Asv benchmarks for cellfinder workflow

.gitignore

@@ -81,3 +81,4 @@ venv/
 
 # written by setuptools_scm
 **/_version.py
+benchmarks/results/*

MANIFEST.in

@@ -3,8 +3,14 @@ include README.md
 exclude .pre-commit-config.yaml
 
 recursive-include brainglobe_workflows *.py
+recursive-exclude brainglobe_workflows/cellfinder/notebooks *.py
 
 recursive-exclude * __pycache__
 recursive-exclude * *.py[co]
 recursive-exclude docs *
 recursive-exclude tests *
+
+include *.json
+recursive-include benchmarks *.json
+recursive-include benchmarks *.py
+recursive-exclude benchmarks/results *

asv.conf.json

@@ -0,0 +1,194 @@
+{
+    // 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": "brainglobe_workflows",
+
+    // The project's homepage
+    "project_url": "https://github.com/brainglobe/brainglobe-workflows",
+
+    // 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",
+        "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -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",
+    //     "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}"
+    // ],
+
+    // Customizable commands for installing and uninstalling the project.
+    // See asv.conf.json documentation.
+    "install_command": ["in-dir={env_dir} python -mpip install --force-reinstall {wheel_file}"],
+    "uninstall_command": ["return-code=any python -mpip uninstall -y {project}"],
+
+    // List of branches to benchmark. If not provided, defaults to "master"
+    // (for git) or "default" (for mercurial).
+    "branches": ["smg/cellfinder-wf1-benchmark"], // 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": "conda",
+
+    // 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": "https://github.com/brainglobe/brainglobe-workflows/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    "pythons": ["3.10"],
+
+    // 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 python2.7
+    //     {"python": "2.7", "req": {"numpy": "1.8"}, "env_nobuild": {"FOO": "123"}},
+    //     // additional env if run on windows+conda
+    //     {"platform": "win32", "environment_type": "conda", "python": "2.7", "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": "benchmarks/results",
+
+    // The directory (relative to the current directory) that the html tree
+    // should be written to.  If not provided, defaults to "html".
+    "html_dir": "benchmarks/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/cellfinder/workflows.py

@@ -0,0 +1,98 @@
+import shutil
+
+from brainglobe_utils.IO.cells import save_cells
+from cellfinder_core.main import main as cellfinder_run
+from cellfinder_core.tools.IO import read_with_dask
+
+from brainglobe_workflows.cellfinder.cellfinder_main import (
+    Workflow,
+    workflow_from_cellfinder_run,
+)
+
+
+class TimeBenchmark:
+    """
+    Base class with sensible options
+    See https://asv.readthedocs.io/en/stable/benchmarks.html#benchmark-attributes
+
+    The sample_time, number, repeat, and timer attributes can be adjusted in
+    the setup() routine, which can be useful for parameterized benchmarks
+
+    Other attributes for time benchmarks not specified in this class:
+    - number: the number of iterations in each sample. If number is specified,
+    sample_time is ignored. Note that setup and teardown are not run between
+    iterations: setup runs first, then the timed benchmark routine is called
+    number times, and after that teardown runs.
+    - timer: timeit.default_timer by default
+
+    Notes about some of the default attributes for time benchmarks:
+      - warmup_time: asv will spend this time (in seconds) in calling the
+        benchmarked function repeatedly, before starting to run the
+        actual benchmark
+
+      - repeat: when not provided (repeat set to 0):
+        - if rounds==1 the default is
+            (min_repeat, max_repeat, max_time) = (1, 10, 20.0),
+        - if rounds != 1 the default is
+            (min_repeat, max_repeat, max_time) = (1, 5, 10.0)
+
+      - sample_time: `number` is determined so that each sample takes
+        approx sample_time=10ms
+    """
+
+    timeout = 60  # default: 60 s
+    version = None  # default: None (i.e. hash of source code)
+    warmup_time = 0.1  # default:0.1;
+    rounds = 2  # default:2
+    repeat = 0  # default: 0
+    sample_time = 0.01  # default: 10 ms = 0.01 s;
+    min_run_count = 2  # default:2
+
+    @classmethod
+    def setup(self):
+        cfg = Workflow()
+        cfg.setup_parameters()
+        cfg.setup_input_data()
+        self.cfg = cfg
+
+    def teardown(self):
+        shutil.rmtree(self.cfg.install_path)
+
+
+class TimeFullWorkflow(TimeBenchmark):
+    def time_workflow_from_cellfinder_run(self):
+        workflow_from_cellfinder_run(self.cfg)
+
+
+class TimeReadInputDask(TimeBenchmark):
+    def time_read_signal_w_dask(self):
+        read_with_dask(self.cfg.signal_parent_dir)
+
+    def time_read_background_w_dask(self):
+        read_with_dask(self.cfg.background_parent_dir)
+
+
+class TimeCellfinderRun(TimeBenchmark):
+    def setup(self):
+        TimeBenchmark.setup()
+        self.signal_array = read_with_dask(self.cfg.signal_parent_dir)
+        self.background_array = read_with_dask(self.cfg.background_parent_dir)
+
+    def time_cellfinder_run(self):
+        cellfinder_run(
+            self.signal_array, self.background_array, self.cfg.voxel_sizes
+        )
+
+
+class TimeSaveCells(TimeBenchmark):
+    def setup(self):
+        TimeBenchmark.setup()
+        signal_array = read_with_dask(self.cfg.signal_parent_dir)
+        background_array = read_with_dask(self.cfg.background_parent_dir)
+
+        self.detected_cells = cellfinder_run(
+            signal_array, background_array, self.cfg.voxel_sizes
+        )
+
+    def time_save_cells(self):
+        save_cells(self.detected_cells, self.cfg.detected_cells_filepath)

brainglobe_workflows/__init__.py

@@ -1,7 +1,7 @@
 from importlib.metadata import PackageNotFoundError, version
 
 try:
-    __version__ = version("brainglobe-scripts")
+    __version__ = version("brainglobe-workflows")
 except PackageNotFoundError:
     # package is not installed
     pass