17-classification

17-classification - Classification I CS273 - Data and...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
Classification I S273 ata and Knowledge Bases CS273 - Data and Knowledge Bases Xifeng Yan Computer Science niversity of California at Santa Barbara University of California at Santa Barbara
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Department of Computer Science Classification age income student credit_rating buy_computer <=30 high no fair no <=30 high no excellent no 31…40 high no fair yes >40 medium no fair yes >40 low yes fai ry e s >40 low yes excellent no 31…40 low yes excellent yes 3 0 edium o ir o <=30 medium no fair no <=30 low yes fair yes >40 medium yes fair yes =30 edium es xcellent es <=30 medium yes excellent yes 31…40 medium no excellent yes 31…40 high yes fair yes 40 edium o xcellent o Data and Knowledge Bases | University of California at Santa Barbara 2 >40 medium no excellent no
Background image of page 2
Department of Computer Science Process (1): Model Construction Classification Algorithms Training Data NAME RANK YEARS TENURED ike ssistant Prof o Classifier odel) Mike Assistant Prof 3 no Mary 7 yes Bill Professor 2 (Model) F(x 1 , x 2 ,…x n ) Jim Associate Prof 7 Dave 6 Anne 3 IF rank = ‘professor’ OR years > 6 HEN tenured = ‘yes’ Data and Knowledge Bases | University of California at Santa Barbara 3 THEN tenured = yes
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Department of Computer Science Process (2): Using the Model in Prediction lassifier Classifier esting Testing Data Unseen Data NAME RANK YEARS TENURED om ssistant Prof o (Jeff, Professor, 4) Tenured? Tom Assistant Prof 2 no Merlisa Associate Prof 7 George Professor 5 yes oseph es Data and Knowledge Bases | University of California at Santa Barbara 4 Joseph Assistant Prof 7
Background image of page 4
Department of Computer Science Classification Methods Manual Study Typically rule-based Does not scale up (labor-intensive, rule inconsistency) Automatic Learning Decision-tree Naïve Bayes classifier K-nearest neighbor (KNN) Neural Networks (learn non-linear classifier) Support Vector Machines (SVM) nsemble Approach: bagging boosting Ensemble Approach: bagging, boosting Data and Knowledge Bases | University of California at Santa Barbara 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Department of Computer Science Decision Tree Induction: Training Dataset age income student credit_rating buys_computer <=30 high no fair =30 igh o xcellent o excellent 31…40 high yes >40 medium 40 w es ir low 31…40 low edium o o <3 0 30 31…40 medium Data and Knowledge Bases | University of California at Santa Barbara 6
Background image of page 6
Department of Computer Science Output: A Decision Tree for “ buys_computer” age? overcast <=30 >40 31. .40 student? credit rating? yes fair excellent yes no no yes yes Data and Knowledge Bases | University of California at Santa Barbara 7
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Department of Computer Science How to Build Decision Trees Basic algorithm (a greedy algorithm) Tree is constructed in a top-down recursive divide-and-conquer anner manner At start, all the training examples are at the root ttributes are categorical (if continuous- alued, they are discretized Attributes are categorical (if continuous valued, they are discretized in advance) Examples are partitioned recursively based on selected attributes
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 41

17-classification - Classification I CS273 - Data and...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online