Unsupervised Learning - Kmeans Week 11 Challenge

Ans 1)

When dealing with categorical data, measuring similarity between instances involves using metrics specifically designed for categorical variables. Unlike numerical data where Euclidean distance or other distance metrics are common, categorical data requires different techniques.

Hamming Distance: For binary categorical attributes, Hamming distance counts the number of positions at which the corresponding symbols are different.

Jaccard Similarity Coefficient: For sets of categorical variables, Jaccard similarity measures the size of the intersection relative to the size of the union of the sets.

Dice Similarity Coefficient: Another measure for set similarity, Dice coefficient is similar to Jaccard but uses twice the size of the intersection in the numerator.

Ans 2)

There were a lot of car related datasets so i decide to take car mileage dataset which i used for PCA.

Kindly refer attachment