… slice a dataset based on a condition?

Good practice is to have dimension attached to the datasets. The dimension scales can be used to decide what to slice exactly. The following example first generates a dataset and the slices it depending on the value in the first dimension, in this case the time:

import h5rdmtoolbox as h5tbx
import numpy as np

h5tbx.use(None)

with h5tbx.File() as h5:
    h5.create_dataset('time', data=range(0, 100), make_scale=True)
    h5.create_dataset('x', data=range(0, 100), make_scale=True)
    h5.create_dataset('y', data=range(0, 200), make_scale=True)
    h5.create_dataset('data', np.random.rand(100, 200, 100), attach_scale=('time', 'y', 'x'))
    data = h5.data[:]
    h5.dump()

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
Cell In[1], line 1
----> 1 import h5rdmtoolbox as h5tbx
      2 import numpy as np
      4 h5tbx.use(None)

File ~/checkouts/readthedocs.org/user_builds/h5rdmtoolbox/checkouts/v1.7.0/h5rdmtoolbox/__init__.py:129
    125     with File(src) as h5:
    126         return h5.dumps()
--> 129 from h5rdmtoolbox.wrapper.ld.hdf.file import get_ld as hdf_get_ld
    130 from h5rdmtoolbox.wrapper.ld.user.file import get_ld as user_get_ld
    133 def get_ld(
    134         hdf_filename: Union[str, pathlib.Path],
    135         structural: bool = True,
    136         semantic: bool = True,
    137         blank_node_iri_base: Optional[str] = None,
    138         **kwargs) -> rdflib.Graph:

File ~/checkouts/readthedocs.org/user_builds/h5rdmtoolbox/checkouts/v1.7.0/h5rdmtoolbox/wrapper/ld/__init__.py:1
----> 1 import ssnolib.ssno.standard_name
      2 from ontolutils.namespacelib import M4I
      3 from ontolutils.namespacelib import SCHEMA

ModuleNotFoundError: No module named 'ssnolib'

with h5tbx.File(h5.hdf_filename) as h5:
    h5.data[h5.data.time > 5.4, :, :].plot()