Horizontal Aggregation in SQL to Prepare Datasets and Decision Tree

Data mining is similar to discovering an innovative idea. When data are structured under RDBMs it will be very critical task to make it out. Many data mining concepts and algorithms are used to create prepared datasets in tabular format which consist complex queries, joining tables in data mining. Tabular format take proper input to prepare data sets but existing SQL aggregations having limited capacity to prepare data sets and it is very time consuming task. They return one column per aggregated group. Hence fundamental methods are used to determine horizontal aggregation to signify an outline made by SQL code to return in a horizontal tabular format by using SPJ, CASE and PIVOT methods. This group of new function is called as horizontal aggregation. Aim of this work is to present classification on prepared datasets and further, generating the decision tree by using C4.5 algorithm to reduce the time constraints. Proposed work might be useful for the programmers to interpret the knowledge in the form of decision tree.