mostly through test1

Author: jpn--

activitysim/abm/models/summarize.py

@@ -9,7 +9,7 @@
 import pandas as pd
 
 from activitysim.core import expressions, workflow
-from activitysim.core.configuration.base import PydanticReadable
+from activitysim.core.configuration.base import PreprocessorSettings, PydanticReadable
 from activitysim.core.los import Network_LOS
 
 logger = logging.getLogger(__name__)
@@ -201,7 +201,7 @@ def manual_breaks(
         return bins
 
 
-class SummarizeSettings(PydanticReadable):
+class SummarizeSettings(PydanticReadable, extra="forbid"):
     """
     Settings for the `summarize` component.
     """
@@ -215,6 +215,8 @@ class SummarizeSettings(PydanticReadable):
     EXPORT_PIPELINE_TABLES: bool = True
     """To export pipeline tables for expression development."""
 
+    preprocessor: PreprocessorSettings | None = None
+
 
 @workflow.step
 def summarize(

activitysim/abm/models/trip_matrices.py

@@ -3,6 +3,8 @@
 from __future__ import annotations
 
 import logging
+from pathlib import Path
+from typing import Any
 
 import numpy as np
 import openmatrix as omx
@@ -15,6 +17,17 @@
 logger = logging.getLogger(__name__)
 
 
+class MatrixTableSettings(PydanticReadable):
+    name: str
+    data_field: str
+
+
+class MatrixSettings(PydanticReadable):
+    file_name: Path
+    tables: list[MatrixTableSettings] = []
+    is_tap: bool = False
+
+
 class WriteTripMatricesSettings(PydanticReadable):
     """
     Settings for the `write_trip_matrices` component.
@@ -26,6 +39,12 @@ class WriteTripMatricesSettings(PydanticReadable):
     HH_EXPANSION_WEIGHT_COL: str = "sample_rate"
     """Column represents the sampling rate of households"""
 
+    MATRICES: list[MatrixSettings] = []
+
+    CONSTANTS: dict[str, Any] = {}
+
+    preprocessor: PreprocessorSettings | None = None
+
 
 @workflow.step(copy_tables=["trips"])
 def write_trip_matrices(
@@ -251,9 +270,11 @@ def write_trip_matrices(
         )
 
 
-@workflow.func
 def annotate_trips(
-    state: workflow.State, trips: pd.DataFrame, network_los, model_settings
+    state: workflow.State,
+    trips: pd.DataFrame,
+    network_los,
+    model_settings: WriteTripMatricesSettings,
 ):
     """
     Add columns to local trips table. The annotator has
@@ -298,7 +319,7 @@ def annotate_trips(
 
     # Data will be expanded by an expansion weight column from
     # the households pipeline table, if specified in the model settings.
-    hh_weight_col = model_settings.get("HH_EXPANSION_WEIGHT_COL")
+    hh_weight_col = model_settings.HH_EXPANSION_WEIGHT_COL
 
     if hh_weight_col and hh_weight_col not in trips_df:
         logger.info("adding '%s' from households to trips table" % hh_weight_col)
@@ -314,7 +335,7 @@ def write_matrices(
     zone_index,
     orig_index,
     dest_index,
-    model_settings,
+    model_settings: WriteTripMatricesSettings,
     is_tap=False,
 ):
     """
@@ -329,30 +350,30 @@ def write_matrices(
     but the table 'data_field's must be summable types: ints, floats, bools.
     """
 
-    matrix_settings = model_settings.get("MATRICES")
+    matrix_settings = model_settings.MATRICES
 
     if not matrix_settings:
         logger.error("Missing MATRICES setting in write_trip_matrices.yaml")
 
     for matrix in matrix_settings:
-        matrix_is_tap = matrix.get("is_tap", False)
+        matrix_is_tap = matrix.is_tap
 
         if matrix_is_tap == is_tap:  # only write tap matrices to tap matrix files
-            filename = matrix.get("file_name")
+            filename = str(matrix.file_name)
             filepath = state.get_output_file_path(filename)
             logger.info("opening %s" % filepath)
             file = omx.open_file(str(filepath), "w")  # possibly overwrite existing file
-            table_settings = matrix.get("tables")
+            table_settings = matrix.tables
 
             for table in table_settings:
-                table_name = table.get("name")
-                col = table.get("data_field")
+                table_name = table.name
+                col = table.data_field
 
                 if col not in aggregate_trips:
                     logger.error(f"missing {col} column in aggregate_trips DataFrame")
                     return
 
-                hh_weight_col = model_settings.get("HH_EXPANSION_WEIGHT_COL")
+                hh_weight_col = model_settings.HH_EXPANSION_WEIGHT_COL
                 if hh_weight_col:
                     aggregate_trips[col] = (
                         aggregate_trips[col] / aggregate_trips[hh_weight_col]

activitysim/abm/models/trip_mode_choice.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import logging
+from typing import Any
 
 import numpy as np
 import pandas as pd
@@ -20,13 +21,13 @@
     workflow,
 )
 from activitysim.core.configuration.base import PreprocessorSettings, PydanticReadable
-from activitysim.core.configuration.logit import LogitComponentSettings
+from activitysim.core.configuration.logit import TemplatedLogitComponentSettings
 from activitysim.core.util import assign_in_place
 
 logger = logging.getLogger(__name__)
 
 
-class TripModeChoiceSettings(LogitComponentSettings):
+class TripModeChoiceSettings(TemplatedLogitComponentSettings, extra="forbid"):
     """
     Settings for the `trip_mode_choice` component.
     """
@@ -41,6 +42,14 @@ class TripModeChoiceSettings(LogitComponentSettings):
     """List of columns to be filtered from the dataframe to reduce memory
     needs filter chooser table to these fields"""
 
+    CHOOSER_COLS_TO_KEEP: list[str] = []
+
+    tvpb_mode_path_types: dict[str, Any] = {}
+
+    FORCE_ESCORTEE_CHAUFFEUR_MODE_MATCH: bool = True
+
+    annotate_trips: PreprocessorSettings | None = None
+
 
 @workflow.step
 def trip_mode_choice(
@@ -187,9 +196,9 @@ def trip_mode_choice(
         estimator.write_spec(model_settings)
         estimator.write_model_settings(model_settings, model_settings_file_name)
 
-    model_spec = state.filesystem.read_model_spec(file_name=model_settings["SPEC"])
+    model_spec = state.filesystem.read_model_spec(file_name=model_settings.SPEC)
     nest_spec = config.get_logit_model_settings(model_settings)
-    cols_to_keep = model_settings.get("CHOOSER_COLS_TO_KEEP", None)
+    cols_to_keep = model_settings.CHOOSER_COLS_TO_KEEP
 
     choices_list = []
     cols_to_keep_list = []
@@ -296,7 +305,7 @@ def trip_mode_choice(
 
     # add cached tvpb_logsum tap choices for modes specified in tvpb_mode_path_types
     if network_los.zone_system == los.THREE_ZONE:
-        tvpb_mode_path_types = model_settings.get("tvpb_mode_path_types")
+        tvpb_mode_path_types = model_settings.tvpb_mode_path_types
         for mode, path_type in tvpb_mode_path_types.items():
             skim_cache = tvpb_logsum_odt.cache[path_type]
 
@@ -325,8 +334,9 @@ def trip_mode_choice(
 
     assign_in_place(trips_df, choices_df)
 
-    if state.is_table("school_escort_tours") & model_settings.get(
-        "FORCE_ESCORTEE_CHAUFFEUR_MODE_MATCH", True
+    if (
+        state.is_table("school_escort_tours")
+        & model_settings.FORCE_ESCORTEE_CHAUFFEUR_MODE_MATCH
     ):
         trips_df = (
             school_escort_tours_trips.force_escortee_trip_modes_to_match_chauffeur(
@@ -344,7 +354,7 @@ def trip_mode_choice(
 
     state.add_table("trips", trips_df)
 
-    if model_settings.get("annotate_trips"):
+    if model_settings.annotate_trips:
         annotate.annotate_trips(state, model_settings, trace_label, locals_dict)
 
     if state.settings.trace_hh_id:

activitysim/abm/models/trip_scheduling.py

@@ -5,7 +5,7 @@
 import logging
 import warnings
 from builtins import range
-from typing import List, Literal
+from typing import Any, List, Literal
 
 import numpy as np
 import pandas as pd
@@ -456,6 +456,8 @@ class TripSchedulingSettings(PydanticReadable):
 
     logic_version: int | None = None
 
+    CONSTANTS: dict[str, Any] = {}
+
 
 @workflow.step(copy_tables=False)
 def trip_scheduling(

activitysim/core/simulate.py

@@ -397,9 +397,17 @@ def get_segment_coefficients(
         omnibus_coefficients = pd.read_csv(
             legacy_coeffs_file_path, comment="#", index_col="coefficient_name"
         )
+        try:
+            omnibus_coefficients_segment_name = omnibus_coefficients[segment_name]
+        except KeyError as err:
+            logger.error(f"No key {segment_name} found!")
+            possible_keys = "\n- ".join(omnibus_coefficients.keys())
+            logger.error(f"possible keys include: \n- {possible_keys}")
+            raise
         coefficients_dict = assign.evaluate_constants(
-            omnibus_coefficients[segment_name], constants=constants
+            omnibus_coefficients_segment_name, constants=constants
         )
+
     else:
         coefficients_df = filesystem.read_model_coefficients(model_settings)
         template_df = read_model_coefficient_template(filesystem, model_settings)