Common options

These options are not specific to any script. In the case you import patterns from other scripts, Qumin retrieves the options you used when computing the patterns.

class qumin.config.config.QuminConfig(*, action=Actions.patterns, data, patterns=None, pos=None, lexemes=None, cells=None, sample_lexemes=None, sample_cells=None, force_random=False, seed=1, force=False, cpus=1, resegment=False, checkSegments=True, pats=<factory>, lattice=<factory>, macroclasses=<factory>, heatmap=<factory>, pred=<factory>)[source]
Parameters:

  • action (Actions) – Action, one of: patterns, pred, lattice, macroclasses, microclasses, pred_heatmap

  • data (str) – Path to paralex.package.json paradigms, segments

  • cells (List[str] | None) – Cells to use (subset)

  • pos (List[str] | None) – Parts of speech to use (subset)

  • patterns (str | None) – Path to pattern computation metadata. If null, will compute patterns.

  • lexemes (str | None) – Lexemes to use (subset), path to a file with one lexeme id per row

  • sample_lexemes (int | None) – A number of lexemes to sample, for debug purposes.

  • sample_cells (int | None) – A number of cells to sample, for debug purposes. Samples by frequency if possible, otherwise randomly.

  • force_random (bool) – Whether to force random sampling.

  • seed (int) – Random seed for reproducible random effects.

  • force (bool) – Whether to overpass RAM usage security (2GB)

  • cpus (int) – Number of cpus to use for big computations Defaults to 1. 0 sets the number of available cpus to the maximum - 2.

  • resegment (bool) – Whether to ignore spaces in phon forms and re-compute phonemic segmentation

  • checkSegments (bool) – Whether to control if all forms contain licit segments.

  • pats (PatternsConfig) – Configuration for the patterns action.

  • lattice (LatticeConfig) – Configuration for the lattice action.

  • heatmap (HeatmapConfig) – Configuration for the microclasses and pred_heatmap action.

  • pred (PredictabilityConfig) – Configuration for the pred action.

  • entropy – deprecated.

  • macroclasses (MacroclassConfig)

Changed in version 3.2.0: Namespace entropy is replaced by pred.

Values for the action keyword:

class qumin.config.config.Actions(*values)[source]

Available actions. Each action triggers a different script.

Parameters:

  • patterns – computes alternation patterns (to be imported by other scripts)

  • pred – compute predictability measures

  • lattice – compute inflection class lattices.

  • macroclasses – compute macroclasses clusters.

  • microclasses – compute a heatmap of microclass similarity.

  • pred_heatmap – compute a heatmap for predictability measures

Changed in version 3.2.0: Actions H and ent_heatmap are replaced by pred and pred_heatmap. They are deprecated starting from 4.0.0.

The default configuration for these keys looks like this:

action: patterns
data: ???
patterns: null
pos: null
lexemes: null
cells: null
sample_lexemes: null
sample_cells: null
force_random: false
seed: 1
force: false
cpus: 1
resegment: false
checkSegments: true
pats: See relevant CLI documentation
lattice: See relevant CLI documentation
macroclasses: See relevant CLI documentation
heatmap:
  label: null
  cmap: null
  exhaustive_labels: false
  dense: false
  annotate: false
  order: null
  cols: null
  display:
    n_pairs: true
    freq_margins: true
pred: See relevant CLI documentation

See the full full-config