know

Question 1

universe
attributes
Va

Answer 1

all go U={x,x,x}

Question 2

indiscernibility relation IND{A}

Answer 2

son las equivalences y van en {{z,z},{s}}
aqui tienes que fijarte que te pide

Question 3

B lower es

Answer 3

100 cierto

Question 4

B upper

Answer 4

si y no

Question 5

positive region es

Answer 5

todo lo que en base a lo que te dicen es cierto ojo lo falso tambien cuenta

Question 6

decision system

Answer 6

A=(U, A U {d})

Question 7

Boundary region es

Answer 7

b lower - b upper

Question 8

accuracy of the approximation

Answer 8

b upper / b lowe

Question 9

generalized decision

Answer 9

es cuando pones cada INDa osea la equivalence class con su decision
no es consistente si tiene varios numeros

Question 10

decision relative discernability matrix

Answer 10

haces la tabla con las equivalence y pones las diferencias aqui es DECISION RELATIVE entonces si tienen la misma decision pones TETA

Question 11

boolean discernabilityfunction

Answer 11

es poner todas las diferencias pero en (xx) y las escibres asi
fA(attributos) = (X^b) v (ddhdh)
y luego haces la simplificacion

Question 12

ojo con la simplificacion

Answer 12

tiene que tener todo los valores con lo que debes simplificar por eso es bueno tener una pqeuña

Question 13

support?

Answer 13

Number of objects that fulfill the rule
te van a dar una regla y support es todos los que la cumplen completamente

Question 14

accuracy es…

Answer 14

A fraction of correctly classified objects for the rule conditions
support / todos los que tiene la misma regla pero no la misma decision. entonces todos los que estan en la misma equivalnece class|

Question 15

coverage es…

Answer 15

support /# de objetos que son la regla contraria

Question 16

strenght…

Answer 16

support/todos los objetos en el universo

Question 17

what is the point of using Boolean reasoning in rough sets?

Answer 17

Boolean reasoning is used to obtain the reducts

Question 18

Why do we need to do discretization?

Answer 18

Because in rough sets we use boolean reasoning and for that we need discrete data.

Question 19

supervised learning

Answer 19

data with decision classes /labels
classification problems
case-control studies
algorithm =. decision trees or rule-based learning

Question 20

unsupervised

Answer 20

unknown decision classes
looking for patterns in data
hierarchical clusterings

Question 21

performance or interpretability

Answer 21

performance for things involving life
interpretability for complex coding or data analysis model complex

interpretable ML techniques aim at giving legible answers for predictions

Question 22

cutoffpermutation value needs to be set to at least…

Answer 22

20! to have significant results

Question 23

when is undersampling neccesary

Answer 23

when the distribution of classes is unequal
e.g. 20 controles y 5 pacientes

Question 24

What is the classification accuracy?
what is the expected value?

Answer 24

Accuracy is the power/strenght of our model. We want accuracy over the expected 0.5 because that indicates that the model is correct more often than random chance.

Accuracy = (TP +TN) / (TP + TN + FP + FN). The number of correct predictions divided by total.

Question 25

can we trust the AUC with low samples

Answer 25

It is questionable if we should trust the model performance with such low values.

Question 26

when is appropiate to de k-fold cross validation

Answer 26

when we dont have external test set to test our data

Question 27

sensitivity

Answer 27

TP/(TP+FN)
TRUE POSITIVE RATE

Question 28

specificity

Answer 28

TN/(TN+FP)
TRUE NEGATIVE RATE

Question 29

AUC MEANING

Answer 29

its the area under the ROC curve and its obtained by changing the threshold (cut-off) between true positive rate and true negative rate,

Question 30

How to improve a rule based model. Improving the accuracy and AUC

Answer 30

• Increase the number of permutations in MCFS
• iNCREASE NUMBER IN BOTH SAMPLES
• CHANGE REDUCER e.g johnson to genetic
• decrese or increase the number of features
• detect and remove objects that are wrongly classified

Question 31

Explain how you interpret a VisuNet graph, what does the following parameters mean?
- node size
- lines between nodes
- border size

Answer 31

node size= tells you the decision and coverage support.

Intensity of node color = tells us the relative importance of the feature.

lines between the nodes tell you about how strongly connected the nodes are. Red, thick lines indicates stronger connections.

Border size tells you how many times that feature is included in a rule.

Question 32

describe a strategy for construction decision trees.

Answer 32

use a TOP-DOWN approach and construct the tree RECURSIVELY one split at a time. For each split, the one with the highest ratio is chosen. The tree is finished when there are no possible splits that reduce the information value further.
* Top-down
* recursive
* one at a time

Question 33

Explain decision trees

Answer 33

The root of the tree represents the entire dataset and the first split from the node is the most important because it divides the largest number of features. Further down in the tree, we have other nodes that represent smaller splits and divergences in the data. The leafs represent the final classifications and we can follow the branches from root to leaf to get a sort of “rule” for the classification.

Question 34

What is feature selection and when should we use it?

Answer 34

Identify an ordered list of attributes that best discriminates between/among decision classes.
Good for identifying the most important features for classification in very large sets of features.

External features selection with for example MCFS is necessary if the dataset has more features than objects in the universe and it is done to reduce the dimensionality of features to those that most affect the classification.

Question 35

MCFS MAIN STEPS

Answer 35

1. create S SUBSETS of m attributes chosen at random from the original d attributes
2. s is chosen so that the difference in ranking between ten iterations is small and stable
3. divide the subsets into training and tests set t times
4. for each training set make a tree classifier
5. evaluate on thhe test
6. calculñate the relative importance

Question 36

DECISION TREE STEPS

Answer 36

1. CALCULAS INFO DE TODO
2. separas por atributo y calculas el info size de cada uno por sus diferentes clases. info ([2,3])
3. SACAS el weighted de todos las clas de por ejemplo gen 1 donde sumas si era 2, 3 entonces 5/suma de todo + info de los otros
4. gain resta de original - weighted
5. split_info = sacas el info de la suma de los posibles classes de los dos [] sacas suma
6. gain ratio =. gain / split _info

Question 37

steps for creating a rule-bassed model

Answer 37

1. put aside an external validation set of subject samples
2. data processing, remove imcomplete data
3. feature selection: perform a feature selection to select the most important feautures and reduce noise

Question 38

advantages and disadvantages of MCFS=

Answer 38

Advantages=
preservation of the features
ranking of the features and statisticsal significance of them
little feature shadowing

Disadvantages=
Not possible to explain variability in the data
computational expensive

Question 39

odd distibution of objects e.g 20 cases and 2 control

Answer 39

Undersampling

Question 40

discretization,when should it be performed

Answer 40

before the split of test and training

Question 41

genetic algorithm

Answer 41

uses evolution and continues to search for better

Question 42

boolean expression law used in simplificarion

Answer 42

((AvB)^A =A

Question 43

technique used in MCFS to find a cutoff

Answer 43

permutation test

Question 44

resources to interpret gene expression levels

Answer 44

ENSEMBL GENE ONTOLOGY KEGG