golf major winners

### Getting golf major winners

library(dplyr)
library("rvest")
url <- "http://en.wikipedia.org/wiki/Masters_Tournament"
masters <- url %>% html() %>% html_nodes(xpath='//*[@id="mw-content-text"]/table[4]') %>% html_table()

url1 <- "http://en.wikipedia.org/wiki/U.S._Open_(golf)"
usopen <- url1 %>% html() %>% html_nodes(xpath='//*[@id="mw-content-text"]/table[2]') %>% html_table()

url2 <- "http://en.wikipedia.org/wiki/The_Open_Championship"
theopen <- url2 %>% html() %>% html_nodes(xpath='//*[@id="mw-content-text"]/table[5]') %>% html_table()

url3 <- "http://en.wikipedia.org/wiki/PGA_Championship"
pga1 <- url3 %>% html() %>% html_nodes(xpath='//*[@id="mw-content-text"]/table[3]') %>% html_table()
pga2 <- url3 %>% html() %>% html_nodes(xpath='//*[@id="mw-content-text"]/table[4]') %>% html_table(fill=T)




#tidy up
str(masters)
masters <- masters[[1]][,1:2]
usopen <- usopen[[1]][,1:2]
theopen <- theopen[[1]][c(1,3)]
pga1 <- pga1[[1]][,1:2]
pga2 <- pga2[[1]][,1:2]

#tidyup
masters<-masters[-71,]

usopen<-usopen[-95,]
usopen<-usopen[-71,]

theopen<-theopen[-136,]
theopen<-theopen[-92,]
theopen<-theopen[-71,]
theopen<-theopen[-1,]

pga1<-pga1[-1,]

pga2<-pga2[-41,]
pga2<-pga2[-40,]
pga2<-pga2[-15,]

#add major
masters$major<-"masters"
usopen$major<-"usopen"
theopen$major<-"theopen"
pga1$major<-"pga"
pga2$major<-"pga"


golf<-list(masters, usopen, theopen, pga1, pga2)

library(dplyr)
golf <- lapply(golf, function(x) x %>% mutate(player = gsub( " *\\(.*?\\) *", "", x[,2])))

golf <- do.call("rbind", golf)

golf[,1] <- as.numeric(as.character(golf[,1]))

head(golf)

golf <- golf %>% group_by(player) %>% arrange(Year) %>% mutate(value=1, total = cumsum(value))

topgolfers <- golf %>% filter(max(total)>7) %>% .$player %>% unique()

golf$grp <- ifelse(golf$player %in% topgolfers, 1, 0)

golf1 <- golf %>% filter(grp==1) %>% ungroup()

#not graphing everyone from 0 to 1 wins.....  would need to add in zero wins into df.

library(ggplot2)
ggplot(golf, (aes(Year, total))) + 
  geom_path(aes(group=player), color="gray55", lwd=1) +
  geom_path(aes(Year, total, group=player), color="dodgerblue", lwd=2, data=golf1) +
  scale_x_continuous(breaks=seq(1860, 2020, by=20)) +
  ylab("Total Majors")+
  ggtitle("Cumulative Golf Majors by Player")+
  theme(
    plot.title = element_text(hjust=0,vjust=1, size=rel(3.3)),
    panel.background = element_blank(),
    panel.grid.major.y = element_line(color="gray65"),
    panel.grid.major.x = element_line(color="gray65"),
    panel.grid.minor = element_blank(),
    plot.background  = element_blank(),
    text = element_text(color="gray20", size=10),
    axis.text = element_text(size=rel(1.0)),
    axis.text.x = element_text(color="gray20",size=rel(2.5), angle=90, vjust=1),
    axis.text.y = element_text(color="gray20", size=rel(2.5)),
    axis.title.x = element_text(size=rel(2.5), vjust=0),
    axis.title.y = element_text(size=rel(2.5), vjust=1),
    axis.ticks.y = element_blank(),
    axis.ticks.x = element_blank(),
    legend.position = "none"
  )