Scribd
Upload
87 views

FP-Growth Algorithm

FP-Growth is an algorithm for frequent pattern mining that avoids candidate generation. It builds a compact data structure called an FP-tree to store transaction data, then mines the tree to find frequent itemsets. The algorithm involves building the FP-tree in two database scans, then extracting frequent itemsets directly from the structure. An example is provided demonstrating how transaction data is ordered, inserted into the tree, and mined to identify frequent patterns.

Uploaded by

Anjali Meena
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
87 views

FP-Growth Algorithm

FP-Growth is an algorithm for frequent pattern mining that avoids candidate generation. It builds a compact data structure called an FP-tree to store transaction data, then mines the tree to find frequent itemsets. The algorithm involves building the FP-tree in two database scans, then extracting frequent itemsets directly from the structure. An example is provided demonstrating how transaction data is ordered, inserted into the tree, and mined to identify frequent patterns.

Uploaded by

Anjali Meena
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

WELCOME

FP-GROWTH
ALGORITHM
PRESENTED BY
ANJALI XXXXX
WHAT IS FP GROWTH?

• FP Growth Stands for Frequent Pattern


Growth.
• It is a scalable technique for mining frequent
pattern in a database.
FP-GROWTH

FP-Growth allows frequent itemset discovery without


candidate itemset generation.
Two step approach:
• 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
BULIDING THE FP-TREE

Scan data to determine the support count of each item.


Infrequent items are discarded, while the frequent items
are sorted in decreasing support counts.
Make a second pass over the data to construct the FP­
tree.
As the transactions are read, before being processed,
their items are sorted according to the above order.
SUPPORT COUNT

(absolute) support, or, support count of X:


Frequency or occurrence of an itemset X
• An itemset X is frequent if X’s support is no
less than a minsup threshold
FP TREE EXAMPLE (HOW TO IDENTIFY FREQUENT
PATTERNS USING FP TREE ALGORITHM

• Suppose we have the following DataBase.


STEP 1 -CALCULATE MINIMUM SUPPORT

• First should calculate the minimum support count.


Question says minimum support should be 30%. It
calculate as follows:
Minimum support count(30/100 * 8) = 2.4
As a result, 2.4 appears but to empower the easy
calculation it can be rounded to the ceiling value. Now,
Minimum support count is ceiling(30/100 * 8) = 3
STEP 2 -FIND FREQUENCY OF
OCCURRENCE

• Now time to find the frequency of occurrence of


each item in the Database table. For example, item
A occurs in row 1,row 2,row 3,row 4 and row 7.
Totally 5 times occurs in the Database table. You can
see the counted frequency of occurrence of each
item in Table 2
STEP 2 -FIND FREQUENCY OF OCCURRENCE

TID Frequenc
y
A 5
B 6
C 3
D 6
E 4
Table 1 - Snapshot of
Table2 -Frequency of
the Database
Occurrence
STEP 3 -PRIORITIZE THE ITEMS

• In Table 2 you can see the numbers written in Red


pen. Those are the priority of each item according to
it's frequency of occurrence. Item B got the highest
priority (1) due to it's highest number of
occurrences. At the same time you have opportunity
to drop the items which not fulfill the minimum
support requirement. For instance, if Database
contain F which has frequency 1, then you can drop
it.
STEP 3 -PRIORITIZE THE ITEMS

TID Frequency
Priority
A 5
3
B 6
1
C 3
5
D Table2 -Frequency
6 of
2 Occurrence
E 4
4
STEP 4 -ORDER THE ITEMS ACCORDING TO
PRIORITY

• As you see in the Table 3 new column added to the


Table 1. In the Ordered Items column all the items
are queued according to it's priority, which
mentioned in the Red ink in Table 2. For example, in
the case of ordering row 1, the highest priority item
is B and after that D, A and E respectively.
STEP 4 -ORDER THE ITEMS ACCORDING TO
PRIORITY

Table 3 - New version of the


Table 1
STEP 5 -ORDER THE ITEMS ACCORDING TO PRIORITY
Null

• As a result of previous steps we got a ordered


items table (Table 3). Now it's time to draw the
B: 1
FP tree. We will mention it row by row .
• Row 1:
D: 1
Note that all FP trees have 'null' node as the
root node. So draw the root node first and attach
A:1
the items of the row 1 one by one respectively.
(See the Figure 1) And write their occurrences in
E:1
front of it
Figure 1- FP tree for
Row 1
NUL
L

Row 2:
B:2
Then update the above tree (Figure 1) by
entering the items of row 2. The items of row 2
are B,D,A,E,C. Then without creating another D:2
branch you can go through the previous branch
up to E and then you have to create new node
A:2
after that for C. This case same as a scenario of
traveling through a road to visit the towns of the
country. You should go through the same road to E:2
achieve another town near to the particular
town. When you going through the branch
C:1
second time you should erase one and write two
for indicating the two times you visit to that Figure 2- FP tree for
node. If you visit through three times then write Row 1,2
three after erase two
NUL
L
• Row 3:
B:2
In row 3 you have to visit B,A,E and C
respectively. So you may think A:1 D:2
you can follow the same branch again
by replacing the values of B,A,E and C E:1 A:2

. But you can't do that you have


C:1 E:2
opportunity to come through the B.
But can't connect B to existing A C:1
overtaking D. As a result you should
Figure 3 - After adding third
draw another A and connect it to B row
and then connect new E to that A and
new C to new E.
NUL
L

Row 4: B:4 D:1

Then row 4 contain B,D,A. Now


A:1 D:3
we can just rename the
frequency of occurrences in the E:1 A:3
existing branch. As B:4,D:3,A:3.
C:1
Row 5: E:2

In fifth row have only item D.


C:1
Now we have opportunity draw
new branch from 'null' node. Figure 4- Connect D to null
See Figure 4. node
NUL
L

B:6 D:2
Row 6:
B and D appears in row 6. So
C:1 A:1 D:4 A:1
just change the B:4 to B:5 and
D:3 to D:4.
E:1 A:3 E:1
Row 7:
Attach two new nodes A and E
C:1 E:2
to the D node which hanging on
the null node. Then mark D,A,E
C:1
as D:2,A:1 and E:1.
Row 8 : Figure 5 - Final FP tree
(Ohh.. last row) Attach new node
C to B. Change the traverse
times.(B:6,C:1)
STEP 6 -VALIDATION

• After the five steps the final FP tree as follows: Figure 5.


• How we know is this correct?
• Now count the frequency of occurrence of each item of the FP
tree and compare it with Table 2. If both counts equal, then it
is positive point to indicate your tree is correct.
BENEFITS OF THE FP-TREE STRUCTURE
• Completeness
 Preserve complete information for frequent pattern mining
 Never break a long pattern of any transaction
• Compactness
 Reduce irrelevant info—infrequent items are gone
 Items in frequency descending order: the more frequently
occurring, the more
likely to be shared
 Never be larger than the original database (not count node-links
and the count field)
FP-GROWTH COMPLEXITY

• Therefore, each path in the tree will be at least partially


traversed the number of items existing in that tree path (the
depth of the tree path) * the number of items in the header.
• Complexity of searching through all paths is then bounded by
O(header_count2 * depth of tree)
REFERENCES

• Pang-Ning Tan, Michael Steinbach, Vipin Kumar:Introduction


to Data Mining, Addison-Wesley
Thank
You

You might also like