Jl/add tour data to output

Dockerfile

@@ -6,14 +6,14 @@ ENV FULL_CONDA_PATH $CONDA_DIR/envs/$CONDA_ENV
 
 
 ENV ASIM_PATH /activitysim
-ENV ASIM_SUBDIR example
+ENV ASIM_SUBDIR examples
 ENV EXEC_NAME simulation.py
 
 RUN apt-get --allow-releaseinfo-change update \
 	&& apt-get install -y build-essential zip unzip
 RUN conda update conda --yes
 
-RUN git clone https://github.com/ual/activitysim.git
+RUN git clone -b zn/buffered-road-geoms https://github.com/LBNL-UCB-STI/activitysim.git
 
 RUN conda env create --quiet -p $FULL_CONDA_PATH --file activitysim/environment.yml
 RUN cd activitysim && $FULL_CONDA_PATH/bin/python setup.py install

activitysim/abm/models/generate_beam_plans.py

@@ -7,7 +7,7 @@
 import logging
 import warnings
 
-from activitysim.core import pipeline
+from activitysim.core import pipeline, orca
 from activitysim.core import inject
 
 logger = logging.getLogger('activitysim')
@@ -141,23 +141,32 @@ def generate_beam_plans():
     tours = pipeline.get_table('tours')
     persons = pipeline.get_table('persons')
     households = pipeline.get_table('households')
-    land_use = pipeline.get_table('land_use').reset_index()
 
-    # re-create zones shapefile
-    land_use['geometry'] = land_use['geometry'].apply(wkt.loads)
-    zones = gpd.GeoDataFrame(land_use, geometry='geometry', crs='EPSG:4326')
-    zones.geometry = zones.geometry.buffer(0)
+    if orca.is_table('beam_geoms'):
+        beam_geoms = pipeline.get_table('beam_geoms')
+        beam_geoms['geometry'] = gpd.GeoSeries.from_wkt(beam_geoms['geometry'])
+        zones = gpd.GeoDataFrame(beam_geoms, geometry='geometry', crs='EPSG:4326')
+        zones.geometry = zones.geometry.buffer(0)
+    else:
+        land_use = pipeline.get_table('land_use').reset_index()
+
+        # re-create zones shapefile
+        land_use['geometry'] = land_use['geometry'].apply(wkt.loads)
+        zones = gpd.GeoDataFrame(land_use, geometry='geometry', crs='EPSG:4326')
+        zones.geometry = zones.geometry.buffer(0)
 
     # augment trips table with attrs we need to generate plans
     trips = get_trip_coords(trips, zones, persons)
     trips['departure_time'] = generate_departure_times(trips, tours)
     trips['number_of_participants'] = trips['tour_id'].map(
         tours['number_of_participants'])
+    trips['tour_mode'] = trips['tour_id'].map(
+            tours['tour_mode'])
 
     # trim trips table
     cols = [
-        'person_id', 'departure_time', 'purpose', 'origin',
-        'destination', 'number_of_participants', 'trip_mode', 'x', 'y']
+        'person_id', 'tour_id', 'departure_time', 'purpose', 'origin',
+        'destination', 'number_of_participants', 'tour_mode', 'trip_mode', 'x', 'y']
     sorted_trips = trips[cols].sort_values(
         ['person_id', 'departure_time']).reset_index()
 
@@ -208,10 +217,13 @@ def generate_beam_plans():
 
     final_plans['trip_id'] = final_plans['trip_id'].shift()
     final_plans['trip_mode'] = final_plans['trip_mode'].shift()
+    final_plans['tour_id'] = final_plans['tour_id'].shift()
+    final_plans['tour_mode'] = final_plans['tour_mode'].shift()
     final_plans['number_of_participants'] = final_plans[
         'number_of_participants'].shift()
+
     final_plans = final_plans[[
-        'trip_id', 'person_id', 'number_of_participants', 'trip_mode',
+        'tour_id', 'trip_id', 'person_id', 'number_of_participants', 'tour_mode', 'trip_mode',
         'PlanElementIndex', 'ActivityElement', 'ActivityType', 'x', 'y',
         'departure_time']]
 

activitysim/abm/models/initialize.py

@@ -86,6 +86,12 @@ def initialize_landuse():
 
     model_settings = config.read_model_settings('initialize_landuse.yaml', mandatory=True)
 
+    beam_geometries_path = config.setting('beam_geometries')
+    data_file_path = config.data_file_path(beam_geometries_path, mandatory=True)
+
+    beam_geom_dataframe = pd.read_csv(data_file_path)
+    pipeline.rewrap("beam_geoms", beam_geom_dataframe)
+
     annotate_tables(model_settings, trace_label)
 
     # create accessibility (only required if multiprocessing wants to slice accessibility)

austin/configs/configs/tour_mode_choice_annotate_choosers_preprocessor.csv

@@ -31,29 +31,12 @@ local,_DF_IS_TOUR,'tour_type' in df.columns
 ,origin_walk_time,shortWalk*60/walkSpeed
 ,destination_walk_time,shortWalk*60/walkSpeed
 # RIDEHAIL,,
-,origin_density_measure,"(reindex(land_use.TOTPOP, df[orig_col_name]) + reindex(land_use.TOTEMP, df[orig_col_name])) / (reindex(land_use.TOTACRE, df[orig_col_name]) / 640)"
-,dest_density_measure,"(reindex(land_use.TOTPOP, df[dest_col_name]) + reindex(land_use.TOTEMP, df[dest_col_name])) / (reindex(land_use.TOTACRE, df[dest_col_name]) / 640)"
-,origin_density,"pd.cut(origin_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,dest_density,"pd.cut(dest_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,origin_zone_taxi_wait_time_mean,"origin_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,origin_zone_taxi_wait_time_sd,"origin_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
-,dest_zone_taxi_wait_time_mean,"dest_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,dest_zone_taxi_wait_time_sd,"dest_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
-# ,, Note that the mean and standard deviation are not the values for the distribution itself but of the underlying normal distribution it is derived from
-,origTaxiWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_taxi_wait_time_mean, sigma=origin_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destTaxiWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_taxi_wait_time_mean, sigma=dest_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_singleTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,origin_zone_singleTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,dest_zone_singleTNC_wait_time_mean,"dest_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,dest_zone_singleTNC_wait_time_sd,"dest_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,origSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_singleTNC_wait_time_mean, sigma=origin_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_singleTNC_wait_time_mean, sigma=dest_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_sharedTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,origin_zone_sharedTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,dest_zone_sharedTNC_wait_time_mean,"dest_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,dest_zone_sharedTNC_wait_time_sd,"dest_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,origSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_sharedTNC_wait_time_mean, sigma=origin_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_sharedTNC_wait_time_mean, sigma=dest_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
+,origTaxiWaitTime,"odt_skims['RH_SOLO_WAIT']"
+,destTaxiWaitTime,"dot_skims['RH_SOLO_WAIT']"
+,origSingleTNCWaitTime,"odt_skims['RH_SOLO_WAIT']"
+,destSingleTNCWaitTime,"dot_skims['RH_SOLO_WAIT']"
+,origSharedTNCWaitTime,"odt_skims['RH_POOLED_WAIT']"
+,destSharedTNCWaitTime,"dot_skims['RH_POOLED_WAIT']"
 ,totalWaitTaxi,origTaxiWaitTime + destTaxiWaitTime
 ,totalWaitSingleTNC,origSingleTNCWaitTime + destSingleTNCWaitTime
 ,totalWaitSharedTNC,origSharedTNCWaitTime + destSharedTNCWaitTime

austin/configs/configs/trip_mode_choice_annotate_trips_preprocessor.csv

@@ -45,18 +45,9 @@ dest terminal time not counted at home,_dest_terminal_time,"np.where(inbound & l
 ,origin_walk_time,shortWalk*60/walkSpeed
 ,destination_walk_time,shortWalk*60/walkSpeed
 # RIDEHAIL,,
-,origin_density_measure,"(reindex(land_use.TOTPOP, df[orig_col_name]) + reindex(land_use.TOTEMP, df[orig_col_name])) / (reindex(land_use.TOTACRE, df[orig_col_name]) / 640)"
-,origin_density,"pd.cut(origin_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,origin_zone_taxi_wait_time_mean,"origin_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,origin_zone_taxi_wait_time_sd,"origin_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
-# ,, Note that the mean and standard deviation are not the values for the distribution itself but of the underlying normal distribution it is derived from
-,origTaxiWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_taxi_wait_time_mean, sigma=origin_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_singleTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,origin_zone_singleTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,origSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_singleTNC_wait_time_mean, sigma=origin_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_sharedTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,origin_zone_sharedTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,origSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_sharedTNC_wait_time_mean, sigma=origin_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
+,origTaxiWaitTime,"odt_skims['RH_SOLO_WAIT']"
+,origSingleTNCWaitTime,"odt_skims['RH_SOLO_WAIT']"
+,origSharedTNCWaitTime,"odt_skims['RH_POOLED_WAIT']"
 #,,
 ,sov_available,odt_skims['SOV_TIME']>0
 ,hov2_available,odt_skims['HOV2_TIME']>0

bay_area/configs/configs/tour_mode_choice.yaml

@@ -127,6 +127,7 @@ CONSTANTS:
       5: 0
     min_waitTime: 0
     max_waitTime: 50
+    TNC_missed_trip_penalty: 50
 
     ivt_cost_multiplier: 0.6
     ivt_lrt_multiplier: 0.9

bay_area/configs/configs/tour_mode_choice_annotate_choosers_preprocessor.csv

@@ -31,29 +31,13 @@ local,_DF_IS_TOUR,'tour_type' in df.columns
 ,origin_walk_time,shortWalk*60/walkSpeed
 ,destination_walk_time,shortWalk*60/walkSpeed
 # RIDEHAIL,,
-,origin_density_measure,"(reindex(land_use.TOTPOP, df[orig_col_name]) + reindex(land_use.TOTEMP, df[orig_col_name])) / (reindex(land_use.TOTACRE, df[orig_col_name]) / 640)"
-,dest_density_measure,"(reindex(land_use.TOTPOP, df[dest_col_name]) + reindex(land_use.TOTEMP, df[dest_col_name])) / (reindex(land_use.TOTACRE, df[dest_col_name]) / 640)"
-,origin_density,"pd.cut(origin_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,dest_density,"pd.cut(dest_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,origin_zone_taxi_wait_time_mean,"origin_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,origin_zone_taxi_wait_time_sd,"origin_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
-,dest_zone_taxi_wait_time_mean,"dest_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,dest_zone_taxi_wait_time_sd,"dest_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
 # ,, Note that the mean and standard deviation are not the values for the distribution itself, but of the underlying normal distribution it is derived from
-,origTaxiWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_taxi_wait_time_mean, sigma=origin_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destTaxiWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_taxi_wait_time_mean, sigma=dest_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_singleTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,origin_zone_singleTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,dest_zone_singleTNC_wait_time_mean,"dest_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,dest_zone_singleTNC_wait_time_sd,"dest_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,origSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_singleTNC_wait_time_mean, sigma=origin_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_singleTNC_wait_time_mean, sigma=dest_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_sharedTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,origin_zone_sharedTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,dest_zone_sharedTNC_wait_time_mean,"dest_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,dest_zone_sharedTNC_wait_time_sd,"dest_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,origSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_sharedTNC_wait_time_mean, sigma=origin_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,destSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=dest_zone_sharedTNC_wait_time_mean, sigma=dest_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
+,origTaxiWaitTime,"odt_skims['RH_SOLO_WAIT'] * (1.0 - odt_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_SOLO_REJECTIONPROB']"
+,destTaxiWaitTime,"dot_skims['RH_SOLO_WAIT'] * (1.0 - dot_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * dot_skims['RH_SOLO_REJECTIONPROB']"
+,origSingleTNCWaitTime,"odt_skims['RH_SOLO_WAIT'] * (1.0 - odt_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_SOLO_REJECTIONPROB']"
+,destSingleTNCWaitTime,"dot_skims['RH_SOLO_WAIT'] * (1.0 - dot_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * dot_skims['RH_SOLO_REJECTIONPROB']"
+,origSharedTNCWaitTime,"odt_skims['RH_POOLED_WAIT'] * (1.0 - odt_skims['RH_POOLED_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_POOLED_REJECTIONPROB']"
+,destSharedTNCWaitTime,"dot_skims['RH_POOLED_WAIT'] * (1.0 - dot_skims['RH_POOLED_REJECTIONPROB']) + TNC_missed_trip_penalty * dot_skims['RH_POOLED_REJECTIONPROB']"
 ,totalWaitTaxi,origTaxiWaitTime + destTaxiWaitTime
 ,totalWaitSingleTNC,origSingleTNCWaitTime + destSingleTNCWaitTime
 ,totalWaitSharedTNC,origSharedTNCWaitTime + destSharedTNCWaitTime

bay_area/configs/configs/trip_mode_choice.yaml

@@ -157,6 +157,7 @@ CONSTANTS:
     5: 0
   min_waitTime: 0
   max_waitTime: 50
+  TNC_missed_trip_penalty: 50
 
 # so far, we can use the same spec as for non-joint tours
 preprocessor:

bay_area/configs/configs/trip_mode_choice_annotate_trips_preprocessor.csv

@@ -44,19 +44,10 @@ dest terminal time not counted at home,_dest_terminal_time,"np.where(inbound & l
 ,drive_transit_available,"np.where(df.outbound, _walk_transit_destination, _walk_transit_origin) & (df.auto_ownership > 0)"
 ,origin_walk_time,shortWalk*60/walkSpeed
 ,destination_walk_time,shortWalk*60/walkSpeed
-# RIDEHAIL,,
-,origin_density_measure,"(reindex(land_use.TOTPOP, df[orig_col_name]) + reindex(land_use.TOTEMP, df[orig_col_name])) / (reindex(land_use.TOTACRE, df[orig_col_name]) / 640)"
-,origin_density,"pd.cut(origin_density_measure, bins=[-np.inf, 500, 2000, 5000, 15000, np.inf], labels=[5, 4, 3, 2, 1]).astype(int)"
-,origin_zone_taxi_wait_time_mean,"origin_density.map({k: v for k, v in Taxi_waitTime_mean.items()})"
-,origin_zone_taxi_wait_time_sd,"origin_density.map({k: v for k, v in Taxi_waitTime_sd.items()})"
-# ,, Note that the mean and standard deviation are not the values for the distribution itself, but of the underlying normal distribution it is derived from
-,origTaxiWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_taxi_wait_time_mean, sigma=origin_zone_taxi_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_singleTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_single_waitTime_mean.items()})"
-,origin_zone_singleTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_single_waitTime_sd.items()})"
-,origSingleTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_singleTNC_wait_time_mean, sigma=origin_zone_singleTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
-,origin_zone_sharedTNC_wait_time_mean,"origin_density.map({k: v for k, v in TNC_shared_waitTime_mean.items()})"
-,origin_zone_sharedTNC_wait_time_sd,"origin_density.map({k: v for k, v in TNC_shared_waitTime_sd.items()})"
-,origSharedTNCWaitTime,"rng.lognormal_for_df(df, mu=origin_zone_sharedTNC_wait_time_mean, sigma=origin_zone_sharedTNC_wait_time_sd, broadcast=True, scale=True).clip(min_waitTime, max_waitTime)"
+# RIDEHAIL,, Could just define this in trip_mode_choice.csv but leaving this for now so that we can factor in rejected trips if needed
+,origTaxiWaitTime,"odt_skims['RH_SOLO_WAIT'] * (1.0 - odt_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_SOLO_REJECTIONPROB']"
+,origSingleTNCWaitTime,"odt_skims['RH_SOLO_WAIT'] * (1.0 - odt_skims['RH_SOLO_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_SOLO_REJECTIONPROB']"
+,origSharedTNCWaitTime,"odt_skims['RH_POOLED_WAIT'] * (1.0 - odt_skims['RH_POOLED_REJECTIONPROB']) + TNC_missed_trip_penalty * odt_skims['RH_POOLED_REJECTIONPROB']"
 #,,
 ,sov_available,odt_skims['SOV_TIME']>0
 ,hov2_available,odt_skims['HOV2_TIME']>0

bay_area/configs/settings.yaml

@@ -30,6 +30,9 @@ input_table_list:
 # input skims
 skims_file: skims.omx
 
+# input valid geometries
+beam_geometries: clipped_tazs.csv
+
 # raise error if any sub-process fails without waiting for others to complete
 fail_fast: True