Next Deck

Question 1

a decision tree can be converted to a set of rules by mapping from

Answer 1

the root node to the leaf nodes one by one

Question 2

P(x)

Answer 2

Predictor Prior Probability

Question 2

in this method we assign each observative to its own cluster, then compute the similarity (distance) between each of the clusters and join the two most similar clusters, repeat until there is only a single cluster left

Answer 2

agglomerative method

Question 3

P(x|c)

Answer 3

Likelihood

Question 3

distance between two clusters is defined as the average distance between _ _ in one cluster to _ _ in the other cluster

Answer 3

average linkage, each point, every point

Question 3

The _ (SSE) between the 2 clusters over all of the variables is used as the distance

Answer 3

error sum of squares, Ward’s method

Question 4

Class prior probability

Answer 4

P(c)

Question 4

ID3. If the sample is completely homogeneous the _

Answer 4

entropy is zero

Question 4

in this method we assign all of the observations to a single cluster and then partition the cluster to two least similar clusters, finally we proceed recursively on each cluster until there is one cluster for each observation

Answer 4

divisive method

Question 4

to build a decision tree we need to calculate two types of entropy using freq tables as follows. What is the first, and write the formula.

Answer 4

(a) entropy of the target

Question 5

OneR Algorithm

Answer 5

For each predictor

For each value of that predictor, make a rule is follows

Count how often each class appears

Find the most frequent class

Make the rule assign that class to this value

Calculate the total error of the rules of each predictor

Choose the predictor with the smallest total error

:Fat friends can’t find many charitable characters:

Question 5

constructing a decision tree is all about finding attribute that _

Answer 5

returns the highest information gain (the most homogeneous branches)

Question 6

two types of hierarchical clustering

Answer 6

divisive, agglomerative

Question 6

decision tree: step 1. calculate the entropy of the target

step 2. split on the different attributes & calc the entropy for each branch

step 3. add proportionally to get the _

step 4. _

The result is the _

Answer 6

total entropy for the split

subtract this from the entropy before the split

information gain or decrease in entropy

Question 8

P(c|x)

Answer 8

Posterior Probability

Question 9

K-means clustering: intends to partition n objects into k clusters in which _

Answer 9

each object belongs to the cluster with the nearest mean

Question 10

Bayesian: the _ can be calculated first by constructing _

Answer 10

posterior probability, frequency table

Question 11

Posterior Probability

Answer 11

P(c|x)

Question 12

The ID3 algorithm is run recursively on the _ until all data _.

Answer 12

non-leaf branches, is classified

Question 13

ID3. if the sample is equally divided is has:

Answer 13

entropy of one

Question 15

decision tree: topmost node

Answer 15

root node

Question 15

proximity matrix in clustering: the following methods differ in how the distance between each cluster is measured:

Answer 15

• Single Linkage
• Complete Linkage
• Average Linkage
• Minimum Variance (Ward’s Method)
• Centroid Method

Single clusters are most comforting

Question 16

Decision tree: represents a classification or decision

Answer 16

Leaf Node

Question 17

ID3 uses _ & _ to construct a decision tree

Answer 17

entropy, information gain

Question 19

K-means clusteromg produces _ different clusters. The best number of clusters leading to the greatest seperation is not known as a priori and must be computed from the data.

Answer 19

k

Question 19

the object of k-means clustering is to minimize the \_

Answer 19

total intra-cluster variance or the squared error function

Question 19

decision tree: step 1. calculate the entropy of the target step 2. split on the different attributes & \_

Answer 19

calculate the entropy for each branch

Question 21

Decision tree: has two or more branches

Answer 21

decision node

Question 22

Likelihood

Answer 22

P(x|c)

Question 22

distance between two clusters is defined as the shortest distance beween two points in each cluster

Answer 22

single linkage hierarchical clustering

Question 23

The information gain is based on the _ ater a dataset is split on an attribute

Answer 23

decrease in entropy

Question 24

distance between two clusters is defined as the longest distance between two points in each cluster

Answer 24

complete linkage

Question 26

P(c|x) =

Answer 26

P(x|c)P(c) \_\_\_\_\_\_\_\_ P(x)

Question 28

Draw the likelihood table and work out the posterior probability

Answer 28

answer.

Question 29

frequency tables for numerical variables, first option

Answer 29

binning

Question 30

the _ is based on Bayes theorem with

Answer 30

naive bayesian classified, independence assumptions between predictors

Question 31

Gain(T,X) =

Answer 31

Entropy(T) - Entropy(T,X)

Question 32

Bayesian step (3)

Answer 32

the class with the highest posterior probability is the outcome of prediction

Question 33

before any clustering is performed it is required to determine the \_

Answer 33

proximity matrix containing the distance between each point using a distance function

Question 34

One Rule classification algorithm

Answer 34

OneR

Question 35

the probability density function for the normal distribution is defined by two parameters

Answer 35

mean and standard deviation

Question 36

P(c)

Answer 36

Class Prior Probability

Question 37

decision tree core algorithm by JR Quinlan \_, uses a \_, with no \_

Answer 37

ID3, greedy search, no backtracking

Question 38

OneR, a low total error means a

Answer 38

higher contribution to the predictability of the model

Question 39

OneR generates one rule for:

Answer 39

each predictor in the data then select the rule with the smallest total error as it's one rule

Question 40

decision tree: step 1. calculate the entropy of the \_

Answer 40

target

Question 41

One Rule, to create a rule, \_

Answer 41

contruct a frequency table for each predictor against the targer

Question 42

Information gain =

Answer 42

gain(T,X) = entropy(T) - entropy(T,X)

Question 44

ID3 uses _ to calculate the \_

Answer 44

entropy, homogeneity of a sample

Question 46

Draw a freq table for Outlook: Sunny/Overcase/Rainy, Play golf: yes/no

Answer 46

Question 47

the center of the group of objects (the centroid) is used to determine the average distance between clusters of objects

Answer 47

Centroid method

Question 49

Adding 1 to all the counts when an attribute value doesn't occur with every class value

Answer 49

the zero frequency problem

Question 50

Work out the entropy of the target: * play golf yes = 9 * play gold no = 5

Answer 50

Entropy(5,9) = Entropy(0.36,0.64) =-(0.36 \* log2 0.36) - (0.64 log2 0.64) = 0.94

Question 51

wowk out the likelihood of yes and no, and the probability

Answer 51

answer0.014109

Question 52

Predictor Prior Probability

Answer 52

P(x)

Question 53

K-means clustering algorithm

Answer 53

1. cluster the data into k groups where k is predefined. 2. randomly select k points as cluster centers 3. assign objects to their closest cluster (euclidean) 4. centroid calculation (or mean) 5. repeat until cluster asignments unchanged in rounds Clustering: randomly assigning centroids & repeating

Question 54

Bayesian step 2. Transform the freq tables into _ and calculate the \_

Answer 54

likelihood tables, posterior probability for each class

Question 55

A branch with what entropy needs no more splitting

Answer 55

zero

Question 56

Creating clusters that have a predetermined order from top to bottom

Answer 56

hierarchical clustering