This exercise is a homework assignment that I have in Data Mining course.

PROBLEM 2 In this problem you required to apply various clustering techniques on a given dataset Seeds.csv, which contains 4 attributes of various plant seeds: the length of the seed, the width of the seed, asymmetry coefficient of the seed and the compactness coefficient of the seed. The dataset contains a header and the values are delimited by semicolons. a. Apply the "elbow" (a.k.a "knee") rule to find the optimal number of clusters for this dataset b. Apply the K-means algorithm on this dataset with the number of clusters found in part a. c. Visualize the clusters using scatter plot d. Draw the heatmap of this clustering e. Apply (at least one variant of) hicrarchical clustering on this dataset to generate K partitions (where K is the value found in part a) f. Visualize the elusters using scatter plot g. Draw the heatmap of this clustering h. Briefly compare the results of K-means and hierarchical clustering for this dataset