Classification:
Decision Trees
Outline
Top-Down Decision Tree Construction
Choosing the Splitting Attribute
Information Gain and Gain Ratio
2
DECISION TREE
An internal node is a test on an attribute.
A branch represents an outcome of the test, e.g.,
Color=red.
A leaf node represents a class label or class label
distribution.
At each node, one attribute is chosen to split training
examples into distinct classes as much as possible
A new case is classified by following a matching path
to a leaf node.
3
Weather Data: Play or not Play?
Outlook Temperature Humidity Windy Play?
sunny hot high false No
sunny hot high true No Note:
overcast hot high false Yes Outlook is the
rain mild high false Yes Forecast,
rain cool normal false Yes
no relation to
rain cool normal true No
overcast cool normal true Yes
Microsoft
sunny mild high false No email program
sunny cool normal false Yes
rain mild normal false Yes
sunny mild normal true Yes
overcast mild high true Yes
overcast hot normal false Yes
rain mild high true No
4
Example Tree for “Play?”
Outlook
sunny
overcast rain
Humidity Yes
Windy
high normal true false
No Yes No Yes
5
Building Decision Tree [Q93]
Top-down tree construction
At start, all training examples are at the root.
Partition the examples recursively by choosing one
attribute each time.
Bottom-up tree pruning
Remove subtrees or branches, in a bottom-up
manner, to improve the estimated accuracy on new
cases.
6
Choosing the Splitting Attribute
At each node, available attributes are evaluated
on the basis of separating the classes of the
training examples. A Goodness function is used
for this purpose.
Typical goodness functions:
information gain (ID3/C4.5)
information gain ratio
gini index
7
witten&eibe
Which attribute to select?
8
witten&eibe
A criterion for attribute selection
Which is the best attribute?
The one which will result in the smallest tree
Heuristic: choose the attribute that produces the
“purest” nodes
Popular impurity criterion: information gain
Information gain increases with the average purity of
the subsets that an attribute produces
Strategy: choose attribute that results in greatest
information gain
9
witten&eibe
Computing information
Information is measured in bits
Given a probability distribution, the info required to
predict an event is the distribution’s entropy
Entropy gives the information required in bits (this can
involve fractions of bits!)
Formula for computing the entropy:
entropy( p1 , p2 , , pn ) p1logp1 p2logp2 pn logpn
10
witten&eibe
*Claude Shannon “Father of
information theory”
Born: 30 April 1916
Died: 23 February 2001
Claude Shannon, who has died aged 84, perhaps
more than anyone laid the groundwork for today’s
digital revolution. His exposition of information
theory, stating that all information could be
represented mathematically as a succession of
noughts and ones, facilitated the digital
manipulation of data without which today’s
information society would be unthinkable.
Shannon’s master’s thesis, obtained in 1940 at MIT,
demonstrated that problem solving could be
achieved by manipulating the symbols 0 and 1 in a
process that could be carried out automatically with
electrical circuitry. That dissertation has been hailed
as one of the most significant master’s theses of the
20th century. Eight years later, Shannon published
another landmark paper, A Mathematical Theory of
Communication, generally taken as his most
important scientific contribution.
Shannon applied the same radical approach to cryptography research, in which he later
became a consultant to the US government.
Many of Shannon’s pioneering insights were developed before they could be applied in
practical form. He was truly a remarkable man, yet unknown to most of the world.
11
witten&eibe
Example: attribute “Outlook”, 1
Outlook Temperature Humidity Windy Play?
sunny hot high false No
sunny hot high true No
overcast hot high false Yes
rain mild high false Yes
rain cool normal false Yes
rain cool normal true No
overcast cool normal true Yes
sunny mild high false No
sunny cool normal false Yes
rain mild normal false Yes
sunny mild normal true Yes
overcast mild high true Yes
overcast hot normal false Yes
rain mild high true No
12
witten&eibe
Example: attribute “Outlook”, 2
“Outlook” = “Sunny”:
info([2,3]) entropy(2/5,3/5) 2 / 5 log(2 / 5) 3 / 5 log(3 / 5) 0.971 bits
Note: log(0) is
“Outlook” = “Overcast”:
not defined, but
info([4,0]) entropy(1,0) 1log(1) 0 log(0) 0 bits
we evaluate
0*log(0) as zero
“Outlook” = “Rainy”:
info([3,2]) entropy(3/5,2/5) 3 / 5 log(3 / 5) 2 / 5 log(2 / 5) 0.971 bits
Expected information for attribute:
info([3,2], [4,0],[3,2]) (5 / 14) 0.971 (4 / 14) 0 (5 / 14) 0.971
0.693 bits
13
witten&eibe
Computing the information gain
Information gain:
(information before split) – (information after split)
gain(" Outlook") info([9,5]) - info([2,3], [4,0], [3,2]) 0.940 - 0.693
0.247 bits
Compute for attribute “Humidity”
14
witten&eibe
Example: attribute “Humidity”
“Humidity” = “High”:
info([3,4]) entropy(3/7,4/7) 3 / 7 log(3 / 7) 4 / 7 log(4 / 7) 0.985 bits
“Humidity” = “Normal”:
info([6,1]) entropy(6/7,1/7) 6 / 7 log(6 / 7) 1 / 7 log(1 / 7) 0.592 bits
Expected information for attribute:
info([3,4], [6,1]) (7 / 14) 0.985 (7 / 14) 0.592 0.79 bits
Information Gain:
info([9,5]) - info([3,4], [6,1]) 0.940 - 0.788 0.152
15
Computing the information gain
Information gain:
(information before split) – (information after split)
gain(" Outlook") info([9,5]) - info([2,3], [4,0], [3,2]) 0.940 - 0.693
0.247 bits
Information gain for attributes from weather
data: gain("Outlook") 0.247 bits
gain("Temperature" ) 0.029 bits
gain(" Humidity" ) 0.152 bits
gain(" Windy" ) 0.048 bits
16
witten&eibe
Continuing to split
gain(" Humidity") 0.971 bits
gain("Temperatur e" ) 0.571 bits
gain(" Windy" ) 0.020 bits
17
witten&eibe
The final decision tree
Note: not all leaves need to be pure; sometimes
identical instances have different classes
Splitting stops when data can’t be split any further
18
witten&eibe
Highly-branching attributes
Problematic: attributes with a large number of
values (extreme case: ID code)
Subsets are more likely to be pure if there is a
large number of values
Information gain is biased towards choosing attributes
with a large number of values
This may result in overfitting (selection of an attribute
that is non-optimal for prediction)
21
witten&eibe
Weather Data with ID code
ID Outlook Temperature Humidity Windy Play?
A sunny hot high false No
B sunny hot high true No
C overcast hot high false Yes
D rain mild high false Yes
E rain cool normal false Yes
F rain cool normal true No
G overcast cool normal true Yes
H sunny mild high false No
I sunny cool normal false Yes
J rain mild normal false Yes
K sunny mild normal true Yes
L overcast mild high true Yes
M overcast hot normal false Yes
N rain mild high true No
22
Split for ID Code Attribute
Entropy of split = 0 (since each leaf node is “pure”, having only
one case.
Information gain is maximal for ID code
23
witten&eibe
Gain ratio
Gain ratio: a modification of the information gain
that reduces its bias on high-branch attributes
Gain ratio should be
Large when data is evenly spread
Small when all data belong to one branch
Gain ratio takes number and size of branches into
account when choosing an attribute
It corrects the information gain by taking the intrinsic
information of a split into account (i.e. how much info
do we need to tell which branch an instance belongs to)
24
witten&eibe
Gain Ratio and Intrinsic Info.
Intrinsic information: entropy of distribution of
instances into branches
|S | |S |
IntrinsicInfo(S , A) i log i .
|S| 2 | S |
Gain ratio (Quinlan’86) normalizes info gain by:
GainRatio(S , A) Gain(S, A) .
IntrinsicInfo(S , A)
25
Computing the gain ratio
Example: intrinsic information for ID code
info([1,1, ,1) 14 (1 / 14 log1 / 14) 3.807 bits
Importance of attribute decreases as intrinsic
information gets larger
Example of gain ratio:
gain("Attribute")
gain_ratio(" Attribute")
intrinsic_info("Attribute")
Example: 0.940 bits
gain_ratio(" ID_code") 0.246
3.807 bits
26
witten&eibe
Gain ratios for weather data
Outlook Temperature
Info: 0.693 Info: 0.911
Gain: 0.940-0.693 0.247 Gain: 0.940-0.911 0.029
Split info: info([5,4,5]) 1.577 Split info: info([4,6,4]) 1.362
Gain ratio: 0.247/1.577 0.156 Gain ratio: 0.029/1.362 0.021
Humidity Windy
Info: 0.788 Info: 0.892
Gain: 0.940-0.788 0.152 Gain: 0.940-0.892 0.048
Split info: info([7,7]) 1.000 Split info: info([8,6]) 0.985
Gain ratio: 0.152/1 0.152 Gain ratio: 0.048/0.985 0.049
27
witten&eibe
More on the gain ratio
“Outlook” still comes out top
However: “ID code” has greater gain ratio
Standard fix: ad hoc test to prevent splitting on that type of
attribute
Problem with gain ratio: it may overcompensate
May choose an attribute just because its intrinsic information is
very low
Standard fix:
First, only consider attributes with greater than average information gain
Then, compare them on gain ratio
28
witten&eibe
*CART Splitting Criteria: Gini Index
If a data set T contains examples from n classes, gini
index, gini(T) is defined as
where pj is the relative frequency of class j in T.
gini(T) is minimized if the classes in T are skewed.
29
*Gini Index
After splitting T into two subsets T1 and T2 with sizes
N1 and N2, the gini index of the split data is defined
as
The attribute providing smallest ginisplit(T) is chosen
to split the node.
30
Discussion
Algorithm for top-down induction of decision
trees (“ID3”) was developed by Ross Quinlan
Gain ratio just one modification of this basic algorithm
Led to development of C4.5, which can deal with
numeric attributes, missing values, and noisy data
Similar approach: CART (to be covered later)
There are many other attribute selection criteria!
(But almost no difference in accuracy of result.)
31
Summary
Top-Down Decision Tree Construction
Choosing the Splitting Attribute
Information Gain biased towards attributes with a
large number of values
Gain Ratio takes number and size of branches
into account when choosing an attribute
32
