BayDAG Contributions

HOW_TO_RELEASE.md

@@ -42,15 +42,16 @@
 
 00. Run black to ensure that the codebase passes all style checks.
     This check should only take a few seconds.  These checks are also done on
-    Travis and are platform independent, so they should not be necessary to
+    GitHub Actions and are platform independent, so they should not be necessary to
     replicate locally, but are listed here for completeness.
     ```sh
     black --check --diff .
     ```
 
-00. Run the regular test suite on Windows. Travis tests are done on Linux,
-    but most users are on Windows, and the test suite should also be run
-    on Windows to ensure that it works on that platform as well.  If you
+00. Run the regular test suite on Windows. Most GitHub Actions tests are done on Linux,
+    Linux (it's faster to start up and run a new clean VM for testing) but most
+    users are on Windows, and the test suite should also be run on Windows to
+    ensure that it works on that platform as well.  If you
     are not preparing this release on Windows, you should be sure to run
     at least through this step on a Windows machine before finalizing a
     release.
@@ -135,6 +136,10 @@
     ```sh
     gh release create v1.2.3
     ```
+    The process of creating and tagging a release will automatically
+    trigger various GitHub Actions scripts to build, test, and publish the
+    new release to PyPI and conda forge, assuming there are no errors.
+
     For a development pre-release, include the `--prerelease` argument.
     As the project's policy is that only formally released code is merged
     to the main branch, any pre-release should also be built against a

activitysim/abm/models/__init__.py

@@ -20,6 +20,7 @@
     joint_tour_frequency,
     joint_tour_participation,
     joint_tour_scheduling,
+    joint_tour_frequency_composition,
     location_choice,
     mandatory_scheduling,
     mandatory_tour_frequency,

activitysim/abm/models/cdap.py

@@ -78,6 +78,17 @@ def cdap_simulate(persons_merged, persons, households, chunk_size, trace_hh_id):
         file_name=model_settings["FIXED_RELATIVE_PROPORTIONS_SPEC"]
     )
 
+    add_joint_tour_utility = model_settings.get("ADD_JOINT_TOUR_UTILITY", False)
+
+    if add_joint_tour_utility:
+        # Rules and coefficients for generating cdap joint tour specs for different household sizes
+        joint_tour_coefficients_file_name = model_settings.get(
+            "JOINT_TOUR_COEFFICIENTS", "cdap_joint_tour_coefficients.csv"
+        )
+        cdap_joint_tour_coefficients = pd.read_csv(
+            config.config_file_path(joint_tour_coefficients_file_name), comment="#"
+        )
+
     persons_merged = persons_merged.to_frame()
 
     # add tour-based chunk_id so we can chunk all trips in tour together
@@ -101,11 +112,27 @@ def cdap_simulate(persons_merged, persons, households, chunk_size, trace_hh_id):
     # (also when multiprocessing locutor might not see all household sizes)
     logger.info("Pre-building cdap specs")
     for hhsize in range(2, cdap.MAX_HHSIZE + 1):
-        spec = cdap.build_cdap_spec(cdap_interaction_coefficients, hhsize, cache=True)
+        spec = cdap.build_cdap_spec(
+            cdap_interaction_coefficients,
+            hhsize,
+            cache=True,
+            joint_tour_alt=add_joint_tour_utility,
+        )
         if inject.get_injectable("locutor", False):
             spec.to_csv(
                 config.output_file_path("cdap_spec_%s.csv" % hhsize), index=True
             )
+        if add_joint_tour_utility:
+            # build cdap joint tour spec
+            # joint_spec_dependency = spec.loc[[c for c in spec.index if c.startswith(('M_p', 'N_p', 'H_p'))]]
+            joint_spec = cdap.build_cdap_joint_spec(
+                cdap_joint_tour_coefficients, hhsize, cache=True
+            )
+            if inject.get_injectable("locutor", False):
+                joint_spec.to_csv(
+                    config.output_file_path("cdap_joint_spec_%s.csv" % hhsize),
+                    index=True,
+                )
 
     if estimator:
         estimator.write_model_settings(model_settings, "cdap.yaml")
@@ -127,17 +154,32 @@ def cdap_simulate(persons_merged, persons, households, chunk_size, trace_hh_id):
 
     logger.info("Running cdap_simulate with %d persons", len(persons_merged.index))
 
-    choices = cdap.run_cdap(
-        persons=persons_merged,
-        person_type_map=person_type_map,
-        cdap_indiv_spec=cdap_indiv_spec,
-        cdap_interaction_coefficients=cdap_interaction_coefficients,
-        cdap_fixed_relative_proportions=cdap_fixed_relative_proportions,
-        locals_d=constants,
-        chunk_size=chunk_size,
-        trace_hh_id=trace_hh_id,
-        trace_label=trace_label,
-    )
+    if add_joint_tour_utility:
+        choices, hh_joint = cdap.run_cdap(
+            persons=persons_merged,
+            person_type_map=person_type_map,
+            cdap_indiv_spec=cdap_indiv_spec,
+            cdap_interaction_coefficients=cdap_interaction_coefficients,
+            cdap_fixed_relative_proportions=cdap_fixed_relative_proportions,
+            locals_d=constants,
+            chunk_size=chunk_size,
+            trace_hh_id=trace_hh_id,
+            trace_label=trace_label,
+            add_joint_tour_utility=add_joint_tour_utility,
+        )
+    else:
+        choices = cdap.run_cdap(
+            persons=persons_merged,
+            person_type_map=person_type_map,
+            cdap_indiv_spec=cdap_indiv_spec,
+            cdap_interaction_coefficients=cdap_interaction_coefficients,
+            cdap_fixed_relative_proportions=cdap_fixed_relative_proportions,
+            locals_d=constants,
+            chunk_size=chunk_size,
+            trace_hh_id=trace_hh_id,
+            trace_label=trace_label,
+            add_joint_tour_utility=add_joint_tour_utility,
+        )
 
     if estimator:
         estimator.write_choices(choices)
@@ -161,6 +203,11 @@ def cdap_simulate(persons_merged, persons, households, chunk_size, trace_hh_id):
 
     # - annotate households table
     households = households.to_frame()
+
+    if add_joint_tour_utility:
+        hh_joint = hh_joint.reindex(households.index)
+        households["has_joint_tour"] = hh_joint
+
     expressions.assign_columns(
         df=households,
         model_settings=model_settings.get("annotate_households"),

activitysim/abm/models/joint_tour_frequency_composition.py

@@ -0,0 +1,204 @@
+# ActivitySim
+# See full license in LICENSE.txt.
+import logging
+
+import numpy as np
+import pandas as pd
+import os
+from activitysim.core.interaction_simulate import interaction_simulate
+
+from activitysim.core import simulate
+from activitysim.core import tracing
+from activitysim.core import pipeline
+from activitysim.core import config
+from activitysim.core import inject
+from activitysim.core import expressions
+
+from .util import estimation
+
+from .util.overlap import hh_time_window_overlap
+from .util.tour_frequency import process_joint_tours_frequency_composition
+
+logger = logging.getLogger(__name__)
+
+
+@inject.step()
+def joint_tour_frequency_composition(
+    households_merged, persons, chunk_size, trace_hh_id
+):
+    """
+    This model predicts the frequency and composition of fully joint tours.
+    """
+
+    trace_label = "joint_tour_frequency_composition"
+    model_settings_file_name = "joint_tour_frequency_composition.yaml"
+
+    model_settings = config.read_model_settings(model_settings_file_name)
+
+    alt_tdd = simulate.read_model_alts(
+        "joint_tour_frequency_composition_alternatives.csv", set_index="alt"
+    )
+
+    # - only interested in households with more than one cdap travel_active person and
+    # - at least one non-preschooler
+    households_merged = households_merged.to_frame()
+    choosers = households_merged[households_merged.participates_in_jtf_model].copy()
+
+    # - only interested in persons in choosers households
+    persons = persons.to_frame()
+    persons = persons[persons.household_id.isin(choosers.index)]
+
+    logger.info("Running %s with %d households", trace_label, len(choosers))
+
+    # alt preprocessor
+    alt_preprocessor_settings = model_settings.get("ALTS_PREPROCESSOR", None)
+    if alt_preprocessor_settings:
+
+        locals_dict = {}
+
+        alt_tdd = alt_tdd.copy()
+
+        expressions.assign_columns(
+            df=alt_tdd,
+            model_settings=alt_preprocessor_settings,
+            locals_dict=locals_dict,
+            trace_label=trace_label,
+        )
+
+    # - preprocessor
+    preprocessor_settings = model_settings.get("preprocessor", None)
+    if preprocessor_settings:
+
+        locals_dict = {
+            "persons": persons,
+            "hh_time_window_overlap": hh_time_window_overlap,
+        }
+
+        expressions.assign_columns(
+            df=choosers,
+            model_settings=preprocessor_settings,
+            locals_dict=locals_dict,
+            trace_label=trace_label,
+        )
+
+    estimator = estimation.manager.begin_estimation("joint_tour_frequency_composition")
+
+    model_spec = simulate.read_model_spec(file_name=model_settings["SPEC"])
+    coefficients_df = simulate.read_model_coefficients(model_settings)
+    model_spec = simulate.eval_coefficients(model_spec, coefficients_df, estimator)
+
+    constants = config.get_model_constants(model_settings)
+
+    if estimator:
+        estimator.write_spec(model_settings)
+        estimator.write_model_settings(model_settings, model_settings_file_name)
+        estimator.write_coefficients(coefficients_df, model_settings)
+        estimator.write_choosers(choosers)
+        estimator.write_alternatives(alts)
+
+        assert choosers.index.name == "household_id"
+        assert "household_id" not in choosers.columns
+        choosers["household_id"] = choosers.index
+
+        estimator.set_chooser_id(choosers.index.name)
+
+    # The choice value 'joint_tour_frequency_composition' assigned by interaction_simulate
+    # is the index value of the chosen alternative in the alternatives table.
+    choices = interaction_simulate(
+        choosers=choosers,
+        alternatives=alt_tdd,
+        spec=model_spec,
+        locals_d=constants,
+        chunk_size=chunk_size,
+        trace_label=trace_label,
+        trace_choice_name=trace_label,
+        estimator=estimator,
+    )
+
+    if estimator:
+        estimator.write_choices(choices)
+        choices = estimator.get_survey_values(
+            choices, "households", "joint_tour_frequency_composition"
+        )
+        estimator.write_override_choices(choices)
+        estimator.end_estimation()
+
+    # add joint tour frequency composition column to household table
+    households_merged["joint_tour_frequency_composition"] = choices.reindex(
+        households_merged.index
+    ).fillna(0)
+
+    # - create joint_tours based on choices
+
+    # - we need a person_id in order to generate the tour index (and for register_traceable_table)
+    # - but we don't know the tour participants yet
+    # - so we arbitrarily choose the first person in the household
+    # - to be point person for the purpose of generating an index and setting origin
+    temp_point_persons = persons.loc[persons.PNUM == 1]
+    temp_point_persons["person_id"] = temp_point_persons.index
+    temp_point_persons = temp_point_persons.set_index("household_id")
+    temp_point_persons = temp_point_persons[["person_id", "home_zone_id"]]
+
+    # create a tours table of tour_category "joint" and different tour_types (e.g. shopping, eat)
+    # and add the composition column (adults or children or mixed) to the tour
+
+    # Choices
+    # hhid	choice
+    # 11111	1
+    # 22222	2
+    # 33333	3
+
+    # Alts
+    # alt	purpose1	purpose2	party1	party2	eat	shop
+    # 1	    5	        0	        3	    0	    1	0
+    # 2	    5	        6	        1	    3	    1	1
+    # 3	    6	        0	        1	    0	    0	1
+
+    # Joint Tours
+    # hhid	type	category	composition
+    # 11111	eat	    joint	    mixed
+    # 22222	eat	    joint	    adults
+    # 22222	shop	joint	    mixed
+    # 33333	shop	joint	    adults
+
+    joint_tours = process_joint_tours_frequency_composition(
+        choices, alt_tdd, temp_point_persons
+    )
+
+    tours = pipeline.extend_table("tours", joint_tours)
+
+    tracing.register_traceable_table("tours", joint_tours)
+    pipeline.get_rn_generator().add_channel("tours", joint_tours)
+
+    # we expect there to be an alt with no tours - which we can use to backfill non-travelers
+    no_tours_alt = 0
+    households_merged["joint_tour_frequency_composition"] = (
+        choices.reindex(households_merged.index).fillna(no_tours_alt).astype(str)
+    )
+
+    households_merged["num_hh_joint_tours"] = (
+        joint_tours.groupby("household_id")
+        .size()
+        .reindex(households_merged.index)
+        .fillna(0)
+        .astype(np.int8)
+    )
+
+    pipeline.replace_table("households", households_merged)
+
+    tracing.print_summary(
+        "joint_tour_frequency_composition",
+        households_merged.joint_tour_frequency_composition,
+        value_counts=True,
+    )
+
+    if trace_hh_id:
+        tracing.trace_df(
+            households_merged, label="joint_tour_frequency_composition.households"
+        )
+
+        tracing.trace_df(
+            joint_tours,
+            label="joint_tour_frequency_composition.joint_tours",
+            slicer="household_id",
+        )