run benchmarking on estimators (#900)

.github/workflows/benchmark.yml

@@ -0,0 +1,23 @@
+name: Benchmark
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  benchmark:
+    name: benchmark
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+      - uses: actions/checkout@v3
+      - run: git fetch origin $GITHUB_BASE_REF:base $GITHUB_REF:pr
+      - run: pip install asv virtualenv
+      - run: asv machine --yes
+      - run: asv continuous base pr

asv.conf.json

@@ -0,0 +1,195 @@
+{
+    // 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": "NiMARE",
+
+    // The project's homepage
+    "project_url": "https://github.com/neurostuff/NiMARE",
+
+    // 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}"
+    // ],
+
+    // Customizable commands for installing and uninstalling the project.
+    // See asv.conf.json documentation.
+    // "install_command": ["in-dir={env_dir} python -mpip install {wheel_file}"],
+    "install_command": ["python -mpip install .[tests]"],
+    // "uninstall_command": ["return-code=any python -mpip 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": ["3.8", "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/bench_cbma.py

@@ -0,0 +1,57 @@
+"""Benchmark the CBMA estimators."""
+
+import os
+
+import nimare
+from nimare.meta.cbma import ALE, KDA, MKDAChi2, MKDADensity
+from nimare.tests.utils import get_test_data_path
+
+
+class TimeCBMA:
+    """Time CBMA estimators."""
+
+    def setup(self):
+        """
+        Setup the data.
+
+        Loads the dataset required for the benchmarks.
+        """
+        self.dataset = nimare.dataset.Dataset(
+            os.path.join(get_test_data_path(), "test_pain_dataset.json")
+        )
+
+    def time_ale(self):
+        """
+        Time the ALE estimator.
+
+        Fits the ALE estimator to the dataset and measures the time taken.
+        """
+        meta = ALE()
+        meta.fit(self.dataset)
+
+    def time_mkdadensity(self):
+        """
+        Time the MKDADensity estimator.
+
+        Fits the MKDADensity estimator to the dataset and measures the time taken.
+        """
+        meta = MKDADensity()
+        meta.fit(self.dataset)
+
+    def time_kda(self):
+        """
+        Time the KDA estimator.
+
+        Fits the KDA estimator to the dataset and measures the time taken.
+        """
+        meta = KDA()
+        meta.fit(self.dataset)
+
+    def time_mkdachi2(self):
+        """
+        Time the MKDAChi2 estimator.
+
+        Fits the MKDAChi2 estimator to the dataset and measures the time taken.
+        """
+        meta = MKDAChi2()
+        meta.fit(self.dataset, self.dataset)

benchmarks/bench_ibma.py.bak

@@ -0,0 +1,97 @@
+"""Benchmark the IBMA estimators."""
+from shutil import copyfile
+import os
+import tempfile
+
+import nimare
+from nimare.meta.ibma import Fishers, Stouffers, WeightedLeastSquares, DerSimonianLaird, Hedges
+from nimare.tests.utils import get_test_data_path
+
+
+class TimeIBMA:
+    """Time IBMA estimators."""
+
+    def setup(self):
+        """
+        Setup the data.
+
+        Creates a temporary directory, loads the dataset, and moves the image contents
+        of the dataset to the temporary directory.
+        """
+        self.tmpdir = tempfile.TemporaryDirectory()
+
+        # Load dataset
+        dset_file = os.path.join(get_test_data_path(), "test_pain_dataset.json")
+        dset_dir = os.path.join(get_test_data_path(), "test_pain_dataset")
+        mask_file = os.path.join(dset_dir, "mask.nii.gz")
+        dset = nimare.dataset.Dataset(dset_file, mask=mask_file)
+        dset.update_path(dset_dir)
+        # Move image contents of Dataset to temporary directory
+        for c in dset.images.columns:
+            if c.endswith("__relative"):
+                continue
+            for f in dset.images[c].values:
+                if (f is None) or not os.path.isfile(f):
+                    continue
+                new_f = f.replace(
+                    dset_dir.rstrip(os.path.sep), str(self.tmpdir.name).rstrip(os.path.sep)
+                )
+                dirname = os.path.dirname(new_f)
+                if not os.path.isdir(dirname):
+                    os.makedirs(dirname)
+                copyfile(f, new_f)
+        dset.update_path(self.tmpdir.name)
+        self.dataset = dset
+
+    def time_fishers(self):
+        """
+        Time the Fishers estimator.
+
+        Fits the Fishers estimator to the dataset and measures the time taken.
+        """
+        meta = Fishers()
+        meta.fit(self.dataset)
+
+    def time_stouffers(self):
+        """
+        Time the Stouffers estimator.
+
+        Fits the Stouffers estimator to the dataset and measures the time taken.
+        """
+        meta = Stouffers()
+        meta.fit(self.dataset)
+
+    def time_weighted_least_squares(self):
+        """
+        Time the Weighted Least Squares estimator.
+
+        Fits the Weighted Least Squares estimator to the dataset and measures the time taken.
+        """
+        meta = WeightedLeastSquares()
+        meta.fit(self.dataset)
+
+    def time_der_simonian_laird(self):
+        """
+        Time the DerSimonian-Laird estimator.
+
+        Fits the DerSimonian-Laird estimator to the dataset and measures the time taken.
+        """
+        meta = DerSimonianLaird()
+        meta.fit(self.dataset)
+
+    def time_hedges(self):
+        """
+        Time the Hedges estimator.
+
+        Fits the Hedges estimator to the dataset and measures the time taken.
+        """
+        meta = Hedges()
+        meta.fit(self.dataset)
+
+    def teardown(self):
+        """
+        Clean up the temporary directory.
+
+        Removes the temporary directory and its contents.
+        """
+        self.tmpdir.cleanup()