PUBLIC: A Decision Tree Classifier that Integrates Building and Pruning . Rajeev Rastogi Kyuseok Shim Bell Laboratories Murray Hill, NJ 07974 24th VLDB Conference, New York, USA, 1998 P76021140 郭育婷 P76021336 林吾軒 P76021043 黃喻豐 P76014339 李聲彥 P76021213 顏孝軒.
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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.
PUBLIC: A Decision Tree Classifier that Integrates Building and Pruning
Rajeev RastogiKyuseok Shim
Bell Laboratories
Murray Hill, NJ 07974
24th VLDB Conference, New York, USA, 1998
P76021140 郭育婷
P76021336 林吾軒
P76021043 黃喻豐
P76014339 李聲彥
P76021213 顏孝軒
Decision Tree
Training Data
Record
Attribute
Class
cost(S) < cost(each leaf of S)
A,B,C,D,E,F
E,F
A
B,C,D
B,C
F
D
E
If cost(B,C) < cost(B)+cost(C)
=> prune!!!
B
C
(PrUningand BuiLdingIntegrated in Classification)
A < vi
A ∈ V = {v1, v2, v3, … vm}
N
Y
Root Attribute lists : Z
Attribute lists : Y
Attribute lists : X
S : n records
S1 : n1 records
S2: n2records
Lelt
Right
Init & breadth-first
Compute entropy
split
leaf
node
prune
C(S)+1
Less then CS(S)+1
/*n1,…,nkare sorted in decreasing order*/
Thanks for your attention！