{ "data_id": "43833", "name": "Official-World-Golf-Ranking-Data", "exact_name": "Official-World-Golf-Ranking-Data", "version": 1, "version_label": "v1.0", "description": "Official World Golf Ranking Data\n\nContext:\nThe Official World Golf Ranking is a system for rating the performance level of male professional golfers. It was started in 1986. [1]\nThe rankings are based on a player's position in individual tournaments (i.e. not pairs or team events) over a \"rolling\" two-year period. New rankings are produced each week. During 2018, nearly 400 tournaments on 20 tours were covered by the ranking system. All players competing in these tournaments are included in the rankings. In 2019, 23 tours will factor into the world rankings. [1]\nThe World Ranking Points for each player are accumulated over a two year rolling period with the points awarded for each tournament maintained for a 13-week period to place additional emphasis on recent performances. [2]\nRanking points are then reduced in equal decrements for the remaining 91 weeks of the two year Ranking period. Each player is then ranked according to his average points per tournament, which is determined by dividing his total number of points by the tournaments he has played over that two-year period. [2]\nThere is a minimum divisor of 40 tournaments over the two year ranking period and a maximum divisor of a players last 52 tournaments. [2]\nSimply put, a golfer's World Ranking is obtained by dividing their points total by the number of events they have played, which gives their average. Players are then ranked; a higher average yields a higher rank. [1]\n\nData:\n\nThe data was acquired from the Official World Golf Ranking website.\nStored in a long data format.\nThis file will be updated weekly after the conclusion of every tournament.\n\n\nTours Included in the Rankings:\n\nPGA Tour\nEuropean Tour\nAsian Tour (not a charter member of the Federation)\nPGA Tour of Australasia\nJapan Golf Tour\nSunshine Tour\nKorn Ferry Tour\nChallenge Tour\nPGA Tour Canada\nGolf Tour\nKorean Tour\nPGA Tour Latinoamrica\nAsian Development Tour\nPGA Tour China\nAlps Tour\nNordic Golf League\nPGA EuroPro Tour\nProGolf Tour\nMENA Golf Tour\nBig Easy Tour\nChina Tour\nAll Thailand Golf Tour\nProfessional Golf Tour of India\nAbema TV Tour\n\n\nCollection Method:\n\nAcquired the data using the Python library BeautifulSoup. Manipulated data using the Pandas NumPy libraries.\n\n\nContents:\n\n9000 players\n\n\nAcknowledgements:\n\nData scraped from: Official World Golf Ranking\nPlease formally reference this Kaggle dataset.\nPlease contribute analysis and findings as a kernel.\n\n\nInspirations:\n\nCan this dataset be used to predict who will win upcoming PGA Tour tournaments?\nCan we predict the players that will make the tournament cuts?\n\n\nDisclaimer:\nThe Official World Golf Ranking website contains plenty of messy data in the 'Name' column. There are still records where there is not enough information for me to infer the proper name of the athlete. If the name contains a date within brackets it is because there are two players with the same name. The date is the birth date of the athlete and is used to uniquely identify athletes with the same name.\n\nQuestions, Concerns Suggestions:\n\nFeel free to email me for questions, concerns or suggestions, bradklassenoutlook.com\n\n\nResources\n[1] https:\/\/en.wikipedia.org\/wiki\/Official_World_Golf_Ranking\n[2] http:\/\/www.owgr.com\/about", "format": "arff", "uploader": "Elif Ceren Gok", "uploader_id": 30125, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 15:31:54", "update_comment": null, "last_update": "2022-03-24 15:31:54", "licence": "CC BY-NC-SA 4.0", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102658\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Official-World-Golf-Ranking-Data", "Official World Golf Ranking Data Context: The Official World Golf Ranking is a system for rating the performance level of male professional golfers. It was started in 1986. [1] The rankings are based on a player's position in individual tournaments (i.e. not pairs or team events) over a \"rolling\" two-year period. New rankings are produced each week. During 2018, nearly 400 tournaments on 20 tours were covered by the ranking system. All players competing in these tournaments are included in the r " ], "weight": 5 }, "qualities": { "NumberOfInstances": 9000, "NumberOfFeatures": 12, "NumberOfClasses": null, "NumberOfMissingValues": 29318, "NumberOfInstancesWithMissingValues": 8394, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.0013333333333333333, "PercentageOfNumericFeatures": 83.33333333333334, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 93.26666666666667, "AutoCorrelation": null, "PercentageOfMissingValues": 27.146296296296295 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "Week", "index": "0", "type": "numeric", "distinct": "1", "missing": "0", "min": "11", "max": "11", "mean": "11", "stdev": "0" }, { "name": "This_Week", "index": "1", "type": "numeric", "distinct": "1529", "missing": "0", "min": "1", "max": "2089", "mean": "1847", "stdev": "528" }, { "name": "Last_Week", "index": "2", "type": "numeric", "distinct": "1520", "missing": "5", "min": "1", "max": "2087", "mean": "1845", "stdev": "527" }, { "name": "End_2019", "index": "3", "type": "numeric", "distinct": "1541", "missing": "206", "min": "1", "max": "2074", "mean": "1829", "stdev": "527" }, { "name": "Name", "index": "4", "type": "string", "distinct": "8998", "missing": "0" }, { "name": "Average_Points", "index": "5", "type": "numeric", "distinct": "1528", "missing": "6912", "min": "0", "max": "9", "mean": "0", "stdev": "1" }, { "name": "Total_Points", "index": "6", "type": "numeric", "distinct": "1231", "missing": "6912", "min": "0", "max": "444", "mean": "16", "stdev": "36" }, { "name": "Events_Played_Divisor", "index": "7", "type": "numeric", "distinct": "13", "missing": "0", "min": "40", "max": "52", "mean": "41", "stdev": "2" }, { "name": "Points_Lost_2020", "index": "8", "type": "numeric", "distinct": "668", "missing": "6932", "min": "-89", "max": "0", "mean": "-3", "stdev": "7" }, { "name": "Points_Gained_2020", "index": "9", "type": "numeric", "distinct": "390", "missing": "8351", "min": "1", "max": "111", "mean": "9", "stdev": "14" }, { "name": "Events_Played_Actual", "index": "10", "type": "numeric", "distinct": "67", "missing": "0", "min": "1", "max": "72", "mean": "12", "stdev": "15" }, { "name": "Pro\/Am", "index": "11", "type": "string", "distinct": "2", "missing": "0" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }