some preprocessing operations,
41	like truncating time series to generate samples with the same length.
42
43	Parameters
44	----------
45	dataset_name : str,
46	The name of the dataset to be loaded, which should be supported, i.e. in SUPPORTED_DATASETS.
47
48	use_cache :
49	Whether to use cache. This is an argument of tsdb.load_dataset().
50
51	Returns
52	-------
53	data : dict,
54	A dict contains the preprocessed dataset.
55	Users only need to continue the preprocessing steps to generate the data they want,
56	e.g. standardizing and splitting.
57
58	"""
59	logger.info(	×
60	f"Loading the dataset {dataset_name} with TSDB (https://github.com/WenjieDu/Time_Series_Database)..."
61	)
62	assert dataset_name in SUPPORTED_DATASETS, (	×
63	f"Dataset {dataset_name} is not supported. "
64	f"If you believe this dataset is valuable to be supported by PyPOTS,"
65	f"please create an issue on GitHub "
66	f"https://github.com/WenjieDu/PyPOTS/issues"
67	)
68	logger.info(f"Starting preprocessing {dataset_name}...")	×
69	data = tsdb.load_dataset(dataset_name, use_cache)	×
70	data = PREPROCESSING_FUNC[dataset_name](data)	×
71	return data	×

WenjieDu / PyPOTS / 4676447045

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous