data mining fp growth
DESCRIPTION
A simple graphical presentation of the implementation of FP Growth Algorithm for mining frequent pattern in a databaseTRANSCRIPT
![Page 1: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/1.jpg)
Presented By:Shihab RahmanDolon Chanpa
Department Of Computer Science And Engineering,
University of Dhaka
FP Growth Algorithm For Mining Frequent Pattern
![Page 2: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/2.jpg)
FP Growth Stands for frequent pattern growth
It is a scalable technique for mining frequent pattern in a database
What is FP Growth?
![Page 3: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/3.jpg)
FP growth improves Apriority to a big extentFrequent Item set Mining is possible without
candidate generationOnly “two scan” to the database is needed
BUT HOW?
FP Growth
![Page 4: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/4.jpg)
Simply a two step procedure– Step 1: Build a compact data structure called
the FP-tree• Built using 2 passes over the data-set.
– Step 2: Extracts frequent item sets directly from the FP-tree
FP Growth
![Page 5: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/5.jpg)
Now Lets Consider the following transaction table
FP Growth
TID List of item IDs
T100 I1,I2,I3
T200 I2,I4
T300 I2,I3
T400 I1,I2,I4
T500 I1,I3
T600 I2,I3
T700 I1,I3
T800 I1,I2,I3,I5
T900 I1,I2,I3
![Page 6: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/6.jpg)
Now we will build a FP tree of that databaseItem sets are considered in order of their
descending value of support count.
FP Growth
![Page 7: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/7.jpg)
null
I2:1
I1:1
I5:1
For Transaction:I2,I1,I5
![Page 8: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/8.jpg)
null
I2:2
I1:1
I5:1
I4:1
For Transaction:I2,I4
![Page 9: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/9.jpg)
null
I2:3
I1:1
I5:1
I3:1
I4:1
For Transaction:I2,I3
![Page 10: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/10.jpg)
null
I2:4
I1:2
I5:1
I3:1
I4:1
I4:1
For Transaction:I2,I1,I4
![Page 11: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/11.jpg)
null
I2:4
I1:2 I3:
1I4:1
I4:1
For Transaction:I1,I3
I5:1
I1:1
I3:1
![Page 12: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/12.jpg)
null
I2:5
I1:2 I3:
2I4:1
I4:1
For Transaction:I2,I3
I5:1
I1:1
I3:1
![Page 13: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/13.jpg)
null
I2:5
I1:2 I3:
2I4:1
I4:1
For Transaction:I1,I3
I5:1
I1:2
I3:2
![Page 14: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/14.jpg)
null
I2:6
I1:3
I3:1
I3:2
I5:1
I4:1
I4:1
For Transaction:I2,I1,I3,I5
I5:1
I1:2
I3:2
![Page 15: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/15.jpg)
null
I2:7
I1:4
I3:2
I3:2
I5:1
I4:1
I4:1
For Transaction:I2,I1,I3
I1:2
I3:2
I5:1
Almost Over!
![Page 16: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/16.jpg)
I2 7
I1 6
I3 6
I4 2
I5 2
null
I2:7
I1:4
I3:2
I3:2
I5:1
I4:1
I4:1
To facilitate tree traversal, an item header table is built so that each item points to itsoccurrences in the tree via a chain of node-links.
I1:2
I3:2
I5:1
FP Tree Construction Over!!Now we need to find conditional pattern base and Conditional FP Tree for each item
![Page 17: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/17.jpg)
null
I2:7
I1:4
I3:2
I3:2
I5:1
I4:1
I4:1
I1:2
I3:2
I5:1
Conditional Pattern Base
I5 {{I2,I1:1},{I2,I1,I3:1}}
Conditional FP Tree for I5:{I2:2,I1:2}
![Page 18: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/18.jpg)
null
I2:7
I1:4
I3:2
I3:2
I5:1
I4:1
I4:1
I1:2
I3:2
I5:1
Conditional Pattern Base
I4 {{I2,I1:1},{I2:1}}
Conditional FP Tree for I4:{I2:2}
![Page 19: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/19.jpg)
null
I2:7
I14
I3:2
I3:2
I5:1
I4:1
I4:1
I1:2
I3:2
I5:1
Conditional Pattern Base
I3 {{I2,I1:2},{I2:2},{I1:2}}
Conditional FP Tree for I3:{I2:4,I1:2},{I1:2}
![Page 20: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/20.jpg)
null
I2:7
I1:4
I3:2
I3:2
I5:1
I4:1
I4:1
I1:2
I3:2
I5:1
Conditional Pattern Base
I1 {{I2:4}}
Conditional FP Tree for I1:{I2:4}
![Page 21: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/21.jpg)
Frequent Patters Generated
Frequent Pattern Generated
I5 {I2, I5: 2}, {I1, I5: 2}, {I2, I1, I5: 2}
I4 {I2, I4: 2}
I3 {I2, I3: 4}, {I1, I3: 4}, {I2, I1, I3: 2}
I1 {I2, I1: 4}
![Page 22: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/22.jpg)
Advantages of FP-Growthonly 2 passes over data-set“compresses” data-setno candidate generationmuch faster than Apriori
Disadvantages of FP-GrowthFP-Tree may not fit in memory!!FP-Tree is expensive to build
Discussion
0
10
20
30
40
50
60
70
80
90
100
0 0.5 1 1.5 2 2.5 3
Support threshold(%)
Ru
n t
ime
(se
c.)
D1 FP-grow th runtime
D1 Apriori runtime
![Page 23: Data mining fp growth](https://reader035.vdocuments.mx/reader035/viewer/2022081413/547fa4abb4af9fad768b4641/html5/thumbnails/23.jpg)
Thank You