Tasks

After selecting the topic, you have to define a data mining task: for example, prediction of average

temperature in some city for a given period, prediction if a patient has a kidney disease, association

rules in terrorist attacks...

The main goal of this project is to practice Data Mining skills in all steps of the study. Thus, you need

to perform the following tasks:

Phase $1$:

$1.$ Understand the data: Import the data selected $.........$csv file into RapidMiner. While importing the

data, you should properly choose the types of the attributes. Identify the type of each attribute

$($nominal$,$ ordinal, interval or ratio$)$ and report it$.$ Get statistics about the data to identify the values of

the summarizing properties for each attribute including frequency, location and spread $[$e$.$g$.$ value

ranges of the attributes, frequency of values, medians, means, variances or standard deviation$].$

$[$CLO $2\mathrm{.}12$ S$3][5$ Marks$]$

$2.$ Analyze the data by using different visualization techniques provided by RapidMiner.

$[$CLO $2\mathrm{.}12$ S$3][2$ Mark$]$

$3.$ Find and analyze the correlated attributes $($you can use the Correlation Matrix operator or Scatter

Plot chart$).[$CLO $2\mathrm{.}12$ S$3][1$ Mark$]$

$4.$ Propose a way of cleaning data: e$.$g$.$ replacing missing values, do normalization if needed, corrections

or errors, etc. $[$CLO $1\mathrm{.}21$ K$2][3$ Marks