Data Cleaning and Transformation
This project has been designed to demonstrate the skills and technologies required to undertake high level data cleaning of a raw dataset.
EA Sports FIFA 21 Data Cleaning and Transformation
About this dataset
FIFA 21 is an association football simulation video game published by Electronic Arts as part of the FIFA series. It is the 28th installment in the FIFA series, and was released on 9 October 2020 for Microsoft Windows, Nintendo Switch, PlayStation 4 and Xbox One.
Measures
- Removal of images, links.
- Standardise metric values for height and weight.
- Refine contract type with dates
- Resolve string instances in 'Hits' column.
About the Data
The dataset contains information about 18,979 football players and 77 columns of the players statistics and demography in 2021. The columns include the players Unique-ID, Name, Age, Nationality, Position, Overall Rating, Wage, Contract and so on.
Conclusions
The data was webscarped and thus contained many with web elements that were required to be removed. There was also a great deal of inconsistency in columns that measured attributes and contract type/dates. The cleaned and transformed dataset will lead to a significantly more accurate analysis.