sourcecode/scoring/pflip_model.py [289:308]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  ):
    """Return DataFrame containing notes authored within cutoffMts.

    Args:
      notes: Input DataFrame containing creation times.
      noteStatusHistory: Input DataFrame containing creation times.
      cutoffMts: Allowable creation window measured in milliseconds.
    """
    # Validate that "notes" contains a subset of noteStatusHistory.
    assert notes[c.noteIdKey].nunique() == len(notes), "notes contains duplicate noteIds"
    assert noteStatusHistory[c.noteIdKey].nunique() == len(
      noteStatusHistory
    ), "noteStatusHistory contains duplicate noteIds"
    assert len(notes) == len(
      noteStatusHistory[[c.noteIdKey, c.createdAtMillisKey]].merge(
        notes[[c.noteIdKey, c.createdAtMillisKey]],
        on=[c.noteIdKey, c.createdAtMillisKey],
        how="inner",
      )
    ), "notes is not a subset of noteStatusHistory"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



sourcecode/scoring/pflip_plus_model.py [226:247]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
  ):
    """Determine notes to include in scoring and associated metadata.

    To be included, notes must have an associated tweet and classification.  Returned columns
    include: noteId, tweetId, classification, noteCreationMillis, tweetCreationMillis

    Args:
      notes: Input DataFrame containing creation times.
      noteStatusHistory: Input DataFrame containing creation times.
    """
    # Validate that "notes" contains a subset of noteStatusHistory.
    assert notes[c.noteIdKey].nunique() == len(notes), "notes contains duplicate noteIds"
    assert noteStatusHistory[c.noteIdKey].nunique() == len(
      noteStatusHistory
    ), "noteStatusHistory contains duplicate noteIds"
    assert len(notes) == len(
      noteStatusHistory[[c.noteIdKey, c.createdAtMillisKey]].merge(
        notes[[c.noteIdKey, c.createdAtMillisKey]],
        on=[c.noteIdKey, c.createdAtMillisKey],
        how="inner",
      )
    ), "notes is not a subset of noteStatusHistory"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -