[WIP] add asv benchmark code

.gitignore

@@ -47,3 +47,5 @@ _version.py
 
 # other
 node_modules/
+
+.asv/

asv.conf.json

@@ -0,0 +1,203 @@
+{
+    // The version of the config file format.  Do not change, unless
+    // you know what you are doing.
+    "version": 1,
+
+    // The name of the project being benchmarked
+    "project": "spatialdata",
+
+    // The project's homepage
+    "project_url": "https://spatialdata.scverse.org/",
+
+    // The URL or local path of the source code repository for the
+    // project being benchmarked
+    "repo": ".",
+
+    // The Python project's subdirectory in your repo.  If missing or
+    // the empty string, the project is assumed to be located at the root
+    // of the repository.
+    // "repo_subdir": "",
+
+    // Customizable commands for building the project.
+    // See asv.conf.json documentation.
+    // To build the package using pyproject.toml (PEP518), uncomment the following lines
+    // "build_command": [
+    //     "python -m pip install build",
+    //     "python -m build",
+    //     "python -mpip wheel -w {build_cache_dir} {build_dir}"
+    // ],
+    // To build the package using setuptools and a setup.py file, uncomment the following lines
+    // "build_command": [
+    //     "python setup.py build",
+    //     "python -mpip wheel -w {build_cache_dir} {build_dir}"
+    // ],
+    "build_command": ["python -V"], // skip build stage
+
+    // Customizable commands for installing and uninstalling the project.
+    // See asv.conf.json documentation.
+    // "install_command": ["in-dir={env_dir} python -mpip install {wheel_file}"],
+    // "uninstall_command": ["return-code=any python -mpip uninstall -y {project}"],
+
+    // Install using default install
+    "install_command": [
+        "in-dir={env_dir} python -m pip install {build_dir}[test]"
+    ],
+    "uninstall_command": [
+        "in-dir={env_dir} python -m pip uninstall -y {project}"
+    ],
+
+    // List of branches to benchmark. If not provided, defaults to "main"
+    // (for git) or "default" (for mercurial).
+    "branches": ["main"], // for git
+    // "branches": ["default"],    // for mercurial
+
+    // The DVCS being used.  If not set, it will be automatically
+    // determined from "repo" by looking at the protocol in the URL
+    // (if remote), or by looking for special directories, such as
+    // ".git" (if local).
+    // "dvcs": "git",
+
+    // The tool to use to create environments.  May be "conda",
+    // "virtualenv", "mamba" (above 3.8)
+    // or other value depending on the plugins in use.
+    // If missing or the empty string, the tool will be automatically
+    // determined by looking for tools on the PATH environment
+    // variable.
+    "environment_type": "virtualenv",
+
+    // timeout in seconds for installing any dependencies in environment
+    // defaults to 10 min
+    // "install_timeout": 600,
+
+    // the base URL to show a commit for the project.
+    // "show_commit_url": "http://github.com/owner/project/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    "pythons": ["3.12"],
+
+    // The list of conda channel names to be searched for benchmark
+    // dependency packages in the specified order
+    // "conda_channels": ["conda-forge", "defaults"],
+
+    // A conda environment file that is used for environment creation.
+    // "conda_environment_file": "environment.yml",
+
+    // The matrix of dependencies to test.  Each key of the "req"
+    // requirements dictionary is the name of a package (in PyPI) and
+    // the values are version numbers.  An empty list or empty string
+    // indicates to just test against the default (latest)
+    // version. null indicates that the package is to not be
+    // installed. If the package to be tested is only available from
+    // PyPi, and the 'environment_type' is conda, then you can preface
+    // the package name by 'pip+', and the package will be installed
+    // via pip (with all the conda available packages installed first,
+    // followed by the pip installed packages).
+    //
+    // The ``@env`` and ``@env_nobuild`` keys contain the matrix of
+    // environment variables to pass to build and benchmark commands.
+    // An environment will be created for every combination of the
+    // cartesian product of the "@env" variables in this matrix.
+    // Variables in "@env_nobuild" will be passed to every environment
+    // during the benchmark phase, but will not trigger creation of
+    // new environments.  A value of ``null`` means that the variable
+    // will not be set for the current combination.
+    //
+    // "matrix": {
+    //     "req": {
+    //         "numpy": ["1.6", "1.7"],
+    //         "six": ["", null],  // test with and without six installed
+    //         "pip+emcee": [""]   // emcee is only available for install with pip.
+    //     },
+    //     "env": {"ENV_VAR_1": ["val1", "val2"]},
+    //     "env_nobuild": {"ENV_VAR_2": ["val3", null]},
+    // },
+
+    // Combinations of libraries/python versions can be excluded/included
+    // from the set to test. Each entry is a dictionary containing additional
+    // key-value pairs to include/exclude.
+    //
+    // An exclude entry excludes entries where all values match. The
+    // values are regexps that should match the whole string.
+    //
+    // An include entry adds an environment. Only the packages listed
+    // are installed. The 'python' key is required. The exclude rules
+    // do not apply to includes.
+    //
+    // In addition to package names, the following keys are available:
+    //
+    // - python
+    //     Python version, as in the *pythons* variable above.
+    // - environment_type
+    //     Environment type, as above.
+    // - sys_platform
+    //     Platform, as in sys.platform. Possible values for the common
+    //     cases: 'linux2', 'win32', 'cygwin', 'darwin'.
+    // - req
+    //     Required packages
+    // - env
+    //     Environment variables
+    // - env_nobuild
+    //     Non-build environment variables
+    //
+    // "exclude": [
+    //     {"python": "3.2", "sys_platform": "win32"}, // skip py3.2 on windows
+    //     {"environment_type": "conda", "req": {"six": null}}, // don't run without six on conda
+    //     {"env": {"ENV_VAR_1": "val2"}}, // skip val2 for ENV_VAR_1
+    // ],
+    //
+    // "include": [
+    //     // additional env for python3.12
+    //     {"python": "3.12", "req": {"numpy": "1.26"}, "env_nobuild": {"FOO": "123"}},
+    //     // additional env if run on windows+conda
+    //     {"platform": "win32", "environment_type": "conda", "python": "3.12", "req": {"libpython": ""}},
+    // ],
+
+    // The directory (relative to the current directory) that benchmarks are
+    // stored in.  If not provided, defaults to "benchmarks"
+    // "benchmark_dir": "benchmarks",
+
+    // The directory (relative to the current directory) to cache the Python
+    // environments in.  If not provided, defaults to "env"
+    "env_dir": ".asv/env",
+
+    // The directory (relative to the current directory) that raw benchmark
+    // results are stored in.  If not provided, defaults to "results".
+    "results_dir": ".asv/results",
+
+    // The directory (relative to the current directory) that the html tree
+    // should be written to.  If not provided, defaults to "html".
+    "html_dir": ".asv/html",
+
+    // The number of characters to retain in the commit hashes.
+    "hash_length": 8,
+
+    // `asv` will cache results of the recent builds in each
+    // environment, making them faster to install next time.  This is
+    // the number of builds to keep, per environment.
+    "build_cache_size": 2
+
+    // The commits after which the regression search in `asv publish`
+    // should start looking for regressions. Dictionary whose keys are
+    // regexps matching to benchmark names, and values corresponding to
+    // the commit (exclusive) after which to start looking for
+    // regressions.  The default is to start from the first commit
+    // with results. If the commit is `null`, regression detection is
+    // skipped for the matching benchmark.
+    //
+    // "regressions_first_commits": {
+    //    "some_benchmark": "352cdf",  // Consider regressions only after this commit
+    //    "another_benchmark": null,   // Skip regression detection altogether
+    // },
+
+    // The thresholds for relative change in results, after which `asv
+    // publish` starts reporting regressions. Dictionary of the same
+    // form as in ``regressions_first_commits``, with values
+    // indicating the thresholds.  If multiple entries match, the
+    // maximum is taken. If no entry matches, the default is 5%.
+    //
+    // "regressions_thresholds": {
+    //    "some_benchmark": 0.01,     // Threshold of 1%
+    //    "another_benchmark": 0.5,   // Threshold of 50%
+    // },
+}

benchmarks/README.md

@@ -0,0 +1,41 @@
+# Benchmarking
+
+setup
+
+```
+pip install -e '.[docs,benchmark]'
+```
+
+In PyCharm, configure your Configuration to include the benchmark module. In Python, you can run using
+
+```
+python -m benchmarks.spatialdata_benchmark
+```
+
+See napari [docs](https://napari.org/stable/developers/contributing/performance/benchmarks.html) on profiling and benchmarking for more information.
+
+run a specific benchmark
+
+```
+PYTHONWARNINGS="ignore" asv run --python=same --show-stderr -b time_query_bounding_box
+```
+
+output:
+
+```
+[50.00%] ··· ======== ============ ============== ============= ===============
+         	--             	filter_table / n_transcripts_per_cell
+         	-------- ---------------------------------------------------------
+          	length   True / 100   True / 10000   False / 100   False / 10000
+         	======== ============ ============== ============= ===============
+           	100  	813±0ms   	1.09±0s    	803±0ms    	980±0ms
+           	1000 	799±0ms   	2.96±0s    	789±0ms    	2.81±0s
+          	10000 	1.32±0s   	24.4±0s    	962±0ms    	21.5±0s
+         	======== ============ ============== ============= ===============
+```
+
+run everything in new env
+
+```
+asv run
+```

benchmarks/spatialdata_benchmark.py

@@ -0,0 +1,89 @@
+# type: ignore
+
+# Write the benchmarking functions here.
+# See "Writing benchmarks" in the asv docs for more information.
+import spatialdata as sd
+
+from .utils import cluster_blobs
+
+
+class MemorySpatialData:
+    # TODO: see what the memory overhead is e.g. Python interpreter...
+    """Calculate the peak memory usage is for artificial datasets with increasing channels."""
+
+    def peakmem_list(self):
+        sdata: sd.SpatialData = sd.datasets.blobs(n_channels=1)
+        return sdata
+
+    def peakmem_list2(self):
+        sdata: sd.SpatialData = sd.datasets.blobs(n_channels=2)
+        return sdata
+
+
+def timeraw_import_inspect():
+    """Time the import of the spatialdata module."""
+    return """
+    import spatialdata
+    """
+
+
+class TimeMapRaster:
+    """Time the."""
+
+    params = [100, 1000, 10_000]
+    param_names = ["length"]
+
+    def setup(self, length):
+        self.sdata = cluster_blobs(length=length)
+
+    def teardown(self, _):
+        del self.sdata
+
+    def time_map_blocks(self, _):
+        sd.map_raster(self.sdata["blobs_image"], lambda x: x + 1)
+
+
+class TimeQueries:
+
+    params = ([100, 1000, 10_000], [True, False], [100, 10_000])
+    param_names = ["length", "filter_table", "n_transcripts_per_cell"]
+
+    def setup(self, length, filter_table, n_transcripts_per_cell):
+        import shapely
+
+        self.sdata = cluster_blobs(length=length, n_transcripts_per_cell=n_transcripts_per_cell)
+        self.polygon = shapely.box(0, 0, length // 2, length // 2)
+
+    def teardown(self, length, filter_table, n_transcripts_per_cell):
+        del self.sdata
+
+    def time_query_bounding_box(self, length, filter_table, n_transcripts_per_cell):
+        self.sdata.query.bounding_box(
+            axes=["x", "y"],
+            min_coordinate=[0, 0],
+            max_coordinate=[length // 2, length // 2],
+            target_coordinate_system="global",
+            filter_table=filter_table,
+        )
+
+    def time_query_polygon_box(self, length, filter_table, n_transcripts_per_cell):
+        sd.polygon_query(
+            self.sdata,
+            self.polygon,
+            target_coordinate_system="global",
+            filter_table=filter_table,
+        )
+
+
+if __name__ == "__main__":
+    length = 1_000
+    sdata = cluster_blobs(length)
+    # sdata.write("tmp_test")
+    sdata.query.bounding_box(
+        axes=["x", "y"],
+        min_coordinate=[0, 0],
+        max_coordinate=[length // 2, length // 2],
+        target_coordinate_system="global",
+        filter_table=True,
+    )
+    print(sdata)