Add asv

Author: dcherian

asv.conf.json

@@ -0,0 +1,162 @@
+{
+    // 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": "flox",
+
+    // The project's homepage
+    "project_url": "http://flox.readthedocs.io/",
+
+    // 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, 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}"],
+    // "build_command": [
+    //     "python setup.py build",
+    //     "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}"
+    // ],
+
+    // List of branches to benchmark. If not provided, defaults to "master"
+    // (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" 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": "http://github.com/dcherian/flox/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    "pythons": ["3.9"],
+
+    // The list of conda channel names to be searched for benchmark
+    // dependency packages in the specified order
+    "conda_channels": ["conda-forge", "nodefaults"],
+
+    // The matrix of dependencies to test.  Each key 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).
+    //
+    "matrix": {
+        "numpy_groupies": [""],
+        "numpy": [""],
+        "pandas": [""],
+        "dask-core": [""],
+        "xarray": [""],
+    },
+
+    // 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'.
+    //
+    // "exclude": [
+    //     {"python": "3.2", "sys_platform": "win32"}, // skip py3.2 on windows
+    //     {"environment_type": "conda", "six": null}, // don't run without six on conda
+    // ],
+    //
+    // "include": [
+    //     // additional env for python2.7
+    //     {"python": "2.7", "numpy": "1.8"},
+    //     // additional env if run on windows+conda
+    //     {"platform": "win32", "environment_type": "conda", "python": "2.7", "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/__init__.py

@@ -0,0 +1,7 @@
+def parameterized(names, params):
+    def decorator(func):
+        func.param_names = names
+        func.params = params
+        return func
+
+    return decorator

benchmarks/combine.py

@@ -0,0 +1,61 @@
+import numpy as np
+
+import flox
+
+from . import parameterized
+
+N = 1000
+
+
+class Combine:
+    def setup(self, *args, **kwargs):
+        raise NotImplementedError
+
+    @parameterized("kind", ("cohorts", "mapreduce"))
+    def time_combine(self, kind):
+        flox.core._npg_combine(
+            getattr(self, f"x_chunk_{kind}"),
+            **self.kwargs,
+            keepdims=True,
+            engine="numpy",
+        )
+
+    @parameterized("kind", ("cohorts", "mapreduce"))
+    def peakmem_combine(self, kind):
+        flox.core._npg_combine(
+            getattr(self, f"x_chunk_{kind}"),
+            **self.kwargs,
+            keepdims=True,
+            engine="numpy",
+        )
+
+
+class Combine1d(Combine):
+    """
+    Time the combine step for dask reductions,
+    this is for reducting along a single dimension
+    """
+
+    def setup(self, *args, **kwargs):
+        def construct_member(groups):
+            return {
+                "groups": groups,
+                "intermediates": [
+                    np.ones((40, 120, 120, 4), dtype=float),
+                    np.ones((40, 120, 120, 4), dtype=int),
+                ],
+            }
+
+        # motivated by
+        self.x_chunk_mapreduce = [
+            construct_member(groups)
+            for groups in [
+                np.array((1, 2, 3, 4)),
+                np.array((5, 6, 7, 8)),
+                np.array((9, 10, 11, 12)),
+            ]
+            * 2
+        ]
+
+        self.x_chunk_cohorts = [construct_member(groups) for groups in [np.array((1, 2, 3, 4))] * 4]
+        self.kwargs = {"agg": flox.aggregations.mean, "axis": (3,), "group_ndim": 1}

benchmarks/reduce.py

@@ -0,0 +1,53 @@
+import numpy as np
+
+import flox
+
+from . import parameterized
+
+N = 1000
+
+
+class ChunkReduce:
+    """Time the core reduction function."""
+
+    def setup(self, *args, **kwargs):
+        raise NotImplementedError
+
+    @parameterized("func", ["sum", "nansum", "mean", "nanmean", "argmax"])
+    def time_reduce(self, func):
+        flox.groupby_reduce(
+            self.array,
+            self.labels,
+            func=func,
+            axis=self.axis,
+        )
+
+    @parameterized("func", ["sum", "nansum", "mean", "nanmean", "argmax"])
+    def peakmem_reduce(self, func):
+        flox.groupby_reduce(
+            self.array,
+            self.labels,
+            func=func,
+            axis=self.axis,
+        )
+
+
+class ChunkReduce1D(ChunkReduce):
+    def setup(self, *args, **kwargs):
+        self.array = np.ones((N,))
+        self.labels = np.repeat(np.arange(5), repeats=N // 5)
+        self.axis = -1
+
+
+class ChunkReduce2D(ChunkReduce):
+    def setup(self, *args, **kwargs):
+        self.array = np.ones((N, N))
+        self.labels = np.repeat(np.arange(N // 5), repeats=5)
+        self.axis = -1
+
+
+class ChunkReduce2DAllAxes(ChunkReduce):
+    def setup(self, *args, **kwargs):
+        self.array = np.ones((N, N))
+        self.labels = np.repeat(np.arange(N // 5), repeats=5)
+        self.axis = None