Abstract Views :107 |
PDF Views:0
Authors
Affiliations
1 K.K.W.I.E.E.R, Nashik, University of Pune, Pune, Maharashtra, IN
Source
International Journal of Engineering Research, Vol 3, No 7 (2014), Pagination: 446-448
Abstract
Data aggregation is a process in which information is gathered and expressed in a summary form, and which is used for purposes such as statistical analysis. A common aggregation purpose is to get more information about particular groups based on specific variables such as age, name, phone number, address, profession, or income. Most data mining algorithms takes as input data set with a horizontal layout. Significant effort is required to prepare summary data set in a relational database with normalized tables. For preparing data sets suitable for data mining analysis, we have to write complex SQL queries, operation of joining tables and column aggregation. Horizontal aggregation can be performing by using operator, it can easily be implemented inside a query processor, much like a select, project and join. PIVOT operator on tabular data that exchange rows, enable data transformations useful in data modeling, data analysis, and data presentation. Two main ingredients in SQL code are joins and aggregations Standard aggregation returns one column per aggregated group and produce table with a vertical layout and Standard aggregations are hard to interpret when grouping attributes have high cardinalities. All these are limitations of standard aggregation. Because of these limitations, standard aggregation is not much suitable for preparation of data set for data mining analysis. Horizontal aggregation is a simple method which generates SQL code to return aggregated columns in a horizontal tabular layout and returns set of numbers instead of one number per row. This project is useful for building a suitable dataset for data mining analysis using horizontal aggregations in SQL. Two fundamental methods are used to evaluate horizontal aggregations: SPJ and Left Outer Join. This project will evaluate horizontal aggregation using Left outer join method.
Keywords
Data Mining, Data Set, Horizontal Aggregation, Left Outer Join, SPJ, Standard Aggregation.
Full Text