Question 1 (25 points)
For each of the three normalization techniques introduced in class, determine whether the relationships between data values change through the normalization process. For example: if a data value x is twice as big as a date value y in the original data, is that still the case once the data is normalized? Include pr oof for your conclusions.
Question 2 (30 points)
Consider the training examples shown in Table 4.7 of the textbook for a binary classification problem. Ignoring the Customer ID, determine the following for each of the
three remaining attributes (Gender, Car Type, Shirt Size):
a) Gini Index
b) Entropy
c) Misclassification Error
Question 3 (20 points)
Discuss the differences and similarities of the fields of statistics and data mining.
Question 4 (25 points)
Using Weka, visualize two datasets of your choice (excluding the IRIS dataset) from the UCI repository and discuss the results (including screen shots). Hint: you might want to try a dataset with numerical feature values and a discrete (as opposed to continuous) class attribute.
PLACE THIS ORDER OR A SIMILAR ORDER WITH US TODAY AND GET AN AMAZING DISCOUNT








Jermaine Byrant
Nicole Johnson



