Document datasets (#3060)

Author: flying-sheep

.azure-pipelines.yml

@@ -4,7 +4,7 @@ trigger:
 
 variables:
   python.version: '3.12'
-  PYTEST_ADDOPTS: '-v --color=yes --nunit-xml=test-data/test-results.xml'
+  PYTEST_ADDOPTS: '-v --color=yes --internet-tests --nunit-xml=test-data/test-results.xml'
   TEST_EXTRA: 'test-full'
   DEPENDENCIES_VERSION: "latest"  # |"pre-release" | "minimum-version"
   TEST_TYPE: "standard" # | "coverage"
@@ -44,11 +44,19 @@ jobs:
     inputs:
       key: '"python $(python.version)" | "$(Agent.OS)" | pyproject.toml'
       restoreKeys: |
-        python | "$(Agent.OS)"
-        python
+        "python" | "$(Agent.OS)"
+        "python"
       path: $(uv_cache_dir)
     displayName: Cache pip packages
 
+
+  - task: Cache@2
+    inputs:
+      key: '"pytest"'
+      restoreKeys: '"pytest"'
+      path: $(System.DefaultWorkingDirectory)/.pytest_cache/d
+    displayName: Cache pytest data
+
   - script: |
       export MPLBACKEND="agg"
       echo $MPLBACKEND

docs/extensions/patch_myst_nb.py

@@ -0,0 +1,30 @@
+"""Extension to patch https://github.com/executablebooks/MyST-NB/pull/599."""
+
+# TODO once MyST-NB 1.1.1/1.2.0 is out, this can be removed.
+
+from __future__ import annotations
+
+from copy import copy
+from typing import TYPE_CHECKING
+
+from myst_nb.core.render import MditRenderMixin
+
+if TYPE_CHECKING:
+    from sphinx.application import Sphinx
+
+
+get_orig = MditRenderMixin.get_cell_level_config
+
+
+def get_cell_level_config(
+    self: MditRenderMixin,
+    field: str,
+    cell_metadata: dict[str, object],
+    line: int | None = None,
+):
+    rv = get_orig(self, field, cell_metadata, line)
+    return copy(rv)
+
+
+def setup(app: Sphinx):
+    MditRenderMixin.get_cell_level_config = get_cell_level_config

docs/references.bib

@@ -99,6 +99,21 @@ @article{Blondel2008
   pages     = {P10008},
 }
 
+@article{Burczynski2006,
+  author    = {Burczynski, Michael E. and Peterson, Ron L. and Twine, Natalie C. and Zuberek, Krystyna A. and Brodeur, Brendan J. and Casciotti, Lori and Maganti, Vasu and Reddy, Padma S. and Strahs, Andrew and Immermann, Fred and Spinelli, Walter and Schwertschlag, Ulrich and Slager, Anna M. and Cotreau, Monette M. and Dorner, Andrew J.},
+  title     = {Molecular Classification of Crohn’s Disease and Ulcerative Colitis Patients Using Transcriptional Profiles in Peripheral Blood Mononuclear Cells},
+  volume    = {8},
+  issn      = {1525-1578},
+  url       = {https://doi.org/10.2353/jmoldx.2006.050079},
+  doi       = {10.2353/jmoldx.2006.050079},
+  number    = {1},
+  journal   = {The Journal of Molecular Diagnostics},
+  publisher = {Elsevier BV},
+  year      = {2006},
+  month     = {feb},
+  pages     = {51--61},
+}
+
 @article{Butler2018,
   author    = {Butler, Andrew and Hoffman, Paul and Smibert, Peter and Papalexi, Efthymia and Satija, Rahul},
   title     = {Integrating single-cell transcriptomic data across different conditions, technologies, and species},

docs/release-notes/1.10.2.md

@@ -12,6 +12,7 @@
 * Fixed incorrect instructions in "testing" dev docs {pr}`2994` {smaller}`I Virshup`
 * Update marsilea tutorial to use `group_` methods {pr}`3001` {smaller}`I Virshup`
 * Fixed citations {pr}`3032` {smaller}`P Angerer`
+* Improve dataset documentation {pr}`3060` {smaller}`P Angerer`
 
 ```{rubric} Bug fixes
 ```

scanpy/_utils/_doctests.py

@@ -26,3 +26,10 @@ def decorator(func: F) -> F:
         return func
 
     return decorator
+
+
+def doctest_internet(func: F) -> F:
+    """Mark function so doctest gets the internet mark."""
+
+    func._doctest_internet = True
+    return func