1 / 107

Johanna GOLD

Rough Sets Theory Logical Analysis of Data. Monday , November 26, 2007. Johanna GOLD. Introduction. Comparison of two theories for rules induction. Different methodologies Same results?. Generalities. Set of objects described by attributes. Each object belongs to a class.

kaori
Télécharger la présentation

Johanna GOLD

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Rough Sets Theory Logical Analysis of Data. Monday, November 26, 2007 Johanna GOLD

  2. Introduction • Comparison of two theories for rules induction. • Different methodologies • Same results?

  3. Generalities • Set of objects described by attributes. • Each object belongs to a class. • We want decision rules.

  4. Approaches • There are two approaches: • Rough Sets Theory (RST) • Logical Analysis of Data (LAD) • Goal : compare them

  5. Contents Rough Sets Theory Logical Analysis Of data Comparison Inconsistencies

  6. Inconsistencies • Two examples having the exact same values in all attributes, but belonging to two different classes. • Example: two sick people have the same symptomas but different disease.

  7. Covered by RST • RST doesn’t correct or aggregate inconsistencies. • For each class : determination of lower and upper approximations.

  8. Approximations • Lower : objects we are sure they belong to the class. • Upper : objects than can belong to the class.

  9. Impact on rules • Lower approximation → certain rules • Upper approximation → possible rules

  10. Pretreatment • Rules induction on numerical data → poor rules → too many rules. • Need of pretreatment.

  11. Discretization • Goal : convert numerical data into discrete data. • Principle : determination of cut points in order to divide domains into successive intervals.

  12. Algorithms • First algorithm: LEM2 • Improved algorithms: • Include the pretreatment • MLEM2, MODLEM, …

  13. LEM2 • Induction of certain rules from the lower approximation. • Induction of possible rules from the upper approximation. • Same procedure

  14. Definitions (1) • For an attribute x and its value v, a block [(x,v)] of attribute-value pair (x,v) is all the cases where the attribute x has the value v. • Ex : [(Age,21)]=[Martha] [(Age,22)]=[David ; Audrey]

  15. Definitions (2) • Let B be a non-empty lower or upper approximation of a concept represented by a decision-value pair (d,w). • Ex : (level,middle)→B=[obj1 ; obj5 ; obj7]

  16. Definitions (3) • Let T be a set of pairs attribute-value (a,v). • Set B depends on set T if and only if:

  17. Definitions (4) • A set T is minimal complex of B if and only if B depends on T and there is no subset T’ of T such as B depends on T’.

  18. Definitions (5) • Let T be a non-empty collection of non-empty set of attribute-value pairs. • T is a set of T. • T is a set of (a,v).

  19. Definitions (6) • T is a local cover of B if and only if: • Each member T of T is a minimal complex of B. • T is minimal

  20. Algorithm principle • LEM2’s output is a local cover for each approximation of the decision table concept. • It then convert them into decision rules.

  21. Algorithm

  22. Heuristics details Among the possible blocks, we choose the one: • With the highest priority • With the highest intersection • With the smallest cardinal

  23. Heuristics details • As long as it is not a minimal complex, pairs are added. • As long as there is not a local cover, minimal complexes are added.

  24. Illustration • Illustration through an example. • We consider that the pretreatment has already been done.

  25. Data set

  26. Cut points • For the attribute Height, we have the values 160, 170 and 180. • The pretreatment gives us two cut points: 165 and 175.

  27. Blocks [(a,v)] • [(Height, 160..165)]={1,3,5} • [(Height, 165..180)]={2,4} • [(Height, 160..175)]={1,2,3,5} • [(Height, 175..180)]={4} • [(Hair, Blond)]={1,2} • [(Hair, Red)]={3} • [(Hair, Black)]={4,5,6}

  28. First concept • G = B = [(Attraction,-)] = {1,4,5,6} • Here there is no inconsistencies. If there were some, it’s at this point that we have to chose between the lower and the upper approximation.

  29. Eligible pairs • Pair (a,v) such as [(a,v)]∩[(Attraction,-)]≠Ø • (Height,160..165) • (Height,165..180) • (Height,160..175) • (Height,175..180) • (Hair,Blond) • (Hair,Black)

  30. Choice of a pair • We chose the most appropriate, which is to say (a,v) for which | [(a,v)] ∩ [(Attraction,-)] | is the highest. • Here : (Hair, Black)

  31. Minimal complex • The pair (Hair, Black) is a minimal complex because:

  32. New concept • B = [(Attraction,-)] – [(Hair,Black)] = {1,4,5,6} - {4,5,6} = {1}

  33. Choice of a pair (1) • Through the pairs (Height,160..165), (Height,160..175) and (Hair, Blond). • Intersections having the same cardinality, we chose the pair having the smallest cardinal: (Hair, Blond)

  34. Choice of a pair (2) • Problem : • (Hair, Blond) is non a minimal complex. • We chose the following pair: (Height,160..165).

  35. Minimal Complex • {(Hair, Blond),(Height,160..165)} is a second minimal complex.

  36. End of the concept • {{(Hair, Black)}, {(Hair, Blond), (Height, 160..165)}} is a local cover of [(Attraction,-)].

  37. Rules • (Hair, Red) → (Attraction,+) • (Hair, Blond) & (Height,165..180 ) → (Attraction,+) • (Hair, Black) → (Attraction,-) • (Hair, Blond) & (Height,160..165 ) → (Attraction,-)

  38. Contents Rough Sets Theory Logical Analysis Of data Comparison Inconsistencies

  39. Principle • Work on binary data. • Extension of boolean approach on non-binary case.

  40. Definitions (1) • Let S be the set of all observations. • Each observation is described by n attributes. • Each observation belongs to a class.

  41. Definitions (2) • The classification can be considered as a partition into two sets • An archive is represented by a boolean function Φ :

  42. Definitions (3) • A literal is a boolean variable or its negation: • A term is a conjunction of literals : • The degree of a term is the number of literals.

  43. Definitions (4) • A term Tcovers a point if T(p)=1. • A characteristic term of a point p is the unique term of degree n covering p. • Ex :

  44. Definitions (5) • A term T is an implicant of a boolean function f if T(p) ≤ f(p) for all • An implicant is called prime if it is minimal (its degree).

  45. Definitions (6) • A positive prime patternis a term covering at least one positive example and no negative example. • A negative prime patternis a term covering at least one negative example and no positive example.

  46. Example

  47. Example • is a positive pattern : • There is no negative example such as • There is one positive example : the 3rd line. • It's a positive prime pattern : • covers one negative example : 4th line. • covers one negative example : 5th line.

  48. Pattern generation • symmetry between positive and negative patterns. • Two approaches : • Top-down • Bottom-up

  49. Top-down • we associate each positive example to its characteristic term→ it’s a pattern. • we take out the literals one by one until having a prime pattern.

  50. Bottom-up • we begin with terms of degree one: • if it does not cover a negative example, it is a pattern • If not, we add literals until having a pattern.

More Related