Tidy Tuesday

── Attaching packages ──────────────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.2.1     ✔ purrr   0.3.2
✔ tibble  2.1.3     ✔ dplyr   0.8.3
✔ tidyr   0.8.3     ✔ stringr 1.4.0
✔ readr   1.3.1     ✔ forcats 0.4.0
── Conflicts ─────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

Attaching package: ‘skimr’

The following object is masked from ‘package:stats’:

    filter


Attaching package: ‘lubridate’

The following object is masked from ‘package:base’:

    date

pets <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-03-26/seattle_pets.csv")

Parsed with column specification:
cols(
  license_issue_date = col_character(),
  license_number = col_character(),
  animals_name = col_character(),
  species = col_character(),
  primary_breed = col_character(),
  secondary_breed = col_character(),
  zip_code = col_character()
)

pets$species <- as.factor(pets$species)

ggplot(pets) +  
  aes(species)+ 
  geom_bar()

NA
NA
NA

dogs <- pets %>% 
  filter(species == "Dog")

cats <- pets %>% 
  filter(species == "Cat")

skim(cats)

Skim summary statistics
 n obs: 17294 
 n variables: 7 

── Variable type:character ──────────────────────────────────────────────────────
           variable missing complete     n min max empty n_unique
       animals_name     406    16888 17294   1  45     0     7026
 license_issue_date       0    17294 17294  11  17     0      882
     license_number       0    17294 17294   1   8     0    17286
      primary_breed       0    17294 17294   3  21     0       58
    secondary_breed   11173     6121 17294   3  21     0       52
           zip_code     127    17167 17294   4  10     0       88

── Variable type:factor ─────────────────────────────────────────────────────────
 variable missing complete     n n_unique                         top_counts
  species       0    17294 17294        1 Cat: 17294, Dog: 0, Goa: 0, Pig: 0
 ordered
   FALSE

cats_by_breed <- cats %>% 
  group_by(primary_breed) %>%
  summarise(count = n()) %>%
  arrange(desc(count))

ggplot(cats_by_breed, aes(reorder(primary_breed, count), y = count)) + geom_col() +
  coord_flip()

'%not in%' <- Negate('%in%')

exclude_cat_breeds <- c("Domestic Shorthair", "Domestic Medium Hair", "Domestic Longhair", "American Shorthair")

cats_by_specific_breed <- cats_by_breed %>% 
  filter(primary_breed %not in% exclude_cat_breeds) %>%
  filter(count >= 5)

ggplot(cats_by_specific_breed, aes(reorder(primary_breed, count), y = count)) + geom_col() +
  coord_flip() +
  labs(x = "Breed Name")

dogs %>% 
  group_by(primary_breed, animals_name) %>%
  summarise(value = n()) %>%
  filter(value == 2) %>%
  arrange(desc(value))

GOT_names <- c("Tyrion", "Jon", "Cersei", "Daenerys", "Sansa", "Arya", "Jaime", "Jorah", "Theon", "Samwell")

GOT_pets <- pets %>% 
  filter(animals_name %in% GOT_names)

GOT_pets %>% group_by(animals_name) %>% summarise(count = n()) %>% arrange(desc(count))

library(gameofthrones)

library(showtext)

Loading required package: sysfonts
Loading required package: showtextdb

font_add_google(name = "Cinzel", family = "Cinzel")

showtext_auto()

ggplot(GOT_pets, aes(fct_infreq(animals_name), fill = species)) + 
  geom_bar() + 
  scale_fill_got_d(option = "Targaryen", direction = - 1) +
  labs(title = "A Goat Named Arya", subtitle = "Game of Thrones Inspired (Maybe) Pet Names in Seattle", x = element_blank(), y = element_blank(), caption = "@MaraAlexeev") +
  theme_minimal() +
  theme(legend.position = c(0.9, 0.6)) +
  labs(fill = "Pet Species") +
  theme(text=element_text(size=16,  family="Cinzel"))

NA

pets$license_issue_date <- as.Date(pets$license_issue_date, "%B %d %Y")

limited <- pets %>% filter(license_issue_date > 2018-01-01)
  

ggplot(limited, aes(license_issue_date)) + geom_bar() + scale_x_date()