Data Science With Excel

Abstract

The stages in data science consist of several stages, one of which is data preparation. At this stage, many things are done so that the dirty data becomes clean data that is ready for modeling. Many applications offer data science convenience in terms of processing data. One of them is excel, this application from Microsoft can perform data processing so that the data is ready for modeling. However, there are limitations in using excel. The maximum number of rows that excel has is only 1,048,576 and the number of columns is 16,384. However, if you process data of no more than 1 million rows, excel can still handle it by using features such as error detection, removing duplicate data, correcting error values, detecting outlier values, handling missing data and validating data. This study shows some of these features along with examples of their use.