东北大学数据挖掘第7章.ppt

k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose center is the nearest to the object Step3: compute the new mean for each cluster Step4: if there is no change, exit. Otherwise go to Step2 k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose center is the nearest to the object Step3: compute the new mean for each cluster Step4: if there is no change, exit. Otherwise go to Step2 k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose center is the nearest to the object Step3: compute the new mean for each cluster Step4: if there is no change, exit. Otherwise go to Step2 k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose center is the nearest to the object Step3: compute the new mean for each cluster Step4: if there is no change, exit. Otherwise go to Step2 k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose center is the nearest to the object Step3: compute the new mean for each cluster Step4: if there is no change, exit. Otherwise go to Step2 k-Means method each cluster is represented by the mean value of the data in the cluster Step1: randomly select k objects as the centers of the clusters Step2: for each remaining object, assign it to the cluster whose c