Example calculation of entropy, Computer Engineering

Example Calculation:

If we see an example we are working with a set of examples like S = {s1,s2,s3,s4} categorised with a binary categorisation of positives and negatives like that s1  is positive and the rest are negative. Expect further there that we want to calculate the information gain of an attribute, A, and  A can take the values {v1,v2,v3} obviously. So lat in finally assume that as: 

1745_Example Calculation of Entropy.png

Whether to work out the information gain for A relative to S but we first use to calculate the entropy of S. Means that to use our formula for binary categorisations that we use to know the proportion of positives in S and the proportion of negatives. Thus these are given such as: p+ = 1/4 and p- = 3/4. So then we can calculate as: 

Entropy(S) = -(1/4)log2(1/4) -(3/4)log2(3/4) = -(1/4)(-2) -(3/4)(-0.415) = 0.5 + 0.311

= 0.811 

Now next here instantly note that there to do this calculation into your calculator that you may need to remember that as: log2(x) = ln(x)/ln(2), when ln(2) is the natural log of 2. Next, we need to calculate the weighted Entropy(Sv) for each value v = v1, v2, v3, v4, noting that the weighting involves multiplying by (|Svi|/|S|). Remember also that Sv  is the set of examples from S which have value v for attribute A. This means that:  Sv1 = {s4}, sv2={s1, s2}, sv3 = {s3}. 

We now have need to carry out these calculations: 

(|Sv1|/|S|) * Entropy(Sv1) = (1/4) * (-(0/1)log2(0/1) - (1/1)log2(1/1)) = (1/4)(-0 -

(1)log2(1)) = (1/4)(-0 -0) = 0 

(|Sv2|/|S|) * Entropy(Sv2) = (2/4) * (-(1/2)log2(1/2) - (1/2)log2(1/2))

                                      = (1/2) * (-(1/2)*(-1) - (1/2)*(-1)) = (1/2) * (1) = 1/2 

(|Sv3|/|S|) * Entropy(Sv3) = (1/4) * (-(0/1)log2(0/1) - (1/1)log2(1/1)) = (1/4)(-0 -

(1)log2(1)) = (1/4)(-0 -0) = 0 

Note that we have taken 0 log2(0) to be zero, which is standard. In our calculation,

we only required log2(1) = 0 and log2(1/2) =  -1. We now have to add these three values together and take the result from our calculation for Entropy(S) to give us the final result: 

Gain(S,A) = 0.811 - (0 + 1/2 + 0) = 0.311 

Now we look at how information gain can be utilising in practice in an algorithm to construct decision trees.

Posted Date: 1/11/2013 6:43:07 AM | Location : United States

Related Discussions:- Example calculation of entropy, Assignment Help, Ask Question on Example calculation of entropy, Get Answer, Expert's Help, Example calculation of entropy Discussions

Write discussion on Example calculation of entropy
Your posts are moderated
Related Questions
Characteristics of computer storage: Storage technologies at all of levels of the storage hierarchy may be distinguished by evaluating particular core characteristics and alon

Is it possible to extract data from tables without using the event 'GET' in the report with an appropriate LDB. False.   You can extract data from tables using Select stateme

What is a reference string? An algorithm is evaluated by running it on a exacting string of memory references and computing the number of page faults. The string of memory refe

Somehow, the worksheet has external links to files that are no longer around. How can we delete the links? Ans) This happens all of the time to MrExcel. I downloaded a little

Representations/Languages Used: Many people are taught "AI" with the opening line: "The three most important things in "AI" are  representation, representation and representat

Explain about the Client/Server Computing? Although there are different various configurations, various hardware and software platforms and even various network protocols into

Q. Show the Bus and Memory Transfers? A digital computer has many registers and rather than connecting wires amid all registers to transfer information between them a common bu

Need an help for projects

Q. For function F(X, Y, Z) = ∑(1, 2, 3, 5, 6) using TRUTH TABLE only 1.  Find POS expression 2.  Simplify POS expression 3.  Implement this simplified expression using t

Assessing Heuristic Searches: Given a particular problem you want to build an agent to solve, so there may be more than one way of justifying it as a search problem, more than