Misk Jeopardy III

Clustering

100

What  Kmeans stands for ?

how the first centroid in Kmeans are selected ?

- K : number of clusters, means:the averaging the data that is finding the centroids 

- randomly, or manually

200

what is the method use to optimize the number of clusters? how it work?

Elbow method: plot of error vs number of clusters, and we choose the the elbow

 or gridsearch -you show specify the error-

300

How to select the number of clusters in the hierarchal clustering ?

Setting the threshold of average distance , then intersection between the threshold line   and the dendrogram plot  

400

What the difference between DBSCAN, and Kmeans 

In Kmeans you need to specify number of clusters but in DBSCAN you don't .

Kmeans label all the data, but DBSCAN don't.

500

What do the DBSCAN hyper-Parameter - eps and minPoints represent  ?

eps: specifies how close points should be to each other to be considered a part of a cluster.

minPoints: the minimum number of points to form a dense region

Mah

100

The problem of bagging that can be solved either :

A- statistical

B- computational

C- both

B

200

What is Bootstrapping ?

Sampling with replacement. 

300

What is the consequence of low inertia ?

Dense cluster

400

What is the code for selecting all the columns for a table in SQL ?

 SELECT *

 From table_name;

500

Tell one pro and one con of boosting

 Pros

- Achieves higher performance than bagging
- Can be used for classification and regression equally well.
- Easily handles mixed data types.

 Cons

- Difficult and time consuming to properly tune hyper-parameters.
- Cannot be parallelized like bagging (bad scalability when huge amounts of data).
- More risk of overfitting compared to bagging.

SVM

100

The cost parameter in the SVM means:

A) The number of cross-validations to be made
B) The kernel to be used
C) The tradeoff between misclassification and simplicity of the model
D) None of the above

C

200

[True or False] If you remove the non-red circled points from the data, the decision boundary will change?

 False

300

What would happen when you use very small C (C~0)?

A) Misclassification would happen
B) Data will be correctly classified
C) Can’t say
D) None of these

A

400

When the C parameter is set to infinite, which of the following holds true?

A) The optimal hyperplane if exists, will be the one that completely separates the data
B) The soft-margin classifier will separate the data
C) None of the above

A

500

What is SVC on sklearn's default kernel and C parameter?

rbf (gaussian) and 1.0

Ensembles

100

10) Which of the following algorithm are not an example of ensemble learning algorithm?

A) Random Forest
B) Adaboost
C) Extra Trees
D) Gradient Boosting
E) Decision Trees

E

200

1) Which of the following is/are true about bagging trees?

1. In bagging trees, individual trees are independent of each other
2. Bagging is the method for improving the performance by aggregating the results of weak learners

A) 1
B) 2
C) 1 and 2
D) None of these

C

300

2) Which of the following is/are true about boosting trees?

1. In boosting trees, individual weak learners are independent of each other
2. It is the method for improving the performance by aggregating the results of weak learners

A) 1
B) 2
C) 1 and 2
D) None of these

B

400

3) Which of the following is/are true about Random Forest and Gradient Boosting ensemble methods?

1. Both methods can be used for classification task
2. Random Forest is use for classification whereas Gradient Boosting is use for regression task
3. Random Forest is use for regression whereas Gradient Boosting is use for Classification task
4. Both methods can be used for regression task

A) 1
B) 2
C) 3
D) 4
E) 1 and 4

E

500

5) what will happen when  the  “max_depth” hyperparameter  is very large in Decision Tree ?

Hint : two things happen

over-fitting and the classification will take a very long time to finish

Formulas

100

What is the formula for Precision?

True Positives / (True Positives + False Positives)

200

What is the formula for Recall?

True Positives / (True Positives + True Negatives)

300

What is the formula to calculate R-square?

1 - (Residual Sum of Squares/ Total Sum of Squares)

400

What is the formula for gini index?

1- sum of squared probability  

500

what is the formula of silhouette coefficient