You are on page 1of 13

VNSIT Bhopal

A Seminar on Decision Tree in


Data Mining

Submitted to :- Submitted By :
Mr . Vinod Patel Rohit Soni
Cs-II
0161cs071081
Rohit 1
Objective
• What is data mining ?
• What is decision tree ?
• Examples of Decision tree ?
• Tree Construction
• Advantages of Decision tree ?
• Disadvantages of Decision tree ?
• Conclusion .

Rohit 2
Data Mining
• The term data mining refers to the finding of
relevant and useful information from
database .
• Data Mining Refers to variety of techniques to
identify nuggets of information or decision
making knowledge in the database and
extracting these in such a way that they can
be put to use in areas such as decision support
,prediction ,forecasting and estimation .

Rohit 3
Decision Tree
• A decision tree is a classification scheme which
generates tree and set of rules .
• It Represent the model of different classes
(Type)
• The set of record available for developing
classification method is generally divided into
two disjoint subsets
• 1) Training set 2) Test set .
• Training set for deriving the classifier.
• Test set for measuring the accuracy of
classifier .
Rohit 4
Examples of Decision Tree
Training Data set
OUTLOOK TEMP(F) HUMIDITY(%) WINDY CLASS

SUNNY 79 90 YES NOPLAY

SUNNY 56 70 NO PLAY

SUNNY 79 75 YES PLAY

SUNNY 60 90 YES NOPLAY

OVERCAST 88 88 NO NOPLAY

OVERCAST 63 75 YES PLAY

OVERCAST 88 95 NO PLAY

RAIN 78 60 NO PLAY

RAIN 66 70 NO NOPLAY

RAIN 68 60 YES NOPLAY

Rohit 5
Rules for this Decision tree
• There are five attribute in training set in which class label is special
attribute.
• Based on training data set ,we have to find set of rules to know what
values of outlook , temperature, humidity and whether or not to play
golf .
• Every path from root node to leaf represent a rule.

OUTLOOK
y rain
sunn
overcast
HUMIDITY WINDY
>7 no
5 PLAY s
< = 7 5 ye

NOPLAY PLAY
PLAY NOPLAY
Rohit 6
We have the following Rules for corresponding
decision tree .
• Rule1 : If it is sunny and the humidity is not
above 75% ,than play .
• Rule2 : If it is sunny and the humidity is not
above 75% ,than not play .
• Rule3: If it is overcast than play .
• Rule4: If it is rainy and not windy .
• Rule5: if it is rainy and windy ,than don’t play.

Rohit 7
Tree Construction principal

• Splitting Attribute :- With every node of the decision


tree ,there is an associated attribute whose value
determine the portioning of the data set when the
node is expanded .
or
 Splitting criterion :- The qualifying condition on the
splitting attribute for data set splitting at a node for a
numeric attribute criteria can be equation or an
inequality for a categorical attribute it is a member
ship condition on the subset values

Rohit 8
Main Phases for Construction of Decision Tree

• Construction Phase : The initial decision tree


is constructed in this phase ,based on the
entire training data set . It recursively
partitioning the training data set into two or
more sub partitions using a splitting criteria
,until a stopping criteria is met .
• Pruning Phase : it remove some of the useless
lower branches and nodes to improve its
performance .
• Processing the pruned tree to improve
understandability . Rohit 9
Advantages of Decision Tree

• Decision tree are able to generate understandable


rules .
• They are able to handle both numerical and
categorical attributes .
• They provide a clear indication about of which field
are most important for prediction and classification .

Rohit 10
Conclusion
• Classification is one of the important problems
in data mining , and particularly classification
using decision tree is currently one of the most
active research area in data mining field .

Rohit 11
Any
queries

Rohit 12
ou
k y
a n
T h
Rohit 13

You might also like