RIO_medale.R

# Pobierz dane

library("XML")
url <- "https://pl.wikipedia.org/wiki/Lista_pa%C5%84stw_%C5%9Bwiata_wed%C5%82ug_liczby_ludno%C5%9Bci"
file<-read_html(url)
tables <-html_nodes(file, "table")

table1 <- html_table(tables[1], fill = TRUE)
table1 <- table1[[1]]
table1 <- table1[table1[,1] != "–",]
table1 <- table1[-1,c(1,2,8)]
table1[1,2] = "Chiny"
table1[3,2] = "USA"
colnames(table1) <- c("Lp","CNT", "population")
table1[,3] <- as.numeric(gsub(table1[,3], pattern="[^0-9]", replacement=""))

url <- "http://sportowefakty.wp.pl/rio-2016/klasyfikacja-medalowa"
file<-read_html(url)
tables<-html_nodes(file, "table")
table2 <- html_table(tables[1], fill = TRUE)
table2 <- table2[[1]]
colnames(table2)[1:2] = c("Lp.RIO","CNT")

table_merged <- merge(table1, table2)

# Rysuj

library(rbokeh)

selected = table_merged[,c("Suma", "population", "CNT")]
selected[,2] <- round(selected[,2]/10^6,3)
colnames(selected) <- c("Medali", "Populacja", "Kraj")
selected$czy_Polska <- factor(selected$Kraj == "Polska")

figure(width = 660, height = 660, title="Populacja a liczba medali w RIO 2016") %>%
  ly_points(x=Populacja, y=Medali, hover = selected, data=selected, color=czy_Polska, legend=FALSE)%>%
  x_axis(log = TRUE, label="Populacja w milionach", use_scientific=FALSE) %>%
  y_axis(log=TRUE, label="Sumaryczna liczba medali")