Benchmarking with ASV

activitysim/abm/models/accessibility.py

@@ -52,6 +52,7 @@ def compute_accessibilities_for_zones(
         trace_od_rows = None
 
     # merge land_use_columns into od_df
+    logger.info(f"{trace_label}: merge land_use_columns into od_df")
     od_df = pd.merge(od_df, land_use_df, left_on='dest', right_index=True).sort_index()
     chunk.log_df(trace_label, "od_df", od_df)
 
@@ -69,11 +70,13 @@ def compute_accessibilities_for_zones(
     if network_los.zone_system == los.THREE_ZONE:
         locals_d['tvpb'] = network_los.tvpb
 
+    logger.info(f"{trace_label}: assign.assign_variables")
     results, trace_results, trace_assigned_locals \
         = assign.assign_variables(assignment_spec, od_df, locals_d,
                                   trace_rows=trace_od_rows, trace_label=trace_label, chunk_log=True)
 
     chunk.log_df(trace_label, "results", results)
+    logger.info(f"{trace_label}: have results")
 
     # accessibility_df = accessibility_df.copy()
     for column in results.columns:

activitysim/abm/models/initialize.py

@@ -184,11 +184,11 @@ def preload_injectables():
 
     t0 = tracing.print_elapsed_time()
 
-    # FIXME - still want to do this?
-    # if inject.get_injectable('skim_dict', None) is not None:
-    #     t0 = tracing.print_elapsed_time("preload skim_dict", t0, debug=True)
-    #
-    # if inject.get_injectable('skim_stack', None) is not None:
-    #     t0 = tracing.print_elapsed_time("preload skim_stack", t0, debug=True)
+    if config.setting('benchmarking', False):
+        # we don't want to pay for skim_dict inside any model component during
+        # benchmarking, so we'll preload skim_dict here.  Preloading is not needed
+        # for regular operation, as activitysim components can load-on-demand.
+        if inject.get_injectable('skim_dict', None) is not None:
+            t0 = tracing.print_elapsed_time("preload skim_dict", t0, debug=True)
 
     return True

activitysim/abm/models/location_choice.py

@@ -886,6 +886,10 @@ def workplace_location(
     # if multiprocessing.current_process().name =='mp_households_0':
     #     raise RuntimeError(f"fake fail {process_name}")
 
+    # disable locutor for benchmarking
+    if config.setting('benchmarking', False):
+        locutor = False
+
     iterate_location_choice(
         model_settings,
         persons_merged, persons, households,
@@ -917,6 +921,10 @@ def school_location(
     if estimator:
         write_estimation_specs(estimator, model_settings, 'school_location.yaml')
 
+    # disable locutor for benchmarking
+    if config.setting('benchmarking', False):
+        locutor = False
+
     iterate_location_choice(
         model_settings,
         persons_merged, persons, households,

activitysim/benchmarking/__init__.py

@@ -0,0 +1 @@
+from . import componentwise

activitysim/benchmarking/asv.conf.json

@@ -0,0 +1,171 @@
+{
+    // 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": "activitysim",
+
+    // The project's homepage
+    "project_url": "https://activitysim.github.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": ["master"], // 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/ActivitySim/activitysim/commit/",
+
+    // The Pythons you'd like to test against.  If not provided, defaults
+    // to the current version of Python used to run `asv`.
+    // "pythons": ["2.7", "3.6"],
+
+    // The list of conda channel names to be searched for benchmark
+    // dependency packages in the specified order
+    "conda_channels": ["conda-forge"],
+
+    // 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": {
+        "pyarrow": [],
+        "numpy": [],
+        "openmatrix": [],
+        "pandas": ["1.2"],
+        "pyyaml": [],
+        "pytables": [],
+        "toolz": [],
+        "orca": [],
+        "psutil": [],
+        "requests": [],
+        "numba": [],
+        "coverage": [],
+        "pytest": [],
+        "cytoolz": []
+    },
+
+    // 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": "../activitysim-asv/env",
+
+    // The directory (relative to the current directory) that raw benchmark
+    // results are stored in.  If not provided, defaults to "results".
+    "results_dir": "../activitysim-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": "../activitysim-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%
+    // },
+}

activitysim/benchmarking/benchmarks/mtc1full.py

@@ -0,0 +1,83 @@
+from activitysim.benchmarking.componentwise import (
+    template_component_timings,
+    template_setup_cache,
+)
+
+EXAMPLE_NAME = "example_mtc_full"
+CONFIGS_DIRS = ("configs",)
+DYNAMIC_CONFIG_DIR = "bench_configs"
+DATA_DIR = "data"
+OUTPUT_DIR = "output"
+COMPONENT_NAMES = [
+    # "compute_accessibility",
+    "school_location",
+    "workplace_location",
+    "auto_ownership_simulate",
+    "free_parking",
+    "cdap_simulate",
+    "mandatory_tour_frequency",
+    "mandatory_tour_scheduling",
+    "joint_tour_frequency",
+    "joint_tour_composition",
+    "joint_tour_participation",
+    "joint_tour_destination",
+    "joint_tour_scheduling",
+    "non_mandatory_tour_frequency",
+    "non_mandatory_tour_destination",
+    "non_mandatory_tour_scheduling",
+    "tour_mode_choice_simulate",
+    "atwork_subtour_frequency",
+    "atwork_subtour_destination",
+    "atwork_subtour_scheduling",
+    "atwork_subtour_mode_choice",
+    "stop_frequency",
+    "trip_purpose",
+    "trip_destination",
+    "trip_purpose_and_destination",
+    "trip_scheduling",
+    "trip_mode_choice",
+    # "write_data_dictionary",
+    # "track_skim_usage",
+    "write_trip_matrices",
+    # "write_tables",
+]
+BENCHMARK_SETTINGS = {
+    "households_sample_size": 48_769,
+}
+SKIM_CACHE = False
+PRELOAD_INJECTABLES = ("skim_dict",)
+REPEAT = 1
+NUMBER = 1
+TIMEOUT = 36000.0  # ten hours
+VERSION = "1"
+
+
+def setup_cache():
+    template_setup_cache(
+        EXAMPLE_NAME,
+        COMPONENT_NAMES,
+        BENCHMARK_SETTINGS,
+        dict(
+            read_skim_cache=SKIM_CACHE,
+            write_skim_cache=SKIM_CACHE,
+        ),
+        CONFIGS_DIRS,
+        DATA_DIR,
+        OUTPUT_DIR,
+        config_overload_dir=DYNAMIC_CONFIG_DIR,
+    )
+
+
+template_component_timings(
+    globals(),
+    COMPONENT_NAMES,
+    EXAMPLE_NAME,
+    (DYNAMIC_CONFIG_DIR, *CONFIGS_DIRS),
+    DATA_DIR,
+    OUTPUT_DIR,
+    PRELOAD_INJECTABLES,
+    REPEAT,
+    NUMBER,
+    TIMEOUT,
+    VERSION,
+)