Project Meeting 2024.10.08

Agenda

• General Admin - Phase 10A tasks
• Admin Transition
• Technical Tasks - Estimation Enhancements

General Admin

• Phase 10A Tasks
  • Consensus is to go after some of the tasks on list of issues
  • Use Notes section to comment on list of issues
    • Agencies should use Notes section to highlight super critical issues to address

Admin Transition

• Admin Level of Effort
  • MWCOG director is asking for level of effort document that he can review and use for further discussions with AMPO
    • AMPO has reviewed document with Joe and Alex
    • Mark made updates to table with meeting attendance, Joe and Alex will review
    • Mark will share document as-is
  • Mark will ask about timeline for further discussions with MPO directors and AMPO

Technical

• Estimation Run Time Performance
  • Estimation mode runs in single-process only
    • Fix: Coalesced processes together ** Works if in estimation mode and multiprocessing is on
  • EDB writing is slow
    • Fix: Allow for EDBs to be written in csv, parquet, pickle file types
      • New options:
        • EDB_FILETYPE (options: csv, parquet, pkl)
        • File type not available on all types of files
  • Destination Choice Location EDBs
    • Fix: Allow for sampling
      • SAMPLE_SIZE
      • EDB_ALTS_FILE_FORMAT (options: compact, verbose)
    • There does not need to be consistency between sample size in estimation and application
  • CI Testing
    • Runs on small MTC test example
    • Added infer.py into test system (calls internal ActivitySim functions for things like tour and trip IDs)
    • Test all file types to ensure consistency
• Larch Updates
  • Enhance Larch useability and add data and output checking features
    • New features check whether data input is in format that is useable for Larch
      • Chosen alternative is formally not available (availability explicitly set to False)
      • In a sized choice model, chosen alternative has zero size
      • No choice made when case weight is non-zero
      • NaNs appear in data
      • Chooser attributes have insufficient variance
      • Model is over-specified, with a nearly singular hessian (e.g. complete set of alternative specific constants)
      • Upcoming: chosen alternative is functionally not available (e.g. alternative utility <-50 at null parameters)
• Next Steps
  • Finish implementation of location choice sampling
  • Test Larch enhancements
  • Benchmark improvements against pre-improvement platform with full-scale datasets
• Big Picture
  • Task 1: Completed (or almost completed) 3 out of 4 main tasks
  • Task 2: Working toward completion of 1 of 3 tasks
• Aiming to complete all tasks by mid-December