https://r4ds.had.co.nz/
reisijad=read_csv("http://www.tlu.ee/~jaagup/andmed/muu/estonia_reisijad.txt")
select(reisijad, Country, Sex)
colnames(reisijad)
select(reisijad, Firstname:Age)
select(reisijad, -(Firstname:Age))
select(reisijad, starts_with("C"))
select(reisijad, ends_with("name"))
select(reisijad, contains("a"))
select(reisijad, matches("t[aeiou]"))
select(reisijad, matches("[aeiou]$"))
select(reisijad, matches("[aeiou]$"), everything())
library(nycflights13)
flights
colnames(flights)
select(flights, contains("dep"), contains("arr"), -contains("sched"))
select(flights, dep_time, dep_time)
transmute(flights, paev=paste(year,month, day, sep = "-"), origin)
reisijad %>% arrange(desc(Age)) %>% 
  transmute(keskvanus=cummean(Age), Age, 
            vahe=Age-.$Age[row_number()+1],
            vahevanimaga=max(Age)-Age)
# Kuvage juurde vahe vanimaga

reisijad %>% group_by(Country) %>% summarise(kesk=mean(Age))
reisijad %>% group_by(Country) %>% 
  summarise(kesk=mean(Age), nkesk=mean(Age[Sex=='F']))

# Ridadeks on sood
# Tulpadeks on Estonia, Finland ja Sweden
# Lahtrite väärtusteks on keskmised vanused

reisijad %>% group_by(Sex) %>% 
  summarise(ekesk=mean(Age[Country=='Estonia']), 
            rkesk=mean(Age[Country=='Sweden']))

reisijad %>% filter(Country %in% c("Estonia", "Sweden")) %>% 
  group_by(Country, Sex) %>% 
  summarise(kesk=mean(Age)) %>%
  spread(Country, kesk)

reisijad %>% group_by(Country) %>% filter(n()>10) %>% ungroup()

reisijad %>% group_by(Country) %>% filter(n()>10) %>% 
  group_by(Country, Sex) %>%   summarise(kesk=mean(Age)) %>%
  spread(Country, kesk)


reisijad %>% group_by(Country) %>% filter(n()>2) %>%
  arrange(desc(Age)) %>% mutate(nr=row_number()) %>%
  filter(nr<=3) %>% select(Country, Age, nr) %>%
  spread(Country, Age)


reisijad %>% group_by(Country) %>%
  filter(Survived==1) %>%
  filter(n()>2) %>%
  arrange(Age) %>% mutate(nr=row_number()) %>%
  filter(nr<=3) %>% select(Country, Age, nr) %>%
  spread(Country, Age)

reisijad %>% group_by(Country) %>%
  filter(Survived==1) %>%
  filter(n()>2) %>%
  arrange(Age) %>% mutate(nr=row_number()) %>%
  filter(nr<=3) %>% select(Country, Age, nr) %>%
  spread(Country, Age) %>% write_csv("e:/jaagup/nooremad.csv")

nooremad=read_csv("e:/jaagup/nooremad.csv")
nooremad

isikud=tibble(eesnimi=c("Juku", "Kati", "Mati"))
isikud=tibble(eesnimi=c("Juku", "Kati", "Mati"), klass=6)
isikud=tibble(eesnimi=c("Juku", "Kati", "Mati"), klass=6, 
              tutvustus=paste(eesnimi, klass, "klassist"))

isikud=tibble(eesnimi=c("Juku", "Kati", "Mati", "Madis"),
              pikkus=runif(length(eesnimi), 150, 170))
isikud

sots1=read_delim("http://www.tlu.ee/~jaagup/andmed/sots/ess08_e_1.txt", ";")
isikud=tibble(tunnus=c("juku-kalle/m", "kati/n", "madis/m"), 
              vanus=c("12 aastat", "ei tea", "sai just 13"))
isikud
isikud %>% separate(tunnus, c("eesnimi", "sugu"), sep="/") %>%
   extract(vanus, "arvuna", "([0-9]+)", remove=FALSE) %>%
   unite(kood, sugu, arvuna,remove = FALSE)