![]() 'GK positioning', 'GK reflexes', 'Heading accuracy', 'Interceptions', 'Free kick accuracy', 'GK diving', 'GK handling', 'GK kicking', 'Composure', 'Crossing', 'Curve', 'Dribbling', 'Finishing', 'Acceleration', 'Aggression', 'Agility', 'Balance', 'Ball control', 'Potential', 'Club', 'Club Logo', 'Value', 'Wage', 'Special', columns Index([ 'ID', 'Photo', 'Name', 'Age', 'Nationality', 'Flag', 'Overall', These attributes are optimal indicators to determine the performance of a player at a particular playing position.ĭata. The FIFA 18 dataset that has been used for this analysis provides statistics of about 16000 players on over 70 different attributes. Thus, all of those are gathered and curated by the company whose job is to bring the gameplay closer to reality as possible, hence preserving coherence and representativeness across the dataset. Observe that it seems to be unfeasible to accurately characterize players in these attributes automatically. Examples of attributes are: dribbling, aggression, vision, marking and ball control. Since 1995 the FIFA Soccer games provide an extensive and coherent scout of players worldwide.įor each attribute, we have an integer from 0 to 100 that measures how good a player is at that attribute. Through several research projects done on soccer analytics, it has been established in the field of academia that the use of data from the FIFA franchise has several merits that traditional datasets based on historical data do not offer. ![]() data developed by Electronic Arts for the latest edition of their FIFA game franchise. The website contains the data from the EA Sports' game FIFA and gets updated regularly with the release of new versions of the game. The data was scrapped from the sofifa website using a python crawling script.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |