Use pandas 2 for docbuild environment

.github/workflows/core_tests.yml

@@ -8,7 +8,7 @@ on:
   pull_request:
     branches:
       - '*'
-  
+
   workflow_dispatch:
 
 env:
@@ -455,7 +455,7 @@ jobs:
 
   develop-docbuild:
     needs: foundation
-    if: github.ref_name == 'main'
+    if: github.ref_name == 'main' || github.ref_name == 'docs-fix'
     name: develop-docbuild
     runs-on: ubuntu-latest
     permissions:

activitysim/abm/misc.py

@@ -18,7 +18,6 @@
 
 @workflow.cached_object
 def households_sample_size(state: workflow.State, override_hh_ids) -> int:
-
     if override_hh_ids is None:
         return state.settings.households_sample_size
     else:
@@ -27,7 +26,6 @@ def households_sample_size(state: workflow.State, override_hh_ids) -> int:
 
 @workflow.cached_object
 def override_hh_ids(state: workflow.State) -> np.ndarray | None:
-
     hh_ids_filename = state.settings.hh_ids
     if hh_ids_filename is None:
         return None
@@ -65,7 +63,6 @@ def override_hh_ids(state: workflow.State) -> np.ndarray | None:
 
 @workflow.cached_object
 def trace_od(state: workflow.State) -> tuple[int, int] | None:
-
     od = state.settings.trace_od
 
     if od and not (

activitysim/abm/models/auto_ownership.py

@@ -72,7 +72,6 @@ def auto_ownership_simulate(
     # - preprocessor
     preprocessor_settings = model_settings.preprocessor
     if preprocessor_settings:
-
         locals_d = {}
         if constants is not None:
             locals_d.update(constants)

activitysim/abm/models/initialize.py

@@ -148,7 +148,6 @@ def initialize_households(
     model_settings_file_name: str = "initialize_households.yaml",
     trace_label: str = "initialize_households",
 ) -> None:
-
     with chunk.chunk_log(state, trace_label, base=True) as chunk_sizer:
         chunk_sizer.log_rss(f"{trace_label}.inside-yield")
 

activitysim/abm/models/input_checker.py

@@ -209,7 +209,6 @@ class HouseholdValidator(pydantic.BaseModel) list_of_households...
 
 
 def report_errors(state, input_checker_settings, v_warnings, v_errors):
-
     # logging overall statistics first before printing details
     for table_settings in input_checker_settings["table_list"]:
         table_name = table_settings["name"]

activitysim/abm/models/non_mandatory_tour_frequency.py

@@ -236,7 +236,6 @@ def non_mandatory_tour_frequency(
     # - preprocessor
     preprocessor_settings = model_settings.preprocessor
     if preprocessor_settings:
-
         locals_dict = {
             "person_max_window": lambda x: person_max_window(state, x),
             "person_available_periods": lambda persons, start_bin, end_bin, continuous: person_available_periods(

activitysim/abm/models/trip_purpose_and_destination.py

@@ -69,7 +69,6 @@ def trip_purpose_and_destination(
     model_settings_file_name: str = "trip_purpose_and_destination.yaml",
     trace_label: str = "trip_purpose_and_destination",
 ) -> None:
-
     if model_settings is None:
         model_settings = TripPurposeAndDestinationSettings.read_settings_file(
             state.filesystem,

activitysim/abm/models/trip_scheduling_choice.py

@@ -358,7 +358,6 @@ def trip_scheduling_choice(
     model_settings_file_name: str = "trip_scheduling_choice.yaml",
     trace_label: str = "trip_scheduling_choice",
 ) -> None:
-
     if model_settings is None:
         model_settings = TripSchedulingChoiceSettings.read_settings_file(
             state.filesystem,
@@ -416,7 +415,6 @@ def trip_scheduling_choice(
     }
 
     if preprocessor_settings:
-
         simulate.set_skim_wrapper_targets(tours_df, skims)
 
         expressions.assign_columns(

activitysim/abm/models/util/cdap.py

@@ -297,7 +297,6 @@ def cached_joint_spec_name(hhsize):
 
 
 def get_cached_spec(state: workflow.State, hhsize):
-
     spec_name = cached_spec_name(hhsize)
 
     spec = state.get_injectable(spec_name, None)
@@ -319,7 +318,6 @@ def get_cached_spec(state: workflow.State, hhsize):
 
 
 def get_cached_joint_spec(state: workflow.State, hhsize):
-
     spec_name = cached_joint_spec_name(hhsize)
 
     spec = state.get_injectable(spec_name, None)
@@ -625,7 +623,6 @@ def build_cdap_joint_spec(
     #         N_p1  0.0  0.0  0.0  1.0  1.0  1.0  0.0  0.0  0.0
     for pnum in range(1, hhsize + 1):
         for activity in ["M", "N", "H"]:
-
             new_row_index = len(spec)
             spec.loc[new_row_index, expression_name] = add_pn(activity, pnum)
 
@@ -638,7 +635,6 @@ def build_cdap_joint_spec(
 
     # for each row in the joint util table
     for row in joint_tour_coefficients.itertuples():
-
         # if there is no dependencies
         if row.dependency is np.nan:
             expression = row.Expression

activitysim/abm/models/util/overlap.py

@@ -138,7 +138,6 @@ def p2p_time_window_overlap(state: workflow.State, p1_ids, p2_ids):
 
 
 def person_pairs(persons):
-
     p = persons[["household_id", "adult"]].reset_index()
     p2p = pd.merge(p, p, left_on="household_id", right_on="household_id", how="outer")
 
@@ -166,7 +165,6 @@ def person_pairs(persons):
 
 
 def hh_time_window_overlap(state: workflow.State, households, persons):
-
     p2p = person_pairs(persons)
 
     p2p["max_overlap"] = p2p_time_window_overlap(state, p2p.person1, p2p.person2)
@@ -189,7 +187,6 @@ def hh_time_window_overlap(state: workflow.State, households, persons):
 
 
 def person_time_window_overlap(state: workflow.State, persons):
-
     p2p = person_pairs(persons)
 
     p2p["max_overlap"] = p2p_time_window_overlap(state, p2p.person1, p2p.person2)
@@ -224,7 +221,6 @@ def person_time_window_overlap(state: workflow.State, persons):
 
 
 def person_max_window(state: workflow.State, persons):
-
     timetable = state.get_injectable("timetable")
 
     # ndarray with one row per person and one column per time period

activitysim/abm/models/util/probabilistic_scheduling.py

@@ -93,7 +93,6 @@ def _report_bad_choices(
     # log the indexes of the first MAX_PRINT offending rows
     MAX_PRINT = 0
     for idx in df.index[:MAX_PRINT].values:
-
         row_msg = "%s : failed %s = %s (hh_id = %s)" % (
             trace_label,
             df.index.name,
@@ -113,7 +112,6 @@ def _preprocess_departure_probs(
     depart_alt_base,
     first_trip_in_leg,
 ):
-
     # zero out probs outside earliest-latest window if one exists
     probs_cols = [c for c in probs_spec.columns if c not in probs_join_cols]
     if clip_earliest_latest:
@@ -129,7 +127,6 @@ def _preprocess_departure_probs(
 
 
 def _preprocess_stop_duration_probs(choosers):
-
     # convert wide to long. duration probs are stored in long format so that
     # inbound/outbound duration probs, which both have a 0 alternative, can be
     # stored in a single config file. open to better suggestions here.
@@ -203,7 +200,6 @@ def _preprocess_scheduling_probs(
 def _postprocess_scheduling_choices(
     scheduling_mode, depart_alt_base, choices, choice_cols, choosers
 ):
-
     """
     This method just converts the choice column indexes returned by the
     logit.make_choices() method into actual departure time values that are
@@ -222,7 +218,6 @@ def _postprocess_scheduling_choices(
     # get applied to trip-specific departure and arrival times, so depart_alt_base
     # is a column/series rather than a scalar.
     if scheduling_mode == "stop_duration":
-
         # for outbound trips, offsets get added to the departure time constraint
         if choosers.outbound.all():
             depart_alt_base = choosers["earliest"]

activitysim/abm/models/util/test/test_input_checker.py

@@ -7,11 +7,11 @@
 
 import pandas as pd
 import pandas.testing as pdt
+import pandera as pa
 import pytest
 import yaml
-import pandera as pa
 
-from activitysim.abm.models.input_checker import validate_with_pandera, TABLE_STORE
+from activitysim.abm.models.input_checker import TABLE_STORE, validate_with_pandera
 
 
 @pytest.fixture(scope="class")
@@ -56,7 +56,6 @@ def households():
 
 
 def test_passing_dataframe(households, v_errors, v_warnings, validation_settings):
-
     TABLE_STORE["households"] = households
 
     class input_checker:
@@ -83,7 +82,6 @@ def dummy_example(cls, households: pd.DataFrame):
 
 
 def test_error_dataframe(households, v_errors, v_warnings, validation_settings):
-
     TABLE_STORE["households"] = households
 
     class input_checker:
@@ -107,7 +105,6 @@ class Household(pa.DataFrameModel):
 
 
 def test_warning_dataframe(households, v_errors, v_warnings, validation_settings):
-
     TABLE_STORE["households"] = households
 
     class input_checker:
@@ -132,7 +129,6 @@ class Household(pa.DataFrameModel):
 def test_custom_check_failure_dataframe(
     households, v_errors, v_warnings, validation_settings
 ):
-
     TABLE_STORE["households"] = households
 
     class input_checker:

activitysim/abm/models/util/trip.py

@@ -15,7 +15,6 @@
 
 
 def failed_trip_cohorts(trips, failed):
-
     # outbound trips in a tour with a failed outbound trip
     bad_outbound_trips = trips.outbound & (
         trips.tour_id.isin(trips.tour_id[failed & trips.outbound])

activitysim/abm/tables/households.py

@@ -127,7 +127,6 @@ def households_merged(
     land_use: pd.DataFrame,
     accessibility: pd.DataFrame,
 ) -> pd.DataFrame:
-
     households = simple_table_join(
         households,
         land_use,

activitysim/abm/tables/table_dict.py

@@ -18,13 +18,11 @@
 
 @workflow.cached_object
 def rng_channels(state: workflow.State):
-
     return cid.RANDOM_CHANNELS
 
 
 @workflow.cached_object
 def traceable_tables(state: workflow.State):
-
     # names of all traceable tables ordered by dependency on household_id
     # e.g. 'persons' has to be registered AFTER 'households'
 

activitysim/abm/test/run_multi_zone_mp.py

@@ -1,3 +1,5 @@
+from __future__ import annotations
+
 # ActivitySim
 # See full license in LICENSE.txt.
 import os
@@ -13,7 +15,6 @@
 
 
 def test_mp_run():
-
     configs_dir = [example_path("configs_3_zone"), example_path("configs")]
     data_dir = example_path("data_3")
 
@@ -34,5 +35,4 @@ def test_mp_run():
 
 
 if __name__ == "__main__":
-
     test_mp_run()

activitysim/abm/test/test_misc/setup_utils.py

@@ -36,7 +36,6 @@ def example_path(dirname):
 
 
 def setup_dirs(ancillary_configs_dir=None, data_dir=None):
-
     # ancillary_configs_dir is used by run_mp to test multiprocess
 
     # test_pipeline_configs_dir = os.path.join(os.path.dirname(__file__), "configs")
@@ -69,7 +68,6 @@ def setup_dirs(ancillary_configs_dir=None, data_dir=None):
 
 
 def close_handlers():
-
     loggers = logging.Logger.manager.loggerDict
     for name in loggers:
         logger = logging.getLogger(name)