06_movies.Rmd

name: movies
# Movies

---

```{r, echo = F}

dir <- "raw_data"
file <- paste0(dir, "/", "movies.csv")
url <- "https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2018/2018-10-23/movie_profit.csv"

# create raw_data folder
if (!dir.exists(dir)) { dir.create(dir) }

# download data from internet and save
if (!file.exists(file)) { download.file(url = url, destfile = file) }

# read in downloaded data
movies_0 <- readr::read_csv(file)
```


```{r, echo = F, warning=F, message=F}
library(ggrepel)


movies <- movies_0 %>% 
  mutate(release_date = lubridate::mdy(release_date)) %>% 
  filter(worldwide_gross != 0) %>% 
  mutate(label = paste0(movie, "\n$", round(production_budget/1000000, 2), "mil."))

```

---

```{r movies, eval=F, echo=F, fig.width=12}
ggplot(data = movies) +
  aes(x = production_budget) +
  aes(y = worldwide_gross/production_budget) +
  geom_point(alpha = .25) +
  facet_wrap(~ genre) +
  theme_bw() +
  aes(col = lubridate::year(release_date)) +
  scale_color_viridis_c(option = "B") +
  labs(col = "") +
  scale_x_log10(labels = scales::dollar_format(), 
                limits = c(100000, 100000000)) + 
  scale_y_log10(breaks = c(.0001,.001,.01,.1,1,10,100, 1000), 
                label = c(".0001X", ".001X", ".01X", ".1X", "1X", "10X", "100X", "1000X"), 
                limits = c(.0001, 1000)) +
  aes(label = paste0(movie, "\n$", round(production_budget/1000000, 2), 
                     "mil.")) +
  ggpmisc::stat_dens2d_filter(data = movies %>% filter(worldwide_gross>10*production_budget), 
                              geom = "text_repel", keep.fraction = 0.06, 
                              size = 2.8, col = "darkgrey") + 
  ggpmisc::stat_dens2d_filter(data = movies %>% filter(worldwide_gross<production_budget), 
                              geom = "text_repel", keep.fraction = 0.002, 
                              size = 2.8, col = "darkgrey") + 
  geom_abline(intercept = 0, slope = 0, lty = 2, col = "darkgrey") +
  labs(x = "production budget") +
  labs(y = "Profit ratio (worldwide gross)") +
  labs(title = "Profit ratio in a 538 movies dataset") +
  labs(subtitle = "Data source: 538 via TidyTuesday | Vis: Gina Reynolds")

  

```

```{r, echo = F, warning=F, message=F, eval = T, fig.show='hide'}
get_what_save_what <- "movies"
eval(parse(text = paste(knitr:::knit_code$get(get_what_save_what), collapse = "")))
ggsave(paste0("figures/", get_what_save_what, ".png"), dpi = 300)
```

`r apply_reveal("movies")`


---