Add benchmarks (#2977)

Co-authored-by: Rahul Shrestha <rahulshrestha0101@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Ilan Gold <ilanbassgold@gmail.com>

.github/workflows/benchmark.yml

@@ -0,0 +1,59 @@
+name: Benchmark
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  benchmark:
+    runs-on: ${{ matrix.os }}
+    defaults:
+      run:
+        shell: bash -e {0} # -e to fail on error
+
+    strategy:
+      fail-fast: false
+      matrix:
+        python: ["3.12"]
+        os: [ubuntu-latest]
+
+    env:
+      OS: ${{ matrix.os }}
+      PYTHON: ${{ matrix.python }}
+      ASV_DIR: "./benchmarks"
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          filter: blob:none
+
+      - name: Fetch main branch for `asv run`’s hash
+        run: git fetch origin main:main
+        if: ${{ github.ref_name != 'main' }}
+
+      - name: Set up Python ${{ matrix.python }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python }}
+          cache: 'pip'
+
+      - name: Cache datasets
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.cache
+          key: benchmark-state-${{ hashFiles('benchmarks/**') }}
+
+      - name: Install dependencies
+        run: pip install asv
+
+      - name: Configure ASV
+        working-directory: ${{ env.ASV_DIR }}
+        run: asv machine --yes
+
+      - name: Quick benchmark run
+        working-directory: ${{ env.ASV_DIR }}
+        run: asv run --dry-run --quick --show-stderr --verbose HEAD^!

.github/workflows/check-pr.yml

@@ -45,7 +45,10 @@ jobs:
     needs: check-milestone
     if: ${{ needs.check-milestone.outputs.no-relnotes-reason == '' && !contains(github.event.pull_request.labels.*.name, 'Development Process 🚀') }}
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          filter: blob:none
       - name: Find out if relevant release notes are modified
         uses: dorny/paths-filter@v2
         id: changes

.github/workflows/publish.yml

@@ -11,8 +11,11 @@ jobs:
     permissions:
       id-token: write # to authenticate as Trusted Publisher to pypi.org
     steps:
-      - uses: actions/checkout@v3
-      - uses: actions/setup-python@v4
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          filter: blob:none
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.x"
           cache: "pip"

.gitignore

@@ -43,3 +43,7 @@ Thumbs.db
 # IDEs and editors
 /.idea/
 /.vscode/
+
+# asv benchmark files
+/benchmarks/.asv
+/benchmarks/data/

benchmarks/README.md

@@ -0,0 +1,10 @@
+# Scanpy Benchmarks
+
+This directory contains code for benchmarking Scanpy using [asv][].
+
+The functionality is checked using the [`benchmark.yml`][] workflow.
+Benchmarks are run using the [benchmark bot][].
+
+[asv]: https://asv.readthedocs.io/
+[`benchmark.yml`]: ../.github/workflows/benchmark.yml
+[benchmark bot]: https://github.com/apps/scverse-benchmark

benchmarks/asv.conf.json

@@ -0,0 +1,168 @@
+{
+    // 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": "scanpy",
+
+    // The project's homepage
+    "project_url": "https://scanpy.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": ["python -mpip install {wheel_file}"],
+    // "uninstall_command": ["return-code=any python -mpip uninstall -y {project}"],
+    "build_command": [
+        "python -m pip install build",
+        "python -m build --wheel -o {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
+
+    // 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": "https://github.com/scverse/scanpy/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", "3.12"],
+
+    // The list of conda channel names to be searched for benchmark
+    // dependency packages in the specified order
+    "conda_channels": ["conda-forge", "defaults"],
+
+    // 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": [""],
+        // "scipy": ["1.2", ""],
+        "scipy": [""],
+        "h5py": [""],
+        "natsort": [""],
+        "pandas": [""],
+        "memory_profiler": [""],
+        "zarr": [""],
+        "pytest": [""],
+        "scanpy": [""],
+        "python-igraph": [""],
+        // "psutil": [""]
+    },
+
+    // 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/benchmarks/preprocessing.py

@@ -0,0 +1,101 @@
+"""
+This module will benchmark preprocessing operations in Scanpy
+API documentation: https://scanpy.readthedocs.io/en/stable/api/preprocessing.html
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import scanpy as sc
+
+from .utils import pbmc68k_reduced
+
+if TYPE_CHECKING:
+    from anndata import AnnData
+
+
+adata: AnnData
+
+
+def setup():
+    global adata
+    adata = pbmc68k_reduced()
+
+
+def time_calculate_qc_metrics():
+    adata.var["mt"] = adata.var_names.str.startswith("MT-")
+    sc.pp.calculate_qc_metrics(
+        adata, qc_vars=["mt"], percent_top=None, log1p=False, inplace=True
+    )
+
+
+def peakmem_calculate_qc_metrics():
+    adata.var["mt"] = adata.var_names.str.startswith("MT-")
+    sc.pp.calculate_qc_metrics(
+        adata, qc_vars=["mt"], percent_top=None, log1p=False, inplace=True
+    )
+
+
+def time_filter_cells():
+    sc.pp.filter_cells(adata, min_genes=200)
+
+
+def peakmem_filter_cells():
+    sc.pp.filter_cells(adata, min_genes=200)
+
+
+def time_filter_genes():
+    sc.pp.filter_genes(adata, min_cells=3)
+
+
+def peakmem_filter_genes():
+    sc.pp.filter_genes(adata, min_cells=3)
+
+
+def time_normalize_total():
+    sc.pp.normalize_total(adata, target_sum=1e4)
+
+
+def peakmem_normalize_total():
+    sc.pp.normalize_total(adata, target_sum=1e4)
+
+
+def time_log1p():
+    sc.pp.log1p(adata)
+
+
+def peakmem_time_log1p():
+    sc.pp.log1p(adata)
+
+
+def time_pca():
+    sc.pp.pca(adata, svd_solver="arpack")
+
+
+def peakmem_pca():
+    sc.pp.pca(adata, svd_solver="arpack")
+
+
+def time_highly_variable_genes():
+    sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+
+
+def peakmem_highly_variable_genes():
+    sc.pp.highly_variable_genes(adata, min_mean=0.0125, max_mean=3, min_disp=0.5)
+
+
+def time_regress_out():
+    sc.pp.regress_out(adata, ["n_counts", "percent_mito"])
+
+
+def peakmem_regress_out():
+    sc.pp.regress_out(adata, ["n_counts", "percent_mito"])
+
+
+def time_scale():
+    sc.pp.scale(adata, max_value=10)
+
+
+def peakmem_scale():
+    sc.pp.scale(adata, max_value=10)