19147903377

Committed 06 Nov 2025 07:47PM UTC coverage: 20.335% (-0.2%) from 20.507%

Build # 19147903377

Build Type

push

github

Committed by

web-flow

Commit Message

Bump the actions group in /.github/workflows with 6 updates + cruft update (#258)

Run Details

0 of 16 new or added lines in 7 files covered. (0.0%)

7 existing lines in 6 files now uncovered.

97 of 477 relevant lines covered (20.34%)

1.22 hits per line

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

22.92

/src/xdatasets/tutorial.py

import uuid
from functools import reduce
from html import escape

from IPython.core.display import HTML
from xarray.core.formatting_html import _icon, _mapping_section, _obj_repr


catalog_path = "https://raw.githubusercontent.com/hydrocloudservices/catalogs/main/catalogs/main.yaml"


def open_dataset(
    name: str,
    **kws,  # noqa: F841
):
    r"""
    Open a dataset from the online public repository (requires internet).

    Available datasets:
    * ``"era5_reanalysis_single_levels"``: ERA5 reanalysis subset (t2m and tp)
    * ``"cehq"``: CEHQ flow and water levels observations

    Parameters
    ----------
    name : str
        Name of the file containing the dataset.
        e.g. 'era5_reanalysis_single_levels'.
    \*\*kws : dict, optional
        Currently not used.

    See Also
    --------
    xarray.open_dataset
    """
    try:
        import intake
    except ImportError as e:
        raise ImportError(
            "tutorial.open_dataset depends on intake and intake-xarray to download and manage datasets."
            " To proceed please install intake and intake-xarray.",
        ) from e

    cat = intake.open_catalog(catalog_path)
    dataset_info = [
        (category, dataset_name) for category in cat._entries.keys() for dataset_name in cat[category]._entries.keys() if dataset_name == name
    ]

    data = reduce(lambda array, index: array[index], dataset_info, cat)

    if data.describe()["driver"][0] == "geopandasfile":
        data = data.read()
    elif data.describe()["driver"][0] == "zarr":
        data = data.to_dask()
    else:
        raise NotImplementedError(
            f"Dataset {name} is not available. Please request further datasets to our github issues pages",
        )
    return data


def summarize_coords(variables):
    li_items = []
    for k in variables:
        li_content = summarize_variable(k, is_index=False)
        li_items.append(f"<li class='xr-var-item'>{li_content}</li>")

    vars_li = "".join(li_items)

    return f"<ul class='xr-var-list'>{vars_li}</ul>"


def summarize_variable(name, is_index=False, dtype=None):  # noqa: F841
    cssclass_idx = " class='xr-has-index'" if is_index else ""
    name = escape(str(name))

    # "unique" ids required to expand/collapse subsections
    attrs_id = "attrs-" + str(uuid.uuid4())
    data_id = "data-" + str(uuid.uuid4())
    attrs_icon = _icon("icon-file-text2")
    data_icon = _icon("icon-database")

    return (
        f"<div class='xr-var-preview'><span{cssclass_idx}>{name}</span></div>"
        f"<input id='{attrs_id}' class='xr-var-attrs-in' "
        f"type='checkbox'>"
        f"<label for='{attrs_id}' title='Show/Hide attributes'>"
        f"{attrs_icon}</label>"
        f"<input id='{data_id}' class='xr-var-data-in' type='checkbox'>"
        f"<label for='{data_id}' title='Show/Hide data repr'>"
        f"{data_icon}</label>"
    )


def list_available_datasets():
    """
    Open, load lazily, and close a dataset from the public online repository (requires internet).

    See Also
    --------
    open_dataset
    """
    try:
        import intake
    except ImportError as e:
        raise ImportError(
            "tutorial.open_dataset depends on intake and intake-xarray to download and manage datasets."
            " To proceed please install intake and intake-xarray.",
        ) from e

    cat = intake.open_catalog(catalog_path)

    # This will need refactor if the catalog has more than 2 levels
    # list(itertools.chain.from_iterable([list(cat[name].keys()) for name in cat._entries.keys()]))

    datasets_catalog = {field: list(sorted(cat[field]._entries.keys())) for field in sorted(cat._entries.keys())}

    def add_section(datasets_catalog):
        return [
            _mapping_section(
                datasets,
                name=field.capitalize(),
                details_func=summarize_coords,
                max_items_collapse=25,
                expand_option_name="display_expand_coords",
            )
            for field, datasets in datasets_catalog.items()
        ]

    a = _obj_repr(
        "",
        [f"<div class='xr-obj-type'>{escape('xdatasets.Catalog')}</div>"],
        add_section(datasets_catalog),
    )

    return HTML(a)


def load_dataset(*args, **kwargs):
    r"""
    Open, load lazily, and close a dataset from the online repository (requires internet).

    Parameters
    ----------
    \*args : sequence
        A sequence of positional arguments passed to `open_dataset`.
    \*\*kwargs : dict
        A dictionary of keyword arguments passed to `open_dataset`.

    See Also
    --------
    open_dataset
    """
    return open_dataset(*args, **kwargs)

1	import uuid	6✔
2	from functools import reduce	6✔
3	from html import escape	6✔
4
5	from IPython.core.display import HTML	6✔
6	from xarray.core.formatting_html import _icon, _mapping_section, _obj_repr	6✔
7
8
9	catalog_path = "https://raw.githubusercontent.com/hydrocloudservices/catalogs/main/catalogs/main.yaml"	6✔
10
11
12	def open_dataset(	6✔
13	name: str,
14	**kws, # noqa: F841
15	):
16	r"""
17	Open a dataset from the online public repository (requires internet).
18
19	Available datasets:
20	* ``"era5_reanalysis_single_levels"``: ERA5 reanalysis subset (t2m and tp)
21	* ``"cehq"``: CEHQ flow and water levels observations
22
23	Parameters
24	----------
25	name : str
26	Name of the file containing the dataset.
27	e.g. 'era5_reanalysis_single_levels'.
28	\\kws : dict, optional
29	Currently not used.
30
31	See Also
32	--------
33	xarray.open_dataset
34	"""
35	try:	×
36	import intake	×
37	except ImportError as e:	×
38	raise ImportError(	×
39	"tutorial.open_dataset depends on intake and intake-xarray to download and manage datasets."
40	" To proceed please install intake and intake-xarray.",
41	) from e
42
43	cat = intake.open_catalog(catalog_path)	×
44	dataset_info = [	×
45	(category, dataset_name) for category in cat._entries.keys() for dataset_name in cat[category]._entries.keys() if dataset_name == name
46	]
47
48	data = reduce(lambda array, index: array[index], dataset_info, cat)	×
49
50	if data.describe()["driver"][0] == "geopandasfile":	×
51	data = data.read()	×
52	elif data.describe()["driver"][0] == "zarr":	×
53	data = data.to_dask()	×
54	else:
55	raise NotImplementedError(	×
56	f"Dataset {name} is not available. Please request further datasets to our github issues pages",
57	)
58	return data	×
59
60
61	def summarize_coords(variables):	6✔
62	li_items = []	×
63	for k in variables:	×
64	li_content = summarize_variable(k, is_index=False)	×
65	li_items.append(f"<li class='xr-var-item'>{li_content}</li>")	×
66
67	vars_li = "".join(li_items)	×
68
69	return f"<ul class='xr-var-list'>{vars_li}</ul>"	×
70
71
72	def summarize_variable(name, is_index=False, dtype=None): # noqa: F841	6✔
73	cssclass_idx = " class='xr-has-index'" if is_index else ""	×
74	name = escape(str(name))	×
75
76	# "unique" ids required to expand/collapse subsections
77	attrs_id = "attrs-" + str(uuid.uuid4())	×
78	data_id = "data-" + str(uuid.uuid4())	×
79	attrs_icon = _icon("icon-file-text2")	×
80	data_icon = _icon("icon-database")	×
81
82	return (	×
83	f"<div class='xr-var-preview'><span{cssclass_idx}>{name}</span></div>"
84	f"<input id='{attrs_id}' class='xr-var-attrs-in' "
85	f"type='checkbox'>"
86	f"<label for='{attrs_id}' title='Show/Hide attributes'>"
87	f"{attrs_icon}</label>"
88	f"<input id='{data_id}' class='xr-var-data-in' type='checkbox'>"
89	f"<label for='{data_id}' title='Show/Hide data repr'>"
90	f"{data_icon}</label>"
91	)
92
93
94	def list_available_datasets():	6✔
95	"""
96	Open, load lazily, and close a dataset from the public online repository (requires internet).
97
98	See Also
99	--------
100	open_dataset
101	"""
102	try:	×
103	import intake	×
104	except ImportError as e:	×
105	raise ImportError(	×
106	"tutorial.open_dataset depends on intake and intake-xarray to download and manage datasets."
107	" To proceed please install intake and intake-xarray.",
108	) from e
109
110	cat = intake.open_catalog(catalog_path)	×
111
112	# This will need refactor if the catalog has more than 2 levels
113	# list(itertools.chain.from_iterable([list(cat[name].keys()) for name in cat._entries.keys()]))
114
NEW 115	datasets_catalog = {field: list(sorted(cat[field]._entries.keys())) for field in sorted(cat._entries.keys())}	×
116
117	def add_section(datasets_catalog):	×
118	return [	×
119	_mapping_section(
120	datasets,
121	name=field.capitalize(),
122	details_func=summarize_coords,
123	max_items_collapse=25,
124	expand_option_name="display_expand_coords",
125	)
126	for field, datasets in datasets_catalog.items()
127	]
128
129	a = _obj_repr(	×
130	"",
131	[f"<div class='xr-obj-type'>{escape('xdatasets.Catalog')}</div>"],
132	add_section(datasets_catalog),
133	)
134
135	return HTML(a)	×
136
137
138	def load_dataset(args, *kwargs):	6✔
139	r"""
140	Open, load lazily, and close a dataset from the online repository (requires internet).
141
142	Parameters
143	----------
144	\*args : sequence
145	A sequence of positional arguments passed to `open_dataset`.
146	\\kwargs : dict
147	A dictionary of keyword arguments passed to `open_dataset`.
148
149	See Also
150	--------
151	open_dataset
152	"""
153	return open_dataset(args, *kwargs)	×

hydrologie / xdatasets / 19147903377

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