diff --git a/docs/conf.py b/docs/conf.py index 6f8b07bfa6a783cb46bbf54c21d0d91cde572269..8fc029d6d2d622cd727ea7b85d4bbce4049a609b 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -53,6 +53,7 @@ html_theme_options = { intersphinx_mapping = { "np": ("https://numpy.org/doc/stable/", None), "Python": ("https://docs.python.org/3", None), + "pooch": ("https://www.fatiando.org/pooch/latest/", None), } # We keep the objects.inv files in our docs folder to get hints on how to specify the # cross-references. More on the topic can be found here: diff --git a/src/zema_emc_annotated/dataset.py b/src/zema_emc_annotated/dataset.py index f7411a734d613907248e7cf625c590a7c54e9aac..1da12a81889ffcb3709f9b0bd75adabcede2bffe 100644 --- a/src/zema_emc_annotated/dataset.py +++ b/src/zema_emc_annotated/dataset.py @@ -65,6 +65,13 @@ class ZeMASamples: The underlying dataset is the annotated "Sensor data set of one electromechanical cylinder at ZeMA testbed (ZeMA DAQ and Smart-Up Unit)" by Dorst et al. [Dorst2021]_. + Each extracted sample will be cached in the download directory of the file, + which is handled by :func:`pooch.os_cache`, where ``<AppName>`` evaluates to + ``pooch``. That way the concurrent retrieval of the same data is as performant as + possible and can simply be left to ``zema_emc_annotated``. Where ever the result + of ``ZeMASamples`` is needed in an external code base, it should be safe to call + it over and over without causing unnecessary extractions or even downloads. The + underlying mechanism is Python's built-in ``pickle``. Parameters ----------