Coverage for src\cognitivefactory\interactive_clustering\sampling\abstract.py: 100.00%

1# -*- coding: utf-8 -*- 

2 

3""" 

4* Name: cognitivefactory.interactive_clustering.sampling.abstract 

5* Description: The abstract class used to define constraints sampling algorithms. 

6* Author: Erwan SCHILD 

7* Created: 17/03/2021 

8* Licence: CeCILL (https://cecill.info/licences.fr.html) 

9""" 

10 

11# ============================================================================== 

12# IMPORT PYTHON DEPENDENCIES 

13# ============================================================================== 

14 

15from abc import ABC, abstractmethod 

16from typing import Dict, List, Optional, Tuple 

17 

18from scipy.sparse import csr_matrix 

19 

20from cognitivefactory.interactive_clustering.constraints.abstract import AbstractConstraintsManager 

21 

22 

23# ============================================================================== 

24# ABSTRACT CONSTRAINTS SAMPLING 

25# ============================================================================== 

26class AbstractConstraintsSampling(ABC): 

27 """ 

28 Abstract class that is used to define constraints sampling algorithms. 

29 The main inherited method is `sample`. 

30 """ 

31 

32 # ============================================================================== 

33 # ABSTRACT METHOD - SAMPLE 

34 # ============================================================================== 

35 @abstractmethod 

36 def sample( 

37 self, 

38 constraints_manager: AbstractConstraintsManager, 

39 nb_to_select: int, 

40 clustering_result: Optional[Dict[str, int]] = None, 

41 vectors: Optional[Dict[str, csr_matrix]] = None, 

42 **kargs, 

43 ) -> List[Tuple[str, str]]: 

44 """ 

45 (ABSTRACT METHOD) 

46 An abstract method that represents the main method used to sample couple of data IDs for constraints annotation. 

47 

48 Args: 

49 constraints_manager (AbstractConstraintsManager): A constraints manager over data IDs. 

50 nb_to_select (int): The number of couple of data IDs to select. 

51 clustering_result (Optional[Dict[str,int]], optional): A dictionary that represents the predicted cluster for each data ID. The keys of the dictionary represents the data IDs. If `None`, no clustering result are used during the sampling. Defaults to `None`. 

52 vectors (Optional[Dict[str, csr_matrix]], optional): vectors (Dict[str, csr_matrix]): The representation of data vectors. The keys of the dictionary represents the data IDs. This keys have to refer to the list of data IDs managed by the `constraints_manager`. The value of the dictionary represent the vector of each data. If `None`, no vectors are used during the sampling. Defaults to `None` 

53 **kargs (dict): Other parameters that can be used in the sampling. 

54 

55 Raises: 

56 ValueError: if some parameters are incorrectly set or incompatible. 

57 

58 Returns: 

59 List[Tuple[str,str]]: A list of couple of data IDs. 

60 """