TidyTuesday: Thanksgiving Dinner

Analyzing data for #tidytuesday week of 11/20/2018 (source)

# LOAD PACKAGES AND PARSE DATA
library(tidyverse)
library(scales)
library(RColorBrewer)
library(forcats)

thanksgiving_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2018/2018-11-20/thanksgiving_meals.csv")

thanksgiving <- 
  thanksgiving_raw %>%
  filter(celebrate != 'No')

thanksgiving %>%
  select(pie1:pie13) %>% 
  pivot_longer(pie1:pie13, names_to = "pie_type") %>% 
  filter(value != 'None') %>% 
  select(value) %>% 
  group_by(value) %>% 
  count() %>% 
  filter(n > 10) %>% 
  ungroup() %>% 
  ggplot(aes(reorder(value, n), n, label = n)) +
  geom_bar(aes(fill = value),
           alpha = 0.9,
           stat='identity') +
  coord_flip() +
  theme_classic() + 
  theme(legend.position = 'none') +
  labs(title = "Most Popular Pies for Thanksgiving (n=980)",
        subtitle = "Question: Which type of pie is typically served at your Thanksgiving dinner? \n Please select all that apply",
       x = "",
       y = "")

thanksgiving %>%
  select(pie1:pie13, us_region) %>%
  pivot_longer(pie1:pie13, names_to = "pie_type") %>% 
  filter(!is.na(value), us_region != 'NA') %>%
  
  # THIS IS PRETTY NASTY AND I SHOULD REFACTOR IN THE FUTURE
  mutate(us_region = ifelse(us_region == 'South Atlantic', 'East', 
                            ifelse(us_region == 'Middle Atlantic', 'North East', 
                                   ifelse(us_region == 'East North Central', 'Midwest',
                                          ifelse(us_region == 'East South Central', 'South',
                                                 ifelse(us_region == 'West North Central', 'Midwest',
                                                        ifelse(us_region == 'West South Central', 'South',
                                                               ifelse(us_region == 'New England', 'North East',
                                                                      ifelse(us_region == 'Pacific', 'West', 
                                                                             ifelse(us_region == 'Mountain', 'Midwest',
                                                               us_region)))))))))) %>% 
  group_by(us_region, value) %>%
  count(sort = TRUE) %>% 
  filter(n > 10) %>% 
  ungroup()  %>% 
  ggplot(aes(us_region, fct_rev(value), fill = n)) + 
  geom_tile() +
  scale_fill_gradient2(
    name = 'n',
    low = '#fee6ce',
    mid = '#fdae6b',
    high = '#e6550d',
    midpoint = 100
  ) +
  theme_classic() + 
  labs(x = "",
       y = "",
       title = "Most Popular Pies for Thanksgiving by US Region")