c(42, 99, 43)

matrix(1:12, nrow=3,ncol=4)

list(
  n_lectures = 12,
  l_topics = c("begining", "data manipulation", "descriptive stats"),
  h_topics = c("data manipulations", "descriptive stats")
  )

data.frame(
  names = c("Olya", "Ilya", "Sasha", "George"),
  lecturer = c(TRUE, TRUE, FALSE, TRUE),
  lecturer_experience = c(19, 6, 0, 3)
  )

nrow(iris) # returns the number of rows

ncol(mtcars) #  returns the number of columns

head(cars) # returns the first 6 rows

head(cars, 4) # returns the first 4 rows

tail(cars) # returns the last 6 rows

summary(cars)  # produce some stats

str(cars)  # shows the structure: variables, their type

#View(cars)

mtcars$mpg # shows the mpg vector

mtcars[3,7] # shows the 3. row, 7. column

mtcars[3,] # shows the 3. row

mtcars[,7] # shows the 7. column

mtcars[mtcars$mpg < 20, ] # show all rows with the mpg value lower then 20

# ?mtcars

library(tidyverse)

packageVersion("tidyverse")

packageVersion("dplyr")

packageVersion("ggplot2")

my_data_1 <- mtcars[5:20,] # select a subset of mtcars
my_data_2 <- mtcars[17:29,] # select a subset of mtcars
combine_rows <- rbind.data.frame(my_data_1, my_data_2)
nrow(my_data_1); nrow(my_data_2); nrow(combine_rows)

my_data_3 <- mtcars[,3:7] # select a subset of mtcars
my_data_4 <- mtcars[,6:11] # select a subset of mtcars
combine_cols <- cbind.data.frame(my_data_3, my_data_4)
ncol(my_data_3); ncol(my_data_4); ncol(combine_cols)

languages <- data.frame(
  languages = c("Selkup", "French", "Chukchi", "Kashubian"),
  countries = c("Russia", "France", "Russia", "Poland"),
  iso = c("sel", "fra", "ckt", "pol")
  )
languages

country_population <- data.frame(
  countries = c("Russia", "Poland", "Finland"),
  population_mln = c(143, 38, 5))
country_population

inner_join(languages, country_population)

left_join(languages, country_population)

right_join(languages, country_population)

anti_join(languages, country_population)

anti_join(country_population, languages)

full_join(country_population, languages)

homo <- read.csv("http://goo.gl/Zjr9aF")
homo

library(tidyverse)
homo <- tbl_df(homo)
homo

homo[homo$age > 28,]

homo %>%
  filter(age > 28, s.duration.ms < 60)

sort(sqrt(abs(sin(1:22))), decreasing = TRUE)

1:22 %>% 
  sin() %>% 
  abs() %>% 
  sqrt() %>% 
  sort(., decreasing = TRUE) # dot here shows where should argument be

homo[3:7, ]

homo %>%
  slice(3:7)

homo[, 8:10]

homo %>%
  select(8:10)

homo %>%
  select(speaker:average.f0.Hz)

homo %>%
  select(-c(speaker, perceived.as.hetero, perceived.as.homo, perceived.as.homo.percent))

# When you want to remove one column you can write it without 
# c() function, e. g. -speaker

homo %>%
  select(speaker, age, s.duration.ms)

homo[order(homo$orientation, homo$age), ]

homo %>%
  arrange(orientation, desc(age))

unique(homo$orientation)

homo %>%
  distinct(orientation, age > 20)

unique(homo[c("orientation", "perceived.as.homo")])

homo %>%
  distinct(orientation, perceived.as.homo)

homo$f0.min <- homo$average.f0.Hz - homo$f0.range.Hz/2
homo$f0.min

homo$f0.max <- homo$average.f0.Hz + homo$f0.range.Hz/2
homo$f0.max

homo %>%
  mutate( f0.mn = average.f0.Hz - f0.range.Hz/2,
          f0.mx = (average.f0.Hz + f0.range.Hz/2)) -> 
  homo
homo  

homo %>%
  summarise(min(age), mean(s.duration.ms))

homo %>%
  group_by(orientation) %>% 
  summarise(my_mean = mean(s.duration.ms))

homo %>%
  group_by(orientation) %>% 
  summarise(mean(s.duration.ms))

homo %>%
  group_by(orientation) %>% 
  summarise(mean_by_orientation = mean(s.duration.ms))

df.short <- data.frame(
                   consonant = c("stops", "fricatives", "affricates", "nasals"),
                   initial = c(123, 87, 73, 7),
                   intervocal = c(57, 77, 82, 78),
                   final = c(30, 69, 12, 104))
df.short

df.short <- data.frame(
                   consonant = c("stops", "fricatives", "affricates", "nasals"),
                   initial = c(123, 87, 73, 7),
                   intervocal = c(57, 77, 82, 78),
                   final = c(30, 69, 12, 104))
df.short

df.short %>% 
  gather(position, number, initial:final) ->
  df.long
df.long

df.long %>% 
  spread(position, number) ->
  df.short
df.short

quartet <- read.csv("https://goo.gl/KuuzYy")
quartet

quartet %>% 
  group_by(dataset) %>% 
  summarise(mean_X = mean(x),
            mean_Y = mean(y),
            sd_X = sd(x),
            sd_Y = sd(y),
            cor = cor(x, y),
            n_obs = n()) %>% 
  select(-dataset) %>% 
  round(., 2)

datasaurus <- read_tsv("https://goo.gl/gtaunr")
head(datasaurus)

datasaurus %>% 
  group_by(dataset) %>% 
  summarise(mean_X = mean(x),
            mean_Y = mean(y),
            sd_X = sd(x),
            sd_Y = sd(y),
            cor = cor(x, y),
            n_obs = n()) %>% 
  select(-dataset) %>% 
  round(., 1)

plot(homo$s.duration.ms, homo$vowel.duration.ms)

ggplot(data = homo, aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()

homo %>%
  ggplot(aes(average.f0.Hz, age))+
  geom_smooth(method = "lm")+
  geom_point(aes(color = orientation))

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     col = c("red", "blue")[homo$orientation])

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             color = orientation)) +
  geom_point()

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     pch = c(16, 17)[homo$orientation])

plot(1:25, pch = 1:25)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             shape = orientation)) +
  geom_point(color = "green")

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     cex = homo$age/20)

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     cex = homo$age)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms,
             size = age)) +
  geom_point()

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     pch = c("⚤", "⚣")[homo$orientation])

levels(homo$orientation) <- c("⚣", "⚤")
homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms, label = orientation, fill = orientation)) +
  geom_label()

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     main = "length of [s] vs. length of vowels")

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  labs(title = "length of [s] vs. length of vowels",
       subtitle = "based on 14 speakers of Cantonese",
       caption = "data from [Chi kuk 2007]")

plot(homo$s.duration.ms, homo$vowel.duration.ms,
     xlab = "duration of [s] in ms", ylab = "vowel duration in ms")

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  xlab("duration of [s] in ms")+
  ylab("vowel duration in ms")

freq <- read.csv("https://goo.gl/TlX7xW", sep = "\t")
freq %>%
  arrange(desc(Freq.ipm.)) %>% 
  slice(1:200) %>% 
  ggplot(aes(Rank, Freq.ipm.)) +
  geom_point() +
  xlab("") +
  ylab("ipm")

plot(1:52138, freq$Freq.ipm.,
  xlab = NA, ylab = "ipm",
  las = 1,
  log = "yx")

freq %>%
  ggplot(aes(1:52138, Freq.ipm.))+
  geom_point()+
  xlab("")+
  ylab("ipm")+
  scale_y_log10()

plot(homo$s.duration.ms, homo$vowel.duration.ms)
rug(homo$s.duration.ms)
rug(homo$vowel.duration.ms, side = 2)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms, color = orientation)) +
  geom_point() +
  geom_rug()

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms, color = orientation)) +
  geom_point() +
  geom_rug()

plot(homo$s.duration.ms, homo$vowel.duration.ms)
abline(h = 120, v = 60)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = mean(homo$vowel.duration.ms))+
  geom_vline(xintercept = 60)

plot(homo$s.duration.ms, homo$vowel.duration.ms)
abline(h = 120, lty = 2)
abline(v = 60, lwd = 42)

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = 120, linetype = 2)+
  geom_vline(xintercept = 60, size = 5)

plot(homo$s.duration.ms, homo$vowel.duration.ms)
abline(h = 120, lty = 4)
abline(v = 60, col = "blue")

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point() +
  geom_hline(yintercept = 120, linetype = 4)+
  geom_vline(xintercept = 60, color = "blue")

homo %>%
  ggplot(aes(s.duration.ms, vowel.duration.ms)) +
  geom_point()+
  annotate(geom = "rect", xmin = 77, xmax = 79,
             ymin = 117, ymax = 122, fill = "red", alpha = 0.2) + 
  annotate(geom = "text", x = 78, y = 125,
             label = "Who is that?\n Outlier?")

head(homo[, c(1, 9)])

head(homo[, c(1, 10)])

barplot(table(homo$orientation))

homo %>%
  ggplot(aes(orientation)) +
  geom_bar()

barplot(homo$age, names.arg = homo$speaker)

homo %>%
  ggplot(aes(speaker, age)) +
  geom_bar(stat = "identity")

barplot(homo$age, names.arg = homo$speaker,
  col = homo$orientation)

homo %>%
  ggplot(aes(speaker, age, fill = orientation)) +
  geom_bar(stat = "identity")

boxplot(homo$s.duration.ms~homo$orientation)

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot()

boxplot(homo$s.duration.ms~homo$orientation)
stripchart(homo$s.duration.ms ~ homo$orientation,
  pch = 1, vertical = T, add = T)

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot()+
  geom_point()

boxplot(homo$s.duration.ms~homo$orientation)
stripchart(homo$s.duration.ms~homo$orientation,
  pch = 1, vertical = T, add = T, method = "jitter")

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_boxplot() +
  geom_jitter(width = 0.5)

homo %>%
  ggplot(aes(orientation, s.duration.ms)) +
  geom_violin() +
  geom_jitter()

mtcars %>% 
  mutate(newvar = mpg > 22,
         newvr = mpg < 17) %>% 
  ggplot(aes(newvr, newvar, color = newvar))+
  geom_jitter(width = 0.2)

mtcars %>% 
  mutate(newvar = mpg > 22,
         newvr = mpg < 17) %>% 
  group_by(newvar, newvr) %>% 
  summarise(number = n()) %>% 
  ggplot(aes(newvr, newvar, label = number))+
  geom_point(aes(size = number, color = newvar))+
  geom_text()+
  scale_size(range = c(10, 30))+
  guides(size = F)

hist(homo$s.duration.ms)

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram()

hist(homo$s.duration.ms,
     breaks = nclass.FD(homo$s.duration.ms))

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram(bins = nclass.FD(homo$s.duration.ms))

hist(homo$s.duration.ms, col = "lightblue")

homo %>%
  ggplot(aes(s.duration.ms)) +
  geom_histogram(fill = "lightblue")

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation)

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation, scales = "free")

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(~orientation, scales = "free_x")

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_wrap(older_then_28~orientation, scales = "free_x")

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_grid(older_then_28~orientation, scales = "free_x")

homo %>% 
  mutate(older_then_28 = ifelse(age > 28, "older", "younger")) %>% 
  ggplot(aes(speaker, s.duration.ms))+
  geom_point() + 
  facet_grid(older_then_28~orientation, scales = "free_x", margins = TRUE)

homo %>% 
  ggplot(aes(speaker, s.duration.ms))+
  # Add an additional geom without facetization variable!
  geom_point(data = homo[,-9], aes(speaker, s.duration.ms), color = "grey") + 
  geom_point() + 
  facet_wrap(~orientation)