k-means算法的简单示例.pptVIP

* * xixi * * * * * * * * * * K-means Clustering K-means Clustering K-means clustering is a sort of clustering algorithm and it is a method of vector quantization, originally from signal processing, that is popular for cluster analysis in data mining. K-means clustering aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. --From Wikipedia Algorithm Procedure Randomly select K points from complete samples as the initial center.(Thats what k means in K-means) Each point in the dataset is assigned to the closed cluster,based upon the Euclidean distance between each point and each cluster center. Each clusters center is recomputed as the average of the points in that cluster. Iterate step 2 or more until the new center of cluster equals to the original center of cluster or less than a specified threshold,then clustering finished. A B C D E F I G J H Example How to cluster A,B...H,J into two clusters? A(1,4) B(2,4) C D E F I G J H Randomly choose A,B as the centre and K=2. Example 0 1 1 1.41 2.24 3.61 4.47 5.39 4.24 5 1 0 1.41 1 2 2.83 3.61 4.47 3.61 4.24 So,we classify A,C as a cluster and B,E,D,F,G,H,I and J as another cluster. Step 1 and 2. A B C D E F G H I J means distance A→B A(1,4) B(2,4) C D E F I G J H Randomly choose A,B as the centre and K=2. Example Step 3. The new centers of the two clusters are (1,4.5) and (3.75,2.875) cluster 1 cluster 2 new center A B C D E F I G J H α(1,4.5) β(3.75,2.875) Example 0.5 1.12 0.5 1.12 1.8 3.91 4.72 5.59 4.61 5.32 2.97 2.08 3.48 2.75 3.58 0.91 1.53 2.41 1.89 2.25 Step 2 again. α , β as the centre and K=2. So,we classify A,B,C,D,E as a cluster and F,G,H,I,J as another cluster. A B C D E F G H I J A B C D E F I G J H α(1,4.5) β(3.75,2.875) Example Step 3 again. α , β as the centre and K=2. The new centers of the two clusters are P(1.6,4.8) and Q(4.8,1.6) cluster 2 cluster 1 ne