def parse_args()

in sourcecode/scoring/runner.py [0:0]

• 148 lines of code
• 1 McCabe index (conditional complexity)

def parse_args():
  parser = argparse.ArgumentParser("Community Notes Scoring")
  parser.add_argument(
    "--check-flips",
    dest="check_flips",
    help="Validate that note statuses align with prior runs (disable for testing)",
    action="store_true",
  )
  parser.add_argument(
    "--nocheck-flips",
    help="Disable validation that note statuses align with prior runs (use for testing)",
    action="store_false",
    dest="check_flips",
  )
  parser.set_defaults(check_flips=False)
  parser.add_argument(
    "--enforce-types",
    dest="enforce_types",
    help="Raise errors when types in Pandas operations do not meet expectations.",
    action="store_true",
  )
  parser.add_argument(
    "--noenforce-types",
    dest="enforce_types",
    help="Log to stderr when types in Pandas operations do not meet expectations.",
    action="store_false",
  )
  parser.set_defaults(enforce_types=False)
  parser.add_argument(
    "-e", "--enrollment", default=c.enrollmentInputPath, help="note enrollment dataset"
  )
  parser.add_argument(
    "--epoch-millis",
    default=None,
    type=float,
    dest="epoch_millis",
    help="timestamp in milliseconds since epoch to treat as now",
  )
  parser.add_argument(
    "--headers",
    dest="headers",
    help="First row of input files should be a header",
    action="store_true",
  )
  parser.add_argument(
    "--noheaders",
    dest="headers",
    help="First row of input files should be data.  There should be no headers.",
    action="store_false",
  )
  parser.set_defaults(headers=True)
  parser.add_argument("-n", "--notes", default=c.notesInputPath, help="note dataset")
  parser.add_argument(
    "--previous-scored-notes", default=None, help="previous scored notes dataset path"
  )
  parser.add_argument(
    "--previous-aux-note-info", default=None, help="previous aux note info dataset path"
  )
  parser.add_argument(
    "--previous-rating-cutoff-millis", default=None, type=int, help="previous rating cutoff millis"
  )
  parser.add_argument("-o", "--outdir", default=".", help="directory for output files")
  parser.add_argument(
    "--pseudoraters",
    dest="pseudoraters",
    help="Include calculation of pseudorater intervals",
    action="store_true",
  )
  parser.add_argument(
    "--nopseudoraters",
    dest="pseudoraters",
    help="Exclude calculation of pseudorater intervals (faster)",
    action="store_false",
  )
  parser.set_defaults(pseudoraters=True)
  parser.add_argument("-r", "--ratings", default=c.ratingsInputPath, help="rating dataset")
  parser.add_argument(
    "--scorers", default=None, type=scorers_from_csv, help="CSV list of scorers to enable."
  )
  parser.add_argument(
    "--seed", default=None, type=int, help="set to an int to seed matrix factorization"
  )
  parser.add_argument(
    "-s", "--status", default=c.noteStatusHistoryInputPath, help="note status history dataset"
  )
  parser.add_argument(
    "--strict-columns",
    dest="strict_columns",
    help="Explicitly select columns and require that expected columns are present.",
    action="store_true",
  )
  parser.add_argument(
    "--nostrict-columns",
    help="Disable validation of expected columns and allow unexpected columns.",
    action="store_false",
    dest="strict_columns",
  )
  parser.set_defaults(strict_columns=True)
  parser.add_argument(
    "--parallel",
    help="Enable parallel run of algorithm.",
    action="store_true",
    dest="parallel",
  )
  parser.set_defaults(parallel=False)

  parser.add_argument(
    "--no-parquet",
    help="Disable writing parquet files.",
    default=False,
    action="store_true",
    dest="no_parquet",
  )

  parser.add_argument(
    "--cutoff-timestamp-millis",
    default=None,
    type=int,
    dest="cutoffTimestampMillis",
    help="filter notes and ratings created after this time.",
  )
  parser.add_argument(
    "--exclude-ratings-after-a-note-got-first-status-plus-n-hours",
    default=None,
    type=int,
    dest="excludeRatingsAfterANoteGotFirstStatusPlusNHours",
    help="Exclude ratings after a note got first status plus n hours",
  )
  parser.add_argument(
    "--days-in-past-to-apply-post-first-status-filtering",
    default=14,
    type=int,
    dest="daysInPastToApplyPostFirstStatusFiltering",
    help="Days in past to apply post first status filtering",
  )
  parser.add_argument(
    "--prescoring-delay-hours",
    default=None,
    type=int,
    dest="prescoring_delay_hours",
    help="Filter prescoring input to simulate delay in hours",
  )
  parser.add_argument(
    "--sample-ratings",
    default=0.0,
    type=float,
    dest="sample_ratings",
    help="Set to sample ratings at random.",
  )
  return parser.parse_args()