# g ., using entropy ). 22 W r i t i n g

g ., using entropy ). 22 W r i t i n g

1.What is an attribute? What is a data instance?

2.What is the noise? How can noise be reduced in a dataset?

3.Define outlier. Describe two different approaches to detect outliers in a dataset.

4.Describe three different techniques to deal with missing values in a dataset. Explain when each of these techniques would be most appropriate.

5.Given a sample dataset with missing values, apply an appropriate technique to deal with them.

6.Give two examples in which aggregation is useful.

7.Given a sample dataset, apply the aggregation of data values.

8.What is sampling?

9.What is simple random sampling? Is it possible to sample data instances using a distribution different from the uniform distribution? If so, give an example of a probability distribution of the data instances that is different from uniform (i.e., equal probability).

10.What is stratified sampling?

11.What is “the curse of dimensionality”?

12.Provide a brief description of what Principal Components Analysis (PCA) does. [Hint: See Appendix A and your lecture notes.] State what the input is and what the output of PCA is.

13.What is the difference between dimensionality reduction and feature selection?

14.Describe in detail two different techniques for feature selection.

15.Given a sample dataset (represented by a set of attributes, a correlation matrix, a covariance matrix), apply feature selection techniques to select the best attributes to keep (or equivalently, the best attributes to remove).

16.What is the difference between feature selection and feature extraction?

17.Give two examples of data in which feature extraction would be useful.

18.Given a sample dataset, apply feature extraction.

19.What is data discretization, and when is it needed?

20.What is the difference between supervised and unsupervised discretization?

21.Given a sample dataset, apply unsupervised (e.g., equal width, equal frequency) discretization or supervised discretization (e.g., using entropy).

22.Describe two approaches to handle nominal attributes with too many values.

23.Given a dataset, apply variable transformation: Either a given function, normalization, or standardization.

24.Definition of Correlation and Covariance, and how to use them in data pre-processing.

Instructions:

Need minimum 1000 words (Each question minimum 50 words).

No References Required