Problem #3 130 points! : Decision Tree Suppose we have a set of data of tennis matches between Serena Williams and different opponents who were once No.1 in WTA single ranking. The matches selected are all Grand Slam tournament finals. Result Year Tournament Surface Opponents Hard Venus Williams Win 2000-2005 French Open Clay Venus Williams VenusWilliams Hard Venus Williams Win 2000-2005 Australian Open Hard Venus Williams VenusWilliams 000-2005 US Open Win 2000-2005 Wimbledon Grass Win 2000-2005 US Open Win 2000-2005 Wimbledon Grass 000-2005 Wimbledon Grass Maria Sharapova Win 20002005 Australian Open HardLindsay Davenport Win 2005-2010 Australian Open Hard Maria Sharapova 2005 2010 Wimbledon rass Venus Williams Hard Jelena Jankovi Win 2005 2010 US Open Win 2005 2010 Australian Open Hard Dinara Safina Win 2005-2010 Wimbledon rass Venus Williams Win 2005 2010 Australian Open HardJustine Henin Win 2010-2015 US Open Win 2010-2015 French Open Clay Maria Sharapova Win 2010-2015 US Open Win 2010-2015 US Open Win 2010-2015 Australian Open Hard Maria Sharapova Win 2010-2015 Wimbledon Grass Hard Victoria Azarenka Hard Victoria Azarenka Hard Caroline Wozniacki 016-2020 Australian Open Hard 016 2020 French Open Clay Garbine Muguruza Angelique Kerber Garbine Muguruza Win 2016-2020 Wimbledn Grass Angelique Kerber Win 2016-2020Australian Open Hard Venus Williams 016 2020 Wimbled Grass Angelique Kerber Try to build a decision tree based on the train data set, with leaves the outcome of matches. You can do this step by step (a) [10 pts] Which attribute is the best option for root? And which attribute is the worst? Give an explanation. (b) [10 pts] How do you split each branch when the root is settled? When will the splitting stop? (c) [10 pts] Draw the final tree. Based on the tree, answer the following questions: o Suppose Serena is a finalist in Australian Open 2019, facing Angelique Kerber, will she win? o Out of the four Grand Slams (Australian Open/French Open /Wimbledon/US Open) in 2019 which one(s) do you think Serena can probably win if she enters the finals? Problem #3 130 points! : Decision Tree Suppose we have a set of data of tennis matches between Serena Williams and different opponents who were once No.1 in WTA single ranking. The matches selected are all Grand Slam tournament finals. Result Year Tournament Surface Opponents Hard Venus Williams Win 2000-2005 French Open Clay Venus Williams VenusWilliams Hard Venus Williams Win 2000-2005 Australian Open Hard Venus Williams VenusWilliams 000-2005 US Open Win 2000-2005 Wimbledon Grass Win 2000-2005 US Open Win 2000-2005 Wimbledon Grass 000-2005 Wimbledon Grass Maria Sharapova Win 20002005 Australian Open HardLindsay Davenport Win 2005-2010 Australian Open Hard Maria Sharapova 2005 2010 Wimbledon rass Venus Williams Hard Jelena Jankovi Win 2005 2010 US Open Win 2005 2010 Australian Open Hard Dinara Safina Win 2005-2010 Wimbledon rass Venus Williams Win 2005 2010 Australian Open HardJustine Henin Win 2010-2015 US Open Win 2010-2015 French Open Clay Maria Sharapova Win 2010-2015 US Open Win 2010-2015 US Open Win 2010-2015 Australian Open Hard Maria Sharapova Win 2010-2015 Wimbledon Grass Hard Victoria Azarenka Hard Victoria Azarenka Hard Caroline Wozniacki 016-2020 Australian Open Hard 016 2020 French Open Clay Garbine Muguruza Angelique Kerber Garbine Muguruza Win 2016-2020 Wimbledn Grass Angelique Kerber Win 2016-2020Australian Open Hard Venus Williams 016 2020 Wimbled Grass Angelique Kerber Try to build a decision tree based on the train data set, with leaves the outcome of matches. You can do this step by step (a) [10 pts] Which attribute is the best option for root? And which attribute is the worst? Give an explanation. (b) [10 pts] How do you split each branch when the root is settled? When will the splitting stop? (c) [10 pts] Draw the final tree. Based on the tree, answer the following questions: o Suppose Serena is a finalist in Australian Open 2019, facing Angelique Kerber, will she win? o Out of the four Grand Slams (Australian Open/French Open /Wimbledon/US Open) in 2019 which one(s) do you think Serena can probably win if she enters the finals
