PREPARATION OF DATASET FOR MINING ANALYSIS USING CANCER DATASET

Abstract

Data preparation is very important for analysis. Incomplete data represent a challenge for achieving a successful data mining process. The data must be prepared and transformed to get the best mineable form. There are many techniques for data preparation that can be used to achieve different data-mining goals. This paper presents the detail description about the types of data, data sources, aggregate functions which are used to prepare the dataset using a new horizontal approach for data mining analysis and experiment with cancer dataset.