K-Means Clustering: An Introduction to Unsupervised Learning, Study notes of Data Mining

Download K-Means Clustering: An Introduction to Unsupervised Learning and more Study notes Data Mining in PDF only on Docsity!

 (^) K-Means clustering is a type of unsupervised learning. The main goal of this algorithm to find groups in data and the number of groups is represented by K. It is an iterative procedure where each data point is assigned to one of the K groups based on feature similarity.

 (^) Understanding ‘K’  (^) Total number of number of clusters  (^) Either it will be given or assumed to solve. Here, K=

 (^) Understanding ‘Centroid’  (^) Centroids are some random k points to form the cluster.  (^) These points can be either the points from the dataset or any other point.  (^) So, here we have selected the above two points as k points (k=2), which are not the part of our dataset.

 (^) Understanding ‘Centroid’  (^) From the above image, it is clear that points left side of the line is near to the K1 or blue centroid, and points to the right of the line are close to the yellow centroid. Let's colour them as blue and yellow for clear visualization.

 (^) Understanding ‘Centroid Update’  (^) As we need to find the closest cluster, so we will repeat the process by choosing a new centroid.  (^) To choose the new centroids, we will compute the canter of gravity of these centroids, and will find new centroids as above:

Applying K-Means Clustering for the following dataset: Suppose, K= So, 1 st Centroid = C1(2,4) 2 nd Centroid = C2(5,2) Given dataset, A(2,4), B(2,3), C(5,2), D(6,2), E(5,2.5), F(2.5,3.5)

. A(2,4) D1==0 D2= =3. C1(2,4) C2(5,2)

. A(2,4) C1(2,4) C2(5,2) As, D1<D2, So A(2,4) will be assigned to C1 Centroid

. A(2,4) B(2,3) D1==1.4 D2= =3. C1(2,4) C2(5,2)

. A(2,4) B(2,3) C1(2,3.5) C2(5,2)

A(2,4) B(2,3) C1(2,3.5) C2(5,2)