The proportionate increase in the size of the data with increase in space implies that clustering a very large data set becomes difficult and is a time consuming process. Sampling is one important technique to scale down the size of dataset and to improve the efficiency of clustering. After sampling, allocating unlabeled data point into proper cluster is difficult in the categorical domain and in real situations data changes over time. However, clustering this type of data not only decreases the quality of clusters and also disregards the expectation of users, who usually require recent clustering results. In both the cases mentioned above, one is of allocating unlabeled data point into proper clusters after the sampling and the other is of finding clustering results when data changes over time which is difficult in the categorical domain. In this paper, using node importance technique, a rough set based method proposed to label unlabeled data point and to find the next clustering result based on the previous clustering result.