Chapter 24 Upsets

We could consider an upset if the winner rank is greater than the loser rank by at least 10. We plot the ranking difference between winners and losers for the grand slams.

24.1 Players causing upsets in Grand Slam Finals

We observe that the upsets are few in Grand Slams Finals. But some of them are there and lets find out what they are.

Venus Williams has created Two upsets in Grand Slam Finals.2017 saw an upset in the US Open when Sloane Stephens defeated Venus Williams in the semifinals and Madison Keys in the finals.

grandslamupsets = grandslam %>%
  filter(rankingdiff < -10) %>%
  select(winner_name,loser_name,winner_rank,loser_rank,tourney_name,year)

plotUpsets = function(upsetsData,titleName)
{
  upsetsData %>%
  group_by(winner_name) %>%
  summarise(Count = n()) %>%
  arrange(desc(Count)) %>%
  ungroup() %>%
  mutate(winner_name = reorder(winner_name,Count)) %>%
  head(10) %>%
 
  ggplot(aes(x = winner_name,y = Count)) +
  geom_bar(stat='identity',colour="white",fill=fillColor2) +
  geom_text(aes(x = winner_name, y = 1, label = paste0("(",Count,")",sep="")),
            hjust=0, vjust=.5, size = 4, colour = 'black',
            fontface = 'bold') +
  labs(x = titleName, 
       y = 'Count', 
       title = titleName) +
  coord_flip() + 
  theme_bw()
}
  
plotUpsets(grandslamupsets,'Upset Winner in Grand Slam Finals')

kable(grandslamupsets,"html") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
  scroll_box(width = "800px")

winner_name	loser_name	winner_rank	loser_rank	tourney_name	year
Jennifer Capriati	Martina Hingis	14	1	Australian Open	2001
Serena Williams	Maria Sharapova	81	2	Australian Open	2007
Venus Williams	Lindsay Davenport	16	1	Wimbledon	2005
Venus Williams	Marion Bartoli	31	19	Wimbledon	2007
Sloane Stephens	Madison Keys	83	16	US Open	2017

# kable(grandslamupsets,"html") %>%
#   kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
#   scroll_box(width = "800px")

24.2 Upsets in Grand Slam SemiFinals

Williams sisters in action again creating upsets in Grand Slam semi Finals.

grandslamSF =getGrandSlamWinners('SF')

grandslamupsets = grandslamSF %>%
  filter(rankingdiff < -10) %>%
  select(winner_name,loser_name,winner_rank,loser_rank,tourney_name,year)

plotUpsets(grandslamupsets,'Upset Winner in Grand Slam Semi Finals')

kable(grandslamupsets,"html") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
  scroll_box(width = "800px")

winner_name	loser_name	winner_rank	loser_rank	tourney_name	year
Jennifer Capriati	Lindsay Davenport	14	2	Australian Open	2001
Venus Williams	Maria Sharapova	16	2	Wimbledon	2005
Serena Williams	Nicole Vaidisova	81	12	Australian Open	2007
Marion Bartoli	Justine Henin	19	1	Wimbledon	2007
Venus Williams	Ana Ivanovic	31	6	Wimbledon	2007
Francesca Schiavone	Elena Dementieva	17	5	French Open	2010
Serena Williams	Caroline Wozniacki	27	1	US Open	2011
Sara Errani	Samantha Stosur	24	6	French Open	2012
Sabine Lisicki	Agnieszka Radwanska	24	4	Wimbledon	2013
Dominika Cibulkova	Agnieszka Radwanska	24	5	Australian Open	2014
Roberta Vinci	Serena Williams	43	1	US Open	2015
Flavia Pennetta	Simona Halep	26	2	US Open	2015
Jelena Ostapenko	Timea Bacsinszky	47	31	Roland Garros	2017
Sloane Stephens	Venus Williams	83	9	US Open	2017

24.3 Upsets in T1 tournaments

getTournamentWinners = function(tourney_level_name,roundname)
{
  return(
    matches %>%
      filter(tourney_level == tourney_level_name) %>%
      filter(round == roundname) %>%
      mutate(agediff = winner_age - loser_age) %>%
      mutate(rankingdiff = loser_rank - winner_rank)
  )
}

T1Winners = getTournamentWinners('T1','F')

T1upsets = T1Winners %>%
  filter(rankingdiff < -10) %>%
  select(winner_name,loser_name,winner_rank,loser_rank,tourney_name,year)

plotUpsets(T1upsets,'Upset Winner in T1 tournament Finals')

kable(T1upsets,"html") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
  scroll_box(width = "800px")

winner_name	loser_name	winner_rank	loser_rank	tourney_name	year
Jelena Dokic	Amelie Mauresmo	23	6	Rome	2001
Daniela Hantuchova	Martina Hingis	26	4	Indian Wells	2002
Magdalena Maleeva	Lindsay Davenport	23	8	Moscow	2002
Iva Majoli	Patty Schnyder	58	30	Charleston	2002
Alicia Molik	Maria Sharapova	20	7	Zurich	2004
Kim Clijsters	Maria Sharapova	38	3	Miami	2005
Kim Clijsters	Lindsay Davenport	133	1	Indian Wells	2005
Justine Henin	Elena Dementieva	43	5	Charleston	2005
Anna Chakvetadze	Nadia Petrova	24	5	Moscow	2006
Daniela Hantuchova	Svetlana Kuznetsova	18	4	Indian Wells	2007
Serena Williams	Justine Henin	18	1	Miami	2007
Ana Ivanovic	Svetlana Kuznetsova	16	4	Berlin	2007

24.4 Upsets in T2 tournaments

T2Winners = getTournamentWinners('T2','F')

T2upsets = T2Winners %>%
  filter(rankingdiff < -10) %>%
  select(winner_name,loser_name,winner_rank,loser_rank,tourney_name,year)

plotUpsets(T2upsets,'Upset Winner in T2 tournament Finals')

kable(T2upsets,"html") %>%
  kable_styling(bootstrap_options = c("striped", "hover", "condensed", "responsive")) %>%
  scroll_box(width = "800px")

winner_name	loser_name	winner_rank	loser_rank	tourney_name	year
Chanda Rubin	Anastasia Myskina	37	19	Eastbourne	2002
Chanda Rubin	Lindsay Davenport	21	9	Los Angeles	2002
Ai Sugiyama	Kim Clijsters	25	3	Scottsdale	2003
Elena Dementieva	Lindsay Davenport	21	5	Amelia Island	2003
Justine Henin	Svetlana Kuznetsova	22	7	Warsaw	2005
Dinara Safina	Amelie Mauresmo	48	4	Paris	2005
Maria Kirilenko	Anna Lena Groenefeld	45	30	Beijing	2005
Alona Bondarenko	Francesca Schiavone	62	14	Luxembourg	2006
Tatiana Golovin	Nadia Petrova	20	7	Amelia Island	2007
Agnes Szavay	Jelena Jankovic	23	3	Beijing	2007
Aleksandra Wozniak	Marion Bartoli	85	15	Stanford	2008
Caroline Wozniacki	Anna Chakvetadze	22	11	New Haven	2008