A Study of Effectiveness of Principal Component Analysis on Different Data Sets

Principal Component Analysis (PCA) is a process of converting a set of objects of correlated features to set of values of linearly uncorrelated variables called Principal Components (PC). The first PC has for highest variability in data, the second PC accounts for next has variability and so on. Over the years PC is used to discover or to reduce the number of features of the data set and to identify new meaningful underlying features. In this paper we have taken 24 benchmark data sets from the University of California, Irvine (UCI) Machine Learning Repository and KEEL data set repository. In the result section we have shown how much information is retained by individual PC to show the effectiveness of PCA.