## ----child = "../setup.Rmd"------------------------------------

## ----setup, include=FALSE--------------------------------------
# R options
options(
  htmltools.dir.version = FALSE,
  dplyr.print_min = 6, 
  dplyr.print_max = 6,
  tibble.width = 65,
  width = 65
  )
# figure height, width, dpi
knitr::opts_chunk$set(echo = TRUE, 
                      fig.width = 8, 
                      fig.asp = 0.618,
                      out.width = "60%",
                      fig.align = "center",
                      dpi = 300,
                      message = FALSE)
# ggplot2
ggplot2::theme_set(ggplot2::theme_gray(base_size = 16))
# set seed
set.seed(1234)
# fontawesome
htmltools::tagList(rmarkdown::html_dependency_font_awesome())
# magick
dev.off <- function(){
  invisible(grDevices::dev.off())
}
# conflicted
library(conflicted)
conflict_prefer("filter", "dplyr")
# xaringanExtra
library(xaringanExtra)
xaringanExtra::use_panelset()
# output number of lines
hook_output <- knitr::knit_hooks$get("output")
knitr::knit_hooks$set(output = function(x, options) {
  lines <- options$output.lines
  if (is.null(lines)) {
    return(hook_output(x, options))  # pass to default hook
  }
  x <- unlist(strsplit(x, "\n"))
  more <- "..."
  if (length(lines)==1) {        # first n lines
    if (length(x) > lines) {
      # truncate the output, but add ....
      x <- c(head(x, lines), more)
    }
  } else {
    x <- c(more, x[lines], more)
  }
  # paste these lines together
  x <- paste(c(x, ""), collapse = "\n")
  hook_output(x, options)
})



## ----packages, echo=FALSE, message=FALSE, warning=FALSE--------
library(tidyverse)
library(DT)
library(scales)


## ----echo=FALSE, caption="The hierarchy of R’s vector types", out.width="120%"----
knitr::include_graphics("img/data-structures-overview.png")


## --------------------------------------------------------------
typeof(TRUE)


## --------------------------------------------------------------
mode(TRUE)


## --------------------------------------------------------------
typeof("hello")


## --------------------------------------------------------------
mode("hello")


## --------------------------------------------------------------
typeof(1.335)
typeof(7)


## --------------------------------------------------------------
mode(1.335) ; mode(7)


## --------------------------------------------------------------
typeof(7L)
typeof(1:3)


## --------------------------------------------------------------
mode(7L) ; mode(1:3)


## --------------------------------------------------------------
c(1, 2, 3)
c("Hello", "World!")
c(c("hi", "hello"), c("bye", "goodbye"))


## --------------------------------------------------------------
x <- c(TRUE, FALSE)
x
typeof(x)


## --------------------------------------------------------------
y <- as.numeric(x)
y
typeof(y)


## --------------------------------------------------------------
x <- 1:3
x
typeof(x)


## --------------------------------------------------------------
y <- as.character(x)
y
typeof(y)


## --------------------------------------------------------------
c(1, "Hello") ; typeof(c(1, "Hello"))
c(FALSE, 3L) ; typeof(c(FALSE, 3L))


## --------------------------------------------------------------
c(1.2, 3L) ; typeof(c(1.2, 3L))
c(2L, "two") ; typeof(c(2L, "two"))


## --------------------------------------------------------------
pi / 0
0 / 0


## --------------------------------------------------------------
1/0 - 1/0
1/0 + 1/0


## --------------------------------------------------------------
x <- c(1, 2, 3, 4, NA)


## --------------------------------------------------------------
mean(x)
mean(x, na.rm = TRUE)
summary(x)


## --------------------------------------------------------------
typeof(NA)


## --------------------------------------------------------------
# TRUE or NA
TRUE | NA


## --------------------------------------------------------------
# FALSE or NA
FALSE | NA


## --------------------------------------------------------------
TRUE | TRUE  # if NA was TRUE
TRUE | FALSE # if NA was FALSE


## --------------------------------------------------------------
FALSE | TRUE  # if NA was TRUE
FALSE | FALSE # if NA was FALSE


## ----message=FALSE---------------------------------------------
cat_lovers <- read_csv("data/cat-lovers.csv")


## ----echo=FALSE------------------------------------------------
cat_lovers


## --------------------------------------------------------------
cat_lovers %>%
  summarise(mean_cats = mean(number_of_cats))


## ----eval=FALSE------------------------------------------------
# ?mean


## ----echo=FALSE, caption="Help for mean", out.width="75%"------
knitr::include_graphics("img/mean-help.png")


## --------------------------------------------------------------
cat_lovers %>%
  summarise(mean_cats = mean(number_of_cats, na.rm = TRUE))


## --------------------------------------------------------------
glimpse(cat_lovers)


## ----echo=FALSE------------------------------------------------
options(htmltools.preserve.raw = FALSE)
cat_lovers %>%
  datatable(options=list(scrollY=F, pageLength = 10))


## --------------------------------------------------------------
cat_lovers %>%
  mutate(number_of_cats = case_when(
    name == "Ginger Clark" ~ 2,
    name == "Doug Bass"    ~ 3,
    TRUE                   ~ as.numeric(number_of_cats)
    )) %>%
  summarise(mean_cats = mean(number_of_cats))


## --------------------------------------------------------------
cat_lovers %>%
  mutate(
    number_of_cats = case_when(
      name == "Ginger Clark" ~ "2",
      name == "Doug Bass"    ~ "3",
      TRUE                   ~ number_of_cats
      ),
    number_of_cats = as.numeric(number_of_cats)
    ) %>%
  summarise(mean_cats = mean(number_of_cats))


## --------------------------------------------------------------
cat_lovers <- cat_lovers %>% #<<
  mutate(
    number_of_cats = case_when(
      name == "Ginger Clark" ~ "2",
      name == "Doug Bass"    ~ "3",
      TRUE                   ~ number_of_cats
      ),
    number_of_cats = as.numeric(number_of_cats)
    )


## --------------------------------------------------------------
typeof(1)


## --------------------------------------------------------------
typeof("a")


## --------------------------------------------------------------
typeof(c(1, "a"))


## --------------------------------------------------------------
temp <- c(0.2, 0.5, 1.47, 3.82, 0.2, 0.78)
temp
# Testing vector type
is.atomic(temp) ; is.list(temp)
# Testing length and value type
length(temp) ; typeof(temp)


## --------------------------------------------------------------
# Two scalar arguments specify row and column sizes
x <- matrix(1:6, nrow = 2, ncol = 3)
x
dim(x)
attributes(x)

# You can also modify an object in place by setting dim()
z <- 1:6
dim(z) <- c(2, 3)


## --------------------------------------------------------------
# One vector argument to describe all dimensions
y <- array(1:12, c(2, 3, 2))
y
attributes(y)


## --------------------------------------------------------------
x <- factor(c("BS", "MS", "PhD", "MS"))
x
attributes(x)


## --------------------------------------------------------------
glimpse(x)
as.integer(x)


## --------------------------------------------------------------
y <- as.Date("2020-01-01")
y
attributes(y)
typeof(y)
class(y)


## --------------------------------------------------------------
as.integer(y)
as.integer(y) / 365 # roughly 50 yrs


## --------------------------------------------------------------
l <- list(
  x = 1:4,
  y = c("hi", "hello", "bye"),
  z = c(TRUE, FALSE)
)
l


## --------------------------------------------------------------
length(l)
typeof(l)
attributes(l)



## --------------------------------------------------------------
df <- data.frame(x = 1:2, y = c("hi", "hello"))
df
attributes(df)


## --------------------------------------------------------------
str(df)
str(l)


## --------------------------------------------------------------
str(temp)
str(z)
str(y)
str(x)


## --------------------------------------------------------------
temp[2] ; temp[2:3]
z[,1] ; z[1,2]
l[1] ; l[[1]] ; l$x


## --------------------------------------------------------------
df
df[,1] ; df$x


## --------------------------------------------------------------
df %>%
  pull(y)