project_draft

Loading data and packages

How different songs’ properties influence it’s popularity?

range(data$danceability)

## [1] 0.000 0.988

range(data$duration_ms)

## [1]    4937 5338302

range(data$tempo)

## [1]   0.000 243.507

range(data$speechiness)

## [1] 0.000 0.971

data1 = data %>% 
  select(id, popularity, year, danceability, duration_ms, tempo, speechiness) %>% 
  mutate(duration = 
           (duration_ms-min(duration_ms))/(max(duration_ms)-min(duration_ms))) %>% 
  select(-duration_ms) %>% 
  mutate(tempo = (tempo-min(tempo))/(max(tempo)-min(tempo)))
  

fig1_data = data1 %>% select(-year) %>% 
  mutate(danceability = cut(danceability, 50, labels=FALSE),
         duration = cut(duration, 50, labels=FALSE),
         tempo = cut(tempo, 50, labels=FALSE),
         speechiness = cut(speechiness, 50, labels=FALSE)) %>% 
  pivot_longer(cols = danceability:duration, 
               names_to = "property") %>% 
  group_by(property, value) %>% 
  summarise(popularity_median = median(popularity)) %>% 
  mutate(property = factor(property, levels=c("danceability",
                                              "tempo",
                                              "speechiness",
                                              "duration")))

## `summarise()` has grouped output by 'property'. You can override using the `.groups` argument.

ggplot(fig1_data, aes(x=value, y=popularity_median, group=property)) + 
  geom_ribbon(aes(ymin = 0, ymax = popularity_median, fill=property), alpha=0.6) + 
  labs(x = "Normalized Value (0-30)", y = "Median Popularity (0-100)") + 
  scale_fill_OkabeIto()

How does songs’ properties change over time?

fig2_data = data1 %>% 
  mutate(decades = year - year %% 10 ) %>% 
  select(-c(popularity, year)) %>% 
  pivot_longer(cols = danceability:duration, 
               names_to = "property") %>% 
  group_by(property, decades) %>% 
  summarise(mean = mean(value))

## `summarise()` has grouped output by 'property'. You can override using the `.groups` argument.

ggplot(fig2_data, aes(x=decades, y=property, fill=mean)) + geom_tile() +
  scale_fill_viridis_c(option = "A") + 
  labs(y="Property", x="Mean for each decade") + 
  theme(legend.position = "top")

The most popular artist over time

library(gganimate)

artist_data = data %>% 
  select(popularity, artists, year) %>% 
  mutate(artists =  gsub("\\[|\\]", "", artists)) %>% 
  separate_rows(artists, sep = ", ") %>% 
  mutate(artists =  gsub("'", "", artists)) %>% 
  mutate(artists =  gsub('"', '', artists))


fig3_data = artist_data %>% 
  mutate(decades = year - year %% 10 ) %>% 
  mutate(year = ifelse(year < 1990, decades, year)) %>% 
  group_by(year, artists) %>% 
  summarise(mean_popularity = mean(popularity)) %>% 
  arrange(year, desc(mean_popularity)) %>% 
  mutate(rank = 1:n()) %>% 
  filter(rank <= 10)

## `summarise()` has grouped output by 'year'. You can override using the `.groups` argument.

my_theme <- theme_classic(base_family = "Times") +
  theme(axis.text.y = element_blank()) +
  theme(axis.ticks.y = element_blank()) +
  theme(axis.line.y = element_blank()) +
  theme(legend.background = element_rect(fill = "gainsboro")) +
  theme(plot.background = element_rect(fill = "gainsboro")) +
  theme(panel.background = element_rect(fill = "gainsboro"))

fig3 = ggplot(fig3_data) +  
  aes(xmin = 18 ,  
      xmax = mean_popularity) +  
  aes(ymin = rank - .45,  
      ymax = rank + .45,  
      y = rank) +  
  facet_wrap(~ year) +  
  geom_rect(alpha = .7) +
  scale_x_continuous(  
    limits = c(-50, 100),
    breaks = c(0, 20, 40, 60, 80, 100)) + 
  geom_text(col = "gray13",  
            hjust = "right",  
            aes(label = artists),  
            x = 10) + 
  scale_y_reverse() + 
  labs(x = 'Popularity (0-100)', y = '') +  
  my_theme 


fig3 = fig3 +  
  facet_null() + 
  geom_text(x = 50 , y = -5,
            family = "Times",
            aes(label = as.character(year)),
            size = 25, col = "grey18", alpha=0.5) + 
  aes(group = artists) +  
  transition_states(year,
                    transition_length = 1,
                    state_length = 4)

animate(fig3, fps=1)