Backport PRs #2478 and #2235 on branch 1.9.x (Separate test utils from tests)

.azure-pipelines.yml

@@ -4,9 +4,11 @@ trigger:
 variables:
   python.version: '3.9'
   PIP_CACHE_DIR: $(Pipeline.Workspace)/.pip
+  PYTEST_ADDOPTS: '-v --color=yes --nunit-xml=nunit/test-results.xml'
   ANNDATA_DEV: no
   RUN_COVERAGE: no
   TEST_EXTRA: 'test-full'
+  PRERELEASE_DEPENDENCIES: no
 
 jobs:
 - job: PyTest
@@ -23,6 +25,8 @@ jobs:
         python.version: '3.9'
         ANNDATA_DEV: yes
         RUN_COVERAGE: yes
+        PRERELEASE_DEPENDENCIES: yes
+
   steps:
   - task: UsePythonVersion@0
     inputs:
@@ -45,9 +49,17 @@ jobs:
 
   - script: |
       python -m pip install --upgrade pip
-      pip install pytest-cov wheel
+      pip install wheel coverage
       pip install .[dev,$(TEST_EXTRA)]
     displayName: 'Install dependencies'
+    condition: eq(variables['PRERELEASE_DEPENDENCIES'], 'no')
+
+  - script: |
+      python -m pip install --pre --upgrade pip
+      pip install --pre wheel coverage
+      pip install --pre .[dev,$(TEST_EXTRA)]
+    displayName: 'Install dependencies release candidates'
+    condition: eq(variables['PRERELEASE_DEPENDENCIES'], 'yes')
 
   - script: |
       pip install -v "anndata[dev,test] @ git+https://github.com/scverse/anndata"
@@ -58,13 +70,13 @@ jobs:
       pip list
     displayName: 'Display installed versions'
 
-  - script: |
-      pytest -v --color=yes --ignore=scanpy/tests/_images --nunit-xml="nunit/test-results.xml"
+  - script: pytest
     displayName: 'PyTest'
     condition: eq(variables['RUN_COVERAGE'], 'no')
 
   - script: |
-      pytest -v --color=yes --ignore=scanpy/tests/_images --nunit-xml="nunit/test-results.xml" --cov=scanpy --cov-report=xml
+      coverage run -m pytest
+      coverage xml
     displayName: 'PyTest (coverage)'
     condition: eq(variables['RUN_COVERAGE'], 'yes')
 

.gitignore

@@ -9,6 +9,8 @@
 /docs/data/
 
 # tests
+/*coverage*
+/nunit/
 /.cache/
 /.pytest_cache/
 /scanpy/tests/test*.h5ad
@@ -39,6 +41,3 @@ Thumbs.db
 # IDEs and editors
 /.idea/
 /.vscode/
-
-# Test artifacts
-**/test-results.xml

pyproject.toml

@@ -141,21 +141,50 @@ exclude = [
 ]
 
 [tool.pytest.ini_options]
-python_files = "test_*.py"
-testpaths = "scanpy/tests/"
+addopts = [
+    "--import-mode=importlib",
+    "-pscanpy.testing._pytest",
+]
+testpaths = ["scanpy"]
+ignore = ["scanpy/tests/_images"]
+xfail_strict = true
 nunit_attach_on = "fail"
 markers = [
     "internet: tests which rely on internet resources (enable with `--internet-tests`)",
 ]
 
 [tool.coverage.run]
-source = ["scanpy"]
+source_pkgs = ["scanpy"]
 omit = ["*/tests/*"]
+[tool.coverage.paths]
+source = [".", "**/site-packages"]
 
 [tool.black]
 line-length = 88
 target-version = ["py38"]
 skip-string-normalization = true
-exclude = """
-/build/.*
-"""
+
+[tool.ruff]
+select = [
+    "F",  # Pyflakes
+    "E",  # Pycodestyle errors
+    "W",  # Pycodestyle warnings
+    "TID251",  # Banned imports
+]
+ignore = [
+    # module imported but unused -> required for Scanpys API
+    "F401",
+    # line too long -> we accept long comment lines; black gets rid of long code lines
+    "E501",
+    # module level import not at top of file -> required to circumvent circular imports for Scanpys API
+    "E402",
+    # E266 too many leading '#' for block comment -> Scanpy allows them for comments into sections
+    "E262",
+    # allow I, O, l as variable names -> I is the identity matrix, i, j, k, l is reasonable indexing notation
+    "E741",
+]
+[tool.ruff.per-file-ignores]
+# Do not assign a lambda expression, use a def
+"scanpy/tools/_rank_genes_groups.py" = ["E731"]
+[tool.ruff.flake8-tidy-imports.banned-api]
+"pytest.importorskip".msg = "Use the “@needs” decorator/mark instead"

scanpy/plotting/_tools/__init__.py

@@ -7,7 +7,7 @@
 from matplotlib.figure import Figure
 from matplotlib.colors import Normalize
 from matplotlib import pyplot as pl
-from matplotlib import rcParams, cm
+from matplotlib import rcParams, colormaps
 from anndata import AnnData
 from typing import Union, Optional, List, Sequence, Iterable, Mapping, Literal
 
@@ -1446,7 +1446,7 @@ def embedding_density(
 
     # Make the color map
     if isinstance(color_map, str):
-        color_map = copy(cm.get_cmap(color_map))
+        color_map = copy(colormaps.get_cmap(color_map))
 
     color_map.set_over('black')
     color_map.set_under('lightgray')

scanpy/plotting/_tools/scatterplots.py

@@ -22,8 +22,7 @@
 from matplotlib.axes import Axes
 from matplotlib.figure import Figure
 from pandas.api.types import is_categorical_dtype
-from matplotlib import pyplot as pl, colors
-from matplotlib.cm import get_cmap
+from matplotlib import pyplot as pl, colors, colormaps
 from matplotlib import rcParams
 from matplotlib import patheffects
 from matplotlib.colors import Colormap, Normalize
@@ -160,7 +159,7 @@ def embedding(
             raise ValueError("Cannot specify both `color_map` and `cmap`.")
         else:
             cmap = color_map
-    cmap = copy(get_cmap(cmap))
+    cmap = copy(colormaps.get_cmap(cmap))
     cmap.set_bad(na_color)
     kwargs["cmap"] = cmap
     # Prevents warnings during legend creation

scanpy/tests/helpers.py → scanpy/testing/_helpers/__init__.py

@@ -7,9 +7,8 @@
 import scanpy as sc
 import numpy as np
 import warnings
-import pytest
 from anndata.tests.helpers import asarray, assert_equal
-from scanpy.tests._data._cached_datasets import pbmc3k
+
 
 # TODO: Report more context on the fields being compared on error
 # TODO: Allow specifying paths to ignore on comparison
@@ -20,7 +19,7 @@
 # These functions can be used to check that functions are correctly using arugments like `layers`, `obsm`, etc.
 
 
-def check_rep_mutation(func, X, *, fields=["layer", "obsm"], **kwargs):
+def check_rep_mutation(func, X, *, fields=("layer", "obsm"), **kwargs):
     """Check that only the array meant to be modified is modified."""
     adata = sc.AnnData(X=X.copy(), dtype=X.dtype)
     for field in fields:
@@ -87,32 +86,12 @@ def check_rep_results(func, X, *, fields=["layer", "obsm"], **kwargs):
         assert_equal(adata_X, adatas_proc[field])
 
 
-def _prepare_pbmc_testdata(sparsity_func, dtype, small=False):
-    """Prepares 3k PBMC dataset with batch key `batch` and defined datatype/sparsity.
-
-    Params
-    ------
-    sparsity_func
-        sparsity function applied to adata.X (e.g. csr_matrix.toarray for dense or csr_matrix for sparse)
-    dtype
-        numpy dtype applied to adata.X (e.g. 'float32' or 'int64')
-    small
-        False (default) returns full data, True returns small subset of the data."""
-
-    adata = pbmc3k().copy()
-
-    if small:
-        adata = adata[:1000, :500]
-        sc.pp.filter_cells(adata, min_genes=1)
-    np.random.seed(42)
-    adata.obs['batch'] = np.random.randint(0, 3, size=adata.shape[0])
-    sc.pp.filter_genes(adata, min_cells=1)
-    adata.X = sparsity_func(adata.X.astype(dtype))
-    return adata
-
-
 def _check_check_values_warnings(function, adata, expected_warning, kwargs={}):
-    '''Runs `function` on `adata` with provided arguments `kwargs` twice: once with `check_values=True` and once with `check_values=False`. Checks that the `expected_warning` is only raised whtn `check_values=True`.'''
+    """
+    Runs `function` on `adata` with provided arguments `kwargs` twice:
+    once with `check_values=True` and once with `check_values=False`.
+    Checks that the `expected_warning` is only raised whtn `check_values=True`.
+    """
 
     # expecting 0 no-int warnings
     with warnings.catch_warnings(record=True) as record:

scanpy/testing/_helpers/data.py

@@ -0,0 +1,69 @@
+"""
+Functions returning copies of datasets as cheaply as possible,
+i.e. without having to hit the disk or (in case of ``_pbmc3k_normalized``) recomputing normalization.
+"""
+
+from __future__ import annotations
+
+try:
+    from functools import cache
+except ImportError:  # Python < 3.9
+    from functools import lru_cache
+
+    def cache(func):
+        return lru_cache(maxsize=None)(func)
+
+
+from anndata import AnnData
+import scanpy as sc
+
+
+# Functions returning the same objects (easy to misuse)
+
+
+_pbmc3k = cache(sc.datasets.pbmc3k)
+_pbmc3k_processed = cache(sc.datasets.pbmc3k_processed)
+_pbmc68k_reduced = cache(sc.datasets.pbmc68k_reduced)
+_krumsiek11 = cache(sc.datasets.krumsiek11)
+_paul15 = cache(sc.datasets.paul15)
+
+
+# Functions returning copies
+
+
+def pbmc3k() -> AnnData:
+    return _pbmc3k().copy()
+
+
+def pbmc3k_processed() -> AnnData:
+    return _pbmc3k_processed().copy()
+
+
+def pbmc68k_reduced() -> AnnData:
+    return _pbmc68k_reduced().copy()
+
+
+def krumsiek11() -> AnnData:
+    return _krumsiek11().copy()
+
+
+def paul15() -> AnnData:
+    return _paul15().copy()
+
+
+# Derived datasets
+
+
+@cache
+def _pbmc3k_normalized() -> AnnData:
+    pbmc = pbmc3k()
+    pbmc.X = pbmc.X.astype("float64")  # For better accuracy
+    sc.pp.filter_genes(pbmc, min_counts=1)
+    sc.pp.log1p(pbmc)
+    sc.pp.normalize_total(pbmc)
+    sc.pp.highly_variable_genes(pbmc)
+    return pbmc
+
+
+def pbmc3k_normalized() -> AnnData:
+    return _pbmc3k_normalized().copy()

scanpy/testing/_pytest/__init__.py

@@ -0,0 +1,48 @@
+"""A private pytest plugin"""
+import pytest
+
+from .fixtures import *  # noqa: F403
+
+
+# In case pytest-nunit is not installed, defines a dummy fixture
+try:
+    import pytest_nunit
+except ModuleNotFoundError:
+
+    @pytest.fixture
+    def add_nunit_attachment(request):
+        def noop(file, description):
+            pass
+
+        return noop
+
+    def pytest_addoption(parser):
+        add_internet_tests_option(parser)
+        parser.addini("nunit_attach_on", "Dummy nunit replacement", default="any")
+
+else:
+
+    def pytest_addoption(parser):
+        add_internet_tests_option(parser)
+
+
+def add_internet_tests_option(parser):
+    parser.addoption(
+        "--internet-tests",
+        action="store_true",
+        default=False,
+        help=(
+            "Run tests that retrieve stuff from the internet. "
+            "This increases test time."
+        ),
+    )
+
+
+def pytest_collection_modifyitems(config, items):
+    run_internet = config.getoption("--internet-tests")
+    skip_internet = pytest.mark.skip(reason="need --internet-tests option to run")
+    for item in items:
+        # All tests marked with `pytest.mark.internet` get skipped unless
+        # `--run-internet` passed
+        if not run_internet and ("internet" in item.keywords):
+            item.add_marker(skip_internet)