Cancer classification is very important in the field of bioinformatics for cancer diagnosis and drug discovery. There are two problems that have been examined in bioinformatics for cancer classification i.e. class discovery and class prediction. Accurate prediction of different type of cancer is very important for providing better treatment and for avoiding the additional cost associated with wrong therapy. Large numbers of methods have been proposed in recent years for classifying the cancer but still lot of problems exist which need to be addressed. In this survey paper, we present various cancer classification methods such as SVM, KNN, Naïvebayes as well role of feature extraction method for classifying gene expression data.