nyc restaurant violations

nyc restaurant violations

# data https://data.cityofnewyork.us/Health/DOHMH-New-York-City-Restaurant-Inspection-Results/43nn-pn8j
# Which are most likely to be violated for critical things like live mice?

library(tidyverse)
library(scales)

nyc_restaurants <- read_csv("Downloads/nyc_restaurants.csv")

# Gradable inspections
ny <- nyc_restaurants %>%
  filter((`INSPECTION TYPE` %in% 
            c('Cycle Inspection / Re-inspection'
              ,'Pre-permit (Operational) / Re-inspection')
          |(`INSPECTION TYPE` %in%
              c('Cycle Inspection / Initial Inspection'
                ,'Pre-permit (Operational) / Initial Inspection')) 
          & SCORE <= 13)
         | (`INSPECTION TYPE` %in%  
              c('Pre-permit (Operational) / Reopening Inspection'
                ,'Cycle Inspection / Reopening Inspection'))
         & GRADE %in% c('A', 'B', 'C', 'P', 'Z')) 

# cuisine
cuisines <- ny %>% count(CAMIS, `CUISINE DESCRIPTION`) %>%
  select(CAMIS, CUISINE=`CUISINE DESCRIPTION`)

# rodent violations
v <- ny %>%
  group_by(CAMIS) %>%
  summarise(inspections=n(),
            critical_flag_inspections = max(ifelse(`CRITICAL FLAG` == 'Critical', 1, 0)),
            mice_rats = max(ifelse(`VIOLATION DESCRIPTION` %in% c("Evidence of mice or live mice present in facility's food and/or non-food areas.",
                                                                  "Evidence of rats or live rats present in facility's food and/or non-food areas."), 1, 0)))  

# Join to cuisines
violations <- v %>% inner_join(cuisines)
agg <- violations %>%
  group_by(CUISINE) %>%
  summarise(restaurants = n(),
            with_rodents = sum(mice_rats),
            pct_with_rodents = with_rodents / restaurants) %>%
  filter(restaurants > 200) %>% # At least 200 restaurants inspected
  arrange(-pct_with_rodents)

# Average
v2 %>%
  summarise(restaurants = n(),
            with_rodents = sum(mice_rats),
            pct_with_rodents = with_rodents / restaurants) 

# Plot
?replace
sort(unique(cuisines$CUISINE))
agg %>%
  mutate(CUISINE=recode(CUISINE, `Bakery Products/Desserts`="Bakery/Desserts",
                        `Juice, Smoothies, Fruit Salads`="Juice, Smoothie")) %>%
  ggplot(aes(reorder(CUISINE, -pct_with_rodents), pct_with_rodents, 
             fill=pct_with_rodents, 
             label=round(pct_with_rodents * 100, 1))) +
  geom_col(alpha=0.8) +
  geom_text(hjust=-0.2, size=3) +
  geom_hline(yintercept = 0.349, linetype="dashed", color="grey50") +
  scale_fill_gradient(low = "dark green", high = "dark red") +
  scale_y_continuous(labels=percent_format(1)) +
  annotate("text", x="Donuts", y=0.38, label="Avg: 35%", size=3, color="grey20") +
  guides(fill="none") +
  coord_flip() +
  theme_classic() +
  labs(x=NULL,
       y="Percent of restaurants with a rodent violation",
       title="Which NYC restaurants are most likely to have mice or rat violations?",
       subtitle = "NYC restaurant inspections with 'Evidence of mice..' or 'Evidence of rats..' violations",
       caption= "NYC OpenData. Cuisines with 200+ restaurants in NYC",
       fill=NULL)
  

output

> agg %>% arrange(-restaurants) %>% print(n=50)
# A tibble: 26 × 4
   CUISINE                        restaurants with_rodents pct_with_rodents
   <chr>                                <int>        <dbl>            <dbl>
 1 American                              5006         1585            0.317
 2 Chinese                               2211          954            0.431
 3 Coffee/Tea                            1758          404            0.230
 4 Pizza                                 1540          612            0.397
 5 Italian                                941          353            0.375
 6 Japanese                               835          303            0.363
 7 Latin American                         808          341            0.422
 8 Mexican                                770          294            0.382
 9 Bakery Products/Desserts               739          283            0.383
10 Caribbean                              678          356            0.525
11 Sandwiches                             626          209            0.334
12 Chicken                                619          215            0.347
13 Donuts                                 584           91            0.156
14 Spanish                                578          248            0.429
15 Hamburgers                             504          100            0.198
16 Juice, Smoothies, Fruit Salads         404           84            0.208
17 Asian/Asian Fusion                     388          128            0.330
18 Tex-Mex                                369           85            0.230
19 Frozen Desserts                        334          101            0.302
20 Jewish/Kosher                          302          128            0.424
21 Indian                                 301          150            0.498
22 French                                 298          111            0.372
23 Thai                                   294          127            0.432
24 Korean                                 288           84            0.292
25 Mediterranean                          261           99            0.379
26 Seafood                                202           58            0.287