Coverage for src\cognitivefactory\interactive_clustering_gui\models\settings.py: 100.00%
204 statements
« prev ^ index » next coverage.py v7.4.3, created at 2024-03-22 23:23 +0100
1# -*- coding: utf-8 -*-
3"""
4* Name: cognitivefactory.interactive_clustering_gui.models.settings
5* Description: Definition of algorithm settings models required for application runs.
6* Author: Erwan Schild
7* Created: 16/12/2021
8* Licence: CeCILL-C License v1.0 (https://cecill.info/licences.fr.html)
9"""
11# ==============================================================================
12# IMPORT PYTHON DEPENDENCIES
13# ==============================================================================
15import enum
16from typing import Any, Dict, Optional, Union
18from pydantic import BaseModel, root_validator, validator
20# ==============================================================================
21# ENUMERATION OF IC GUI MODELIZATIONS
22# ==============================================================================
25class ICGUISettings(str, enum.Enum): # noqa: WPS600 (subclassing str)
26 """The enumeration of available Settings for Interactive Clustering GUI."""
28 PREPROCESSING: str = "preprocessing"
29 VECTORIZATION: str = "vectorization"
30 SAMPLING: str = "sampling"
31 CLUSTERING: str = "clustering"
33 @classmethod
34 def contains(cls, value: Any) -> bool:
35 """Test if value is in this enumeration.
37 Args:
38 value (Any): A value.
40 Returns:
41 bool: `True` if the value is in the enumeration.
42 """
43 return value in cls._value2member_map_
46# ==============================================================================
47# BASE MODEL FOR PREPROCESSING SETTINGS
48# ==============================================================================
51class PreprocessingSpacyLanguageModel(str, enum.Enum): # noqa: WPS600 (subclassing str)
52 """The enumeration of available spacy language model name."""
54 FR_CORE_NEWS_MD: str = "fr_core_news_md"
57class PreprocessingSettingsModel(BaseModel):
58 """The body model for preprocessing settings."""
60 # Parameters.
61 apply_stopwords_deletion: bool
62 apply_parsing_filter: bool
63 apply_lemmatization: bool
64 spacy_language_model: PreprocessingSpacyLanguageModel
66 # Export method.
67 def to_dict(self) -> Dict[str, Any]:
68 """Export the model as a dictionary
70 Returns:
71 Dict[str, Any]: A dictionary that contains paramaters and their values.
72 """
73 return {
74 "apply_stopwords_deletion": self.apply_stopwords_deletion,
75 "apply_parsing_filter": self.apply_parsing_filter,
76 "apply_lemmatization": self.apply_lemmatization,
77 "spacy_language_model": self.spacy_language_model.value,
78 }
80 # Config for schema.
81 class Config: # noqa: WPS431 (nested class)
82 """Configuration for body model of preprocessing settings."""
84 schema_extra = {
85 "example": {
86 "apply_stopwords_deletion": False,
87 "apply_parsing_filter": False,
88 "apply_lemmatization": False,
89 "spacy_language_model": PreprocessingSpacyLanguageModel.FR_CORE_NEWS_MD,
90 }
91 }
94def default_PreprocessingSettingsModel() -> PreprocessingSettingsModel:
95 """Create a PreprocessingSettingsModel instance with default values.
97 Returns:
98 PreprocessingSettingsModel: A PreprocessingSettingsModel instance with default values.
99 """
100 return PreprocessingSettingsModel(
101 apply_stopwords_deletion=False,
102 apply_parsing_filter=False,
103 apply_lemmatization=False,
104 spacy_language_model=PreprocessingSpacyLanguageModel.FR_CORE_NEWS_MD,
105 )
108# ==============================================================================
109# BASE MODEL FOR VECTORIZATION SETTINGS
110# ==============================================================================
113class VectorizerType(str, enum.Enum): # noqa: WPS600 (subclassing str)
114 """The enumeration of available vectorizer type."""
116 TFIDF: str = "tfidf"
117 SPACY: str = "spacy"
120class VectorizationSpacyLanguageModel(str, enum.Enum): # noqa: WPS600 (subclassing str)
121 """The enumeration of available spacy language model name."""
123 FR_CORE_NEWS_MD: str = "fr_core_news_md"
126class VectorizationSettingsModel(BaseModel):
127 """The body model for vectorization settings."""
129 # Parameters.
130 vectorizer_type: VectorizerType
131 spacy_language_model: Optional[VectorizationSpacyLanguageModel]
132 random_seed: int
134 @validator("random_seed")
135 @classmethod
136 def validate_random_seed(cls, value: int) -> int:
137 """The validation of random_seed settings.
139 Args:
140 value (int): The value of random_seed setting.
142 Raises:
143 ValueError: if `random_seed` is incorrectly set.
145 Returns:
146 int: The value of random_seed setting.
147 """
148 if value < 0:
149 raise ValueError("`random_seed` must be greater than or equal to 0.")
150 return value
152 @root_validator
153 @classmethod
154 def validate_vectorization_settings(cls, values: Dict[str, Any]) -> Dict[str, Any]:
155 """The validation of vectorization settings.
157 Args:
158 values (Dict[str, Any]): The values of vectorization settings.
160 Raises:
161 ValueError: if `vectorizer_type` and `spacy_language_model` are incompatible.
163 Returns:
164 Dict[str, Any]: The validated values of vectorization settings.
165 """
167 # Case of no vectorizer.
168 if "vectorizer_type" not in values.keys():
169 raise ValueError("The parameter `vectorizer_type` is required.")
171 # Case of tfidf vectorizer.
172 if values["vectorizer_type"] == VectorizerType.TFIDF:
173 if ("spacy_language_model" in values.keys()) and (values["spacy_language_model"] is not None):
174 raise ValueError("No spacy language model is required when vectorizer is `tfidf`.")
175 values["spacy_language_model"] = None
177 # Case of spacy vectorizer.
178 if values["vectorizer_type"] == VectorizerType.SPACY:
179 if ("spacy_language_model" not in values.keys()) or (values["spacy_language_model"] is None):
180 raise ValueError("A spacy language model is required when vectorizer is `spacy`.")
182 # Return validated values of vectorization settings.
183 return values
185 # Export method.
186 def to_dict(self) -> Dict[str, Any]:
187 """Export the model as a dictionary
189 Returns:
190 Dict[str, Any]: A dictionary that contains paramaters and their values.
191 """
192 return {
193 "vectorizer_type": self.vectorizer_type.value,
194 "spacy_language_model": (
195 self.spacy_language_model.value if (self.spacy_language_model is not None) else None
196 ),
197 "random_seed": self.random_seed,
198 }
200 # Config for schema.
201 class Config: # noqa: WPS431 (nested class)
202 """Configuration for body model of vectorization settings."""
204 schema_extra = {
205 "example": {
206 "vectorizer_type": VectorizerType.TFIDF + "|" + VectorizerType.SPACY,
207 "random_seed": 42,
208 "!!!SPECIFIC: 'vectorizer_type'=='spacy'": {
209 "spacy_language_model": VectorizationSpacyLanguageModel.FR_CORE_NEWS_MD,
210 },
211 }
212 }
215def default_VectorizationSettingsModel() -> VectorizationSettingsModel:
216 """Create a VectorizationSettingsModel instance with default values.
218 Returns:
219 VectorizationSettingsModel: A VectorizationSettingsModel instance with default values.
220 """
221 return VectorizationSettingsModel(
222 vectorizer_type=VectorizerType.TFIDF,
223 spacy_language_model=None,
224 random_seed=42,
225 )
228# ==============================================================================
229# BASE MODEL FOR SAMPLING SETTINGS
230# ==============================================================================
233class SamplingAlgorithm(str, enum.Enum): # noqa: WPS600 (subclassing str)
234 """The enumeration of available sampling algorithms."""
236 RANDOM: str = "random"
237 RANDOM_IN_SAME_CLUSTER: str = "random_in_same_cluster"
238 FARTHEST_IN_SAME_CLUSTER: str = "farthest_in_same_cluster"
239 CLOSEST_IN_DIFFERENT_CLUSTERS: str = "closest_in_different_clusters"
240 CUSTOM: str = "custom"
243class ClusterRestriction(str, enum.Enum): # noqa: WPS600 (subclassing str)
244 """The enumeration of available cluster restrictions for custom sampling algorithm."""
246 SAME_CLUSTER: str = "same_cluster"
247 DIFFERENT_CLUSTERS: str = "different_clusters"
250class DistanceRestriction(str, enum.Enum): # noqa: WPS600 (subclassing str)
251 """The enumeration of available distance restrictions for custom sampling algorithm."""
253 CLOSEST_NEIGHBORS: str = "closest_neighbors"
254 FARTHEST_NEIGHBORS: str = "farthest_neighbors"
257class CustomSamplingInitSettingsModel(BaseModel):
258 """The body submodel for custom sampling initialization settings."""
260 # Parameters.
261 clusters_restriction: ClusterRestriction
262 distance_restriction: DistanceRestriction
263 without_inferred_constraints: bool
265 # Export method.
266 def to_dict(self) -> Dict[str, Any]:
267 """Export the model as a dictionary
269 Returns:
270 Dict[str, Any]: A dictionary that contains paramaters and their values.
271 """
272 return {
273 "clusters_restriction": self.clusters_restriction.value,
274 "distance_restriction": self.distance_restriction.value,
275 "without_inferred_constraints": self.without_inferred_constraints,
276 }
279class SamplingSettingsModel(BaseModel):
280 """Abstract body model for sampling settings."""
282 # Parameters.
283 algorithm: SamplingAlgorithm
284 random_seed: int
285 nb_to_select: int
286 init_kargs: Optional[CustomSamplingInitSettingsModel]
288 @validator("random_seed")
289 @classmethod
290 def validate_random_seed(cls, value: int) -> int:
291 """The validation of random_seed settings.
293 Args:
294 value (int): The value of random_seed setting.
296 Raises:
297 ValueError: if `random_seed` is incorrectly set.
299 Returns:
300 int: The value of random_seed setting.
301 """
302 if value < 0:
303 raise ValueError("`random_seed` must be greater than or equal to 0.")
304 return value
306 @validator("nb_to_select")
307 @classmethod
308 def validate_nb_to_select(cls, value: int) -> int:
309 """The validation of nb_to_select settings.
311 Args:
312 value (int): The value of nb_to_select setting.
314 Raises:
315 ValueError: if `nb_to_select` is incorrectly set.
317 Returns:
318 int: The value of nb_to_select setting.
319 """
320 if value < 1:
321 raise ValueError("`nb_to_select` must be greater than or equal to 1.")
322 return value
324 @root_validator
325 @classmethod
326 def validate_sampling_settings(cls, values: Dict[str, Any]) -> Dict[str, Any]:
327 """The validation of sampling settings.
329 Args:
330 values (Dict[str, Any]): The values of sampling settings.
332 Raises:
333 ValueError: if `algorithm` and `init_kargs` are incompatible.
335 Returns:
336 Dict[str, Any]: The validated values of sampling settings.
337 """
339 # Case of no sampling algorithm.
340 if "algorithm" not in values.keys():
341 raise ValueError("The parameter `algorithm` is required.")
343 # Case of custom sampling algorithm.
344 if values["algorithm"] == SamplingAlgorithm.CUSTOM:
345 if ("init_kargs" not in values.keys()) or (values["init_kargs"] is None):
346 raise ValueError(
347 "A dictionary of initialization (`init_kargs`) is required when algorithm is `custom`."
348 )
350 # Case of predefinite sampling algorithms.
351 else:
352 if ("init_kargs" in values.keys()) and (values["init_kargs"] is not None):
353 raise ValueError(
354 "No dictionary of initialization (`init_kargs`) is required when algorithm is different from `custom`."
355 )
356 values["init_kargs"] = None
358 # Return validated values of sampling settings.
359 return values
361 # Export method.
362 def to_dict(self) -> Dict[str, Any]:
363 """Export the model as a dictionary
365 Returns:
366 Dict[str, Any]: A dictionary that contains paramaters and their values.
367 """
368 return {
369 "algorithm": self.algorithm.value,
370 "random_seed": self.random_seed,
371 "nb_to_select": self.nb_to_select,
372 "init_kargs": self.init_kargs.to_dict() if (self.init_kargs is not None) else None,
373 }
375 # Config for schema.
376 class Config: # noqa: WPS431 (nested class)
377 """Configuration for body model of sampling settings."""
379 schema_extra = {
380 "example": {
381 "algorithm": (
382 SamplingAlgorithm.RANDOM
383 + "|"
384 + SamplingAlgorithm.RANDOM_IN_SAME_CLUSTER
385 + "|"
386 + SamplingAlgorithm.CLOSEST_IN_DIFFERENT_CLUSTERS
387 + "|"
388 + SamplingAlgorithm.FARTHEST_IN_SAME_CLUSTER
389 + "|"
390 + SamplingAlgorithm.CUSTOM
391 ),
392 "random_seed": 42,
393 "nb_to_select": 25,
394 "!!!SPECIFIC: 'algorithm'=='custom'": {
395 "init_kargs": {
396 "clusters_restriction": (
397 ClusterRestriction.SAME_CLUSTER + "|" + ClusterRestriction.DIFFERENT_CLUSTERS
398 ),
399 "distance_restriction": (
400 DistanceRestriction.CLOSEST_NEIGHBORS + "|" + DistanceRestriction.FARTHEST_NEIGHBORS
401 ),
402 "without_inferred_constraints": True,
403 },
404 },
405 }
406 }
409def default_SamplingSettingsModel() -> SamplingSettingsModel:
410 """Create a SamplingSettingsModel instance with default values.
412 Returns:
413 SamplingSettingsModel: A SamplingSettingsModel instance with default values.
414 """
415 return SamplingSettingsModel(
416 algorithm=SamplingAlgorithm.CLOSEST_IN_DIFFERENT_CLUSTERS,
417 random_seed=42,
418 nb_to_select=25,
419 init_kargs=None,
420 )
423# ==============================================================================
424# BASE MODEL FOR CLUSTERING SETTINGS
425# ==============================================================================
428class ClusteringAlgorithmEnum(str, enum.Enum): # noqa: WPS600 (subclassing str)
429 """The enumeration of available clustering algorithms."""
431 KMEANS: str = "kmeans"
432 HIERARCHICAL: str = "hierarchical"
433 SPECTRAL: str = "spectral"
436class KmeansModelEnum(str, enum.Enum): # noqa: WPS600 (subclassing str)
437 """The enumeration of available kmeans models."""
439 COP: str = "COP"
442class KmeansInitSettingsModel(BaseModel):
443 """The body submodel for kmeans instantiation settings."""
445 # Parameters.
446 model: KmeansModelEnum
447 max_iteration: int
448 tolerance: float
450 @validator("max_iteration")
451 @classmethod
452 def validate_max_iteration(cls, value: int) -> int:
453 """The validation of max_iteration settings.
455 Args:
456 value (int): The value of max_iteration setting.
458 Raises:
459 ValueError: if `max_iteration` is incorrectly set.
461 Returns:
462 int: The value of max_iteration setting.
463 """
464 if value < 1:
465 raise ValueError("`max_iteration` must be greater than or equal to 1.")
466 return value
468 @validator("tolerance")
469 @classmethod
470 def validate_tolerance(cls, value: float) -> float:
471 """The validation of tolerance settings.
473 Args:
474 value (float): The value of tolerance setting.
476 Raises:
477 ValueError: if `tolerance` is incorrectly set.
479 Returns:
480 float: The value of tolerance setting.
481 """
482 if value < 0:
483 raise ValueError("The `tolerance` must be greater than 0.0.")
484 return value
486 # Export method.
487 def to_dict(self) -> Dict[str, Any]:
488 """Export the model as a dictionary
490 Returns:
491 Dict[str, Any]: A dictionary that contains paramaters and their values.
492 """
493 return {
494 "model": self.model.value,
495 "max_iteration": self.max_iteration,
496 "tolerance": self.tolerance,
497 }
500def default_KmeansInitSettingsModel() -> KmeansInitSettingsModel:
501 """Create a KmeansInitSettingsModel instance with default values.
503 Returns:
504 KmeansInitSettingsModel: A KmeansInitSettingsModel instance with default values.
505 """
506 return KmeansInitSettingsModel(
507 model=KmeansModelEnum.COP,
508 max_iteration=150,
509 tolerance=0.0001,
510 )
513class HierarchicalLinkageEnum(str, enum.Enum): # noqa: WPS600 (subclassing str)
514 """The enumeration of available hierarchical linkages."""
516 AVERAGE: str = "average"
517 COMPLETE: str = "complete"
518 SINGLE: str = "single"
519 WARD: str = "ward"
522class HierarchicalInitSettingsModel(BaseModel):
523 """The body submodel for hierarchical instantiation settings."""
525 # Parameters.
526 linkage: HierarchicalLinkageEnum
528 # Export method.
529 def to_dict(self) -> Dict[str, Any]:
530 """Export the model as a dictionary
532 Returns:
533 Dict[str, Any]: A dictionary that contains paramaters and their values.
534 """
535 return {
536 "linkage": self.linkage.value,
537 }
540# NEVER USE: KMeans is used as default clustering algorithm.
541#### def default_HierarchicalInitSettingsModel() -> HierarchicalInitSettingsModel:
542#### """Create a HierarchicalInitSettingsModel instance with default values.
543####
544#### Returns:
545#### HierarchicalInitSettingsModel: A HierarchicalInitSettingsModel instance with default values.
546#### """
547#### return HierarchicalInitSettingsModel(
548#### linkage=HierarchicalLinkageEnum.WARD,
549#### )
552class SpectralModelEnum(str, enum.Enum): # noqa: WPS600 (subclassing str)
553 """The enumeration of available spectral models."""
555 SPEC: str = "SPEC"
558class SpectralInitSettingsModel(BaseModel):
559 """The body submodel for spectral instantiation settings."""
561 # Parameters.
562 model: SpectralModelEnum = SpectralModelEnum.SPEC
563 nb_components: Optional[int] = None
565 @validator("nb_components")
566 @classmethod
567 def validate_nb_components(cls, value: Optional[int]) -> Optional[int]:
568 """The validation of nb_components settings.
570 Args:
571 value (Optional[int]): The value of nb_components setting.
573 Raises:
574 ValueError: if `nb_components` is incorrectly set.
576 Returns:
577 Optional[int]: The value of nb_components setting.
578 """
579 if (value is not None) and (value < 2):
580 raise ValueError("`nb_components` must be `None` or greater than or equal to 2.")
581 return value
583 # Export method.
584 def to_dict(self) -> Dict[str, Any]:
585 """Export the model as a dictionary
587 Returns:
588 Dict[str, Any]: A dictionary that contains paramaters and their values.
589 """
590 return {
591 "model": self.model.value,
592 "nb_components": self.nb_components,
593 }
596# NEVER USE: KMeans is used as default clustering algorithm.
597#### def default_SpectralInitSettingsModel() -> SpectralInitSettingsModel:
598#### """Create a SpectralInitSettingsModel instance with default values.
599####
600#### Returns:
601#### SpectralInitSettingsModel: A SpectralInitSettingsModel instance with default values.
602#### """
603#### return SpectralInitSettingsModel(
604#### model=SpectralModelEnum.SPEC,
605#### nb_components=None,
606#### )
609class ClusteringSettingsModel(BaseModel):
610 """The body model for clustering settings."""
612 # Parameters.
613 algorithm: ClusteringAlgorithmEnum
614 random_seed: int
615 nb_clusters: int
616 init_kargs: Union[None, KmeansInitSettingsModel, HierarchicalInitSettingsModel, SpectralInitSettingsModel]
618 @validator("random_seed")
619 @classmethod
620 def validate_random_seed(cls, value: int) -> int:
621 """The validation of random_seed settings.
623 Args:
624 value (int): The value of random_seed setting.
626 Raises:
627 ValueError: if `random_seed` is incorrectly set.
629 Returns:
630 int: The value of random_seed setting.
631 """
632 if value < 0:
633 raise ValueError("`random_seed` must be greater than or equal to 0.")
634 return value
636 @validator("nb_clusters")
637 @classmethod
638 def validate_nb_clusters(cls, value: int) -> int:
639 """The validation of nb_clusters settings.
641 Args:
642 value (int): The value of nb_clusters setting.
644 Raises:
645 ValueError: if `nb_clusters` is incorrectly set.
647 Returns:
648 int: The value of nb_clusters setting.
649 """
650 if value < 2:
651 raise ValueError("`nb_clusters` must be greater than or equal to 2.")
652 return value
654 @root_validator
655 @classmethod
656 def validate_clustering_settings(cls, values: Dict[str, Any]) -> Dict[str, Any]:
657 """The validation of clustering settings.
659 Args:
660 values (Dict[str, Any]): The values of clustering settings.
662 Raises:
663 ValueError: if `algorithm` and `init_kargs` are incompatible.
665 Returns:
666 Dict[str, Any]: The validated values of clustering settings.
667 """
669 # Case of no clustering algorithm.
670 if "algorithm" not in values.keys():
671 raise ValueError("The parameter `algorithm` is required.")
673 # Case of kmeans clustering algorithm.
674 if values["algorithm"] == ClusteringAlgorithmEnum.KMEANS:
675 # Case of no init parameters.
676 if ("init_kargs" not in values.keys()) or (values["init_kargs"] is None):
677 raise ValueError(
678 "A dictionary of initialization (`init_kargs`) is required when algorithm is `kmeans`."
679 )
680 # Case of wrong type init parameters.
681 if not isinstance(values["init_kargs"], KmeansInitSettingsModel):
682 raise ValueError(
683 "The dictionary of initialization (`init_kargs`) is incompatible with algorithm `kmeans`."
684 )
686 # Case of hierarchical clustering algorithm.
687 if values["algorithm"] == ClusteringAlgorithmEnum.HIERARCHICAL:
688 # Case of no init parameters.
689 if ("init_kargs" not in values.keys()) or (values["init_kargs"] is None):
690 raise ValueError(
691 "A dictionary of initialization (`init_kargs`) is required when algorithm is `hierarchical`."
692 )
693 # Case of wrong type init parameters.
694 if not isinstance(values["init_kargs"], HierarchicalInitSettingsModel):
695 raise ValueError(
696 "The dictionary of initialization (`init_kargs`) is incompatible with algorithm `hierarchical`."
697 )
699 # Case of spectral clustering algorithm.
700 if values["algorithm"] == ClusteringAlgorithmEnum.SPECTRAL:
701 # Case of no init parameters.
702 if ("init_kargs" not in values.keys()) or (values["init_kargs"] is None):
703 raise ValueError(
704 "A dictionary of initialization (`init_kargs`) is required when algorithm is `spectral`."
705 )
706 # Case of wrong type init parameters.
707 if not isinstance(values["init_kargs"], SpectralInitSettingsModel):
708 raise ValueError(
709 "The dictionary of initialization (`init_kargs`) is incompatible with algorithm `spectral`."
710 )
712 # Return validated values of sampling settings.
713 return values
715 # Export method.
716 def to_dict(self) -> Dict[str, Any]:
717 """Export the model as a dictionary
719 Returns:
720 Dict[str, Any]: A dictionary that contains paramaters and their values.
721 """
722 return {
723 "algorithm": self.algorithm.value,
724 "random_seed": self.random_seed,
725 "nb_clusters": self.nb_clusters,
726 "init_kargs": self.init_kargs.to_dict() if (self.init_kargs is not None) else {},
727 }
729 # Config for schema.
730 class Config: # noqa: WPS431 (nested class)
731 """Configuration for body model of clustering settings."""
733 schema_extra = {
734 "example": {
735 "algorithm": (
736 ClusteringAlgorithmEnum.KMEANS
737 + "|"
738 + ClusteringAlgorithmEnum.HIERARCHICAL
739 + "|"
740 + ClusteringAlgorithmEnum.SPECTRAL
741 ),
742 "random_seed": 42,
743 "nb_clusters": 2,
744 "init_kargs": {
745 "!!!SPECIFIC: 'algorithm'=='kmeans'": {
746 "model": KmeansModelEnum.COP,
747 "max_iteration": 150,
748 "tolerance": 0.0001,
749 },
750 "!!!SPECIFIC: 'algorithm'=='hierarchical'": {
751 "linkage": (
752 HierarchicalLinkageEnum.WARD
753 + "|"
754 + HierarchicalLinkageEnum.AVERAGE
755 + "|"
756 + HierarchicalLinkageEnum.COMPLETE
757 + "|"
758 + HierarchicalLinkageEnum.SINGLE
759 ),
760 },
761 "!!!SPECIFIC: 'algorithm'=='spectral'": {
762 "model": SpectralModelEnum.SPEC,
763 "nb_components": None,
764 },
765 },
766 }
767 }
770def default_ClusteringSettingsModel() -> ClusteringSettingsModel:
771 """Create a ClusteringSettingsModel instance with default values.
773 Returns:
774 ClusteringSettingsModel: A ClusteringSettingsModel instance with default values.
775 """
776 return ClusteringSettingsModel(
777 algorithm=ClusteringAlgorithmEnum.KMEANS,
778 random_seed=42,
779 nb_clusters=2,
780 init_kargs=default_KmeansInitSettingsModel(),
781 )