njtierney

library(tidyverse)
df_console <- tibble(
  name = c("Smash Bros.", "Red Dead", "Spiderman 4", "Overcooked", "Zelda"),
  sales = c(2001:2005),
  platform = c("NS",
               "PS4",
               "PS4)(PS4",
               "NS(2017)",
               "XboxOne")

njtierney

library(tidyverse)
library(glue)
#> 
#> Attaching package: 'glue'
#> The following object is masked from 'package:dplyr':
#> 
#>     collapse
library(lubridate)
#> 

njtierney

library(tidyverse)

ggplot(airquality,
       aes(x = Ozone)) + 
  geom_histogram(fill = "red")
#> `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
#> Warning: Removed 37 rows containing non-finite values (stat_bin).

njtierney

library(tidyverse)
income <- tibble(income_range = c("0-74",
                                  "75-145",
                                  "150-325",
                                  "325+"),
                 count = c(125,
                           170, 
                           215,
                           250))

njtierney

library(tidyverse)
who_tidy <- who %>% pivot_longer(
    cols = new_sp_m014:newrel_f65,
    names_to = c("diagnosis", "gender", "age"),
    names_pattern = "new_?(.*)_(.)(.*)",
    values_to = "count"
  )

who_tidy

njtierney

library(tidyverse)
chunk <- function(x, n){
  split(x, sort(x %% n))
}

special_chunk <- function(x, n){
  chunk(x, n) %>% 
    map(paste0, collapse = ", ") %>% 
    as.character()

njtierney

library(tidyverse)
top_100 <- tibble(artist = c("The Beatles", "The Mars Volta"), 
                  song = c("Help!", "Cicatriz Esp"))

rock_tibble <- tibble(artist = "The Beatles",
                      song = "Help!") 

prog_rock_tibble <- tibble(artist = "The Mars Volta",
                           song = "Cicatriz Esp")

njtierney

---
class: bg-main1

# Let's get more data

.huge[
We'll use the `genius` package to get song lyric data from [Genius](https://genius.com/).

- `genius_album()` allows you to download the lyrics for an entire album in a 
tidy format. 

njtierney

library(tidyverse)
library(rpart)
set.seed(2020 - 05 - 21)
x <- sort(runif(100) - 0.5)
df <- tibble(x,
             y = 10 * c(x[1:50] ^ 2,
                        x[51:75] * 2,
                        -x[76:100] ^ 2) + rnorm(100) * 0.5)

njtierney

library(tidyverse)
library(gridExtra)

rates <- read_csv("https://raw.githubusercontent.com/numbats/ida/master/slides/data/rates_new.csv")
rates <- rates %>% 
  distinct() %>%  
  arrange(date)

p1 <- ggplot(rates, aes(x=date, y=AUD)) + geom_line()
p2 <- ggplot(rates, aes(x=date, y=EUR)) + geom_line()