## ----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)


## ----message=FALSE---------------------------------------------
hotels <- read_csv("data/hotels.csv")


## --------------------------------------------------------------
hotels %>%
  select(hotel, lead_time) #<<


## ----output.lines=18-------------------------------------------
hotels %>%
  select(-agent) #<<


## --------------------------------------------------------------
hotels %>%
  select(hotel:arrival_date_month) #<<


## --------------------------------------------------------------
hotels %>%
  select(starts_with("arrival")) #<<


## --------------------------------------------------------------
hotels %>%
  select(ends_with("type")) #<<


## ----results='hide'--------------------------------------------
hotels %>%
  pull(lead_time) #<<


## --------------------------------------------------------------
hotels %>%
  pull(lead_time) %>% 
  class() #<<


## --------------------------------------------------------------
hotels %>%
  select(adults, children, babies) %>%
  arrange(babies) #<<


## --------------------------------------------------------------
hotels %>%
  select(adults, children, babies) %>%
  arrange(desc(babies)) #<<


## ----output.lines=17-------------------------------------------
# first five
hotels %>%
  slice(1:5) #<<


## ----output.lines=10-------------------------------------------
hotels %>%
  # slice the first five rows  # this line is a comment
  # select(hotel) %>%           # this one doesn't run
  slice(1:5)                   # this line runs


## ----output.lines=17-------------------------------------------
# bookings in City Hotels
hotels %>%
  filter(hotel == "City Hotel") #<<


## --------------------------------------------------------------
hotels %>%
  filter( 
    adults == 0,     #<<
    children >= 1    #<<
    ) %>% 
  select(adults, babies, children)


## --------------------------------------------------------------
# bookings with no adults and some children or babies in the room
hotels %>%
  filter( 
    adults == 0,     
    children >= 1 | babies >= 1     # | means or  #<<
    ) %>%
  select(adults, babies, children)


## ----include=FALSE---------------------------------------------
options(dplyr.print_max = 20)


## --------------------------------------------------------------
hotels %>% 
  distinct(market_segment) %>% #<<
  arrange(market_segment)


## ----output.lines=13-------------------------------------------
hotels %>% 
  distinct(hotel, market_segment) %>% #<<
  arrange(hotel, market_segment)


## --------------------------------------------------------------
# alphabetical order by default
hotels %>%
  count(market_segment) #<<


## --------------------------------------------------------------
# descending frequency order
hotels %>%
  count(market_segment, sort = TRUE) #<<


## --------------------------------------------------------------
# ascending frequency order
hotels %>%
  count(market_segment) %>%
  arrange(n) #<<


## --------------------------------------------------------------
# descending frequency order
# just like adding sort = TRUE
hotels %>%
  count(market_segment) %>%
  arrange(desc(n)) #<<


## --------------------------------------------------------------
hotels %>%
  count(hotel, market_segment) #<<


## --------------------------------------------------------------
# hotel type first
hotels %>%
  count(hotel, market_segment) #<<


## --------------------------------------------------------------
# market segment first
hotels %>%
  count(market_segment, hotel) #<<


## --------------------------------------------------------------
hotels %>%
  mutate(little_ones = children + babies) %>% #<<
  select(children, babies, little_ones) %>%
  arrange(desc(little_ones))


## --------------------------------------------------------------
# Resort Hotel
hotels %>%
  mutate(little_ones = children + babies) %>%
  filter(
    little_ones >= 1,
    hotel == "Resort Hotel"
    ) %>%
  select(hotel, little_ones)


## --------------------------------------------------------------
# City Hotel
hotels %>%
  mutate(little_ones = children + babies) %>%
  filter(
    little_ones >= 1,
    hotel == "City Hotel"
    )  %>%
  select(hotel, little_ones)


## --------------------------------------------------------------
hotels %>%
  mutate(little_ones = children + babies) %>%
  count(hotel, little_ones) %>%
  mutate(prop = n / sum(n))


## --------------------------------------------------------------
# mean average daily rate for all bookings 
# (calculated by dividing the sum of all lodging transactions by the total number of staying nights)
hotels %>%
  summarise(mean_adr = mean(adr)) #<<


## --------------------------------------------------------------
hotels %>%
  summarise(mean(adr))


## --------------------------------------------------------------
hotels %>%
  summarise(mean_adr = mean(adr))


## --------------------------------------------------------------
# mean average daily rate for all booking at city and resort hotels
hotels %>%
  group_by(hotel) %>% #<<
  summarise(mean_adr = mean(adr))


## --------------------------------------------------------------
hotels %>%
  group_by(hotel) %>%
  summarise(n = n())


## --------------------------------------------------------------
hotels %>%
  count(hotel)


## --------------------------------------------------------------
hotels %>%
  summarise(
    min_adr = min(adr),
    mean_adr = mean(adr),
    median_adr = median(adr),
    max_adr = max(adr)
    )