使用spotifyr聚类Springsteen专辑

spotifyr包很棒，让我们来探索音乐的各个方面，如节奏、舞蹈性和化合价。在这篇文章中，我们将从相同点和不同点来探讨布鲁斯·斯普林斯汀的专辑。

# devtools::install_github('charlie86/spotifyr')

library(spotifyr)
library(tidyverse)
library(magrittr)
library(ggridges)
library(ggcorrplot)
library(viridisLite)
library(factoextra)
library(ggiraphExtra)

使用get_artist_audio_features()函数很容易获得数据。在这里，我们将从csv文件中加载它并查看。

# df <- get_artist_audio_features(artist = "bruce springsteen")

df <- read_csv("https://raw.github.com/peerchristensen/Springsteen_album_clusters/master/springsteen_albums.csv")

glimpse(df)

## Observations: 537
## Variables: 31
## $ artist_name            <chr> "Bruce Springsteen", "Bruce Springsteen...
## $ artist_uri             <chr> "3eqjTLE0HfPfh78zjh6TqT", "3eqjTLE0HfPf...
## $ album_uri              <chr> "0PMasrHdpaoIRuHuhHp72O", "0PMasrHdpaoI...
## $ album_name             <chr> "Born In The U.S.A.", "Born In The U.S....
## $ album_img              <chr> "https://i.scdn.co/image/d002b63ceb5658...
## $ album_type             <chr> "album", "album", "album", "album", "al...
## $ is_collaboration       <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALS...
## $ album_release_date     <chr> "1984-06-04", "1984-06-04", "1984-06-04...
## $ album_release_year     <date> 1984-06-04, 1984-06-04, 1984-06-04, 19...
## $ album_popularity       <dbl> 76, 76, 76, 76, 76, 76, 76, 76, 76, 76,...
## $ track_name             <chr> "Born in the U.S.A.", "Cover Me", "Darl...
## $ track_uri              <chr> "0dOg1ySSI7NkpAe89Zo0b9", "4U7NhC2rQTAh...
## $ track_number           <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, ...
## $ disc_number            <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
## $ danceability           <dbl> 0.398, 0.535, 0.536, 0.429, 0.544, 0.62...
## $ energy                 <dbl> 0.952, 0.884, 0.982, 0.949, 0.762, 0.44...
## $ key                    <chr> "E", "A", "G", "C", "A#", "C#", "F", "A...
## $ loudness               <dbl> -6.042, -5.499, -4.674, -5.295, -7.289,...
## $ mode                   <chr> "major", "minor", "major", "major", "ma...
## $ speechiness            <dbl> 0.0610, 0.0407, 0.0389, 0.0458, 0.0382,...
## $ acousticness           <dbl> 0.000373, 0.001880, 0.014100, 0.084200,...
## $ instrumentalness       <dbl> 7.75e-05, 1.26e-03, 3.67e-05, 0.00e+00,...
## $ liveness               <dbl> 0.1000, 0.1400, 0.2740, 0.1540, 0.0740,...
## $ valence                <dbl> 0.584, 0.796, 0.963, 0.967, 0.473, 0.86...
## $ tempo                  <dbl> 122.093, 120.555, 119.201, 184.286, 120...
## $ duration_ms            <dbl> 278680, 205987, 288027, 192267, 215427,...
## $ time_signature         <dbl> 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, ...
## $ key_mode               <chr> "E major", "A minor", "G major", "C maj...
## $ track_popularity       <dbl> 72, 51, 45, 47, 49, 71, 50, 47, 53, 62,...
## $ track_preview_url      <chr> "https://p.scdn.co/mp3-preview/3b6a5b91...
## $ track_open_spotify_url <chr> "https://open.spotify.com/track/0dOg1yS...

我们只需要做一点清洗和删除一些非录音室的专辑。

# some albums only have one song, some are alternate versions

remove_albums <- c("Greatest Hits",
                   "Hammersmith Odeon, London 75",
                   "The Essential Bruce Springsteen (Bonus Disc)",
                   "The Ties That Bind: The River Collection",
                   "Chapter and Verse",
                   "The Promise",
                   "Tracks")

df %<>% 
  filter(!album_name %in% remove_albums,
         !grepl("live|Live",album_name)) %>%
  mutate(album_name = str_to_title(album_name))

df$album_name <- gsub(":.*","",df$album_name)
df$album_name[grepl("Innocent",df$album_name)]  <- "The Wild, The Innocent.."
df$album_name[grepl("Greetings",df$album_name)] <- "Greetings"
df$album_name[grepl("Darkness",df$album_name)]  <- "Darkness"

让我们先来看看Springsteen歌曲中最常用的五个键。

df                   %>% 
  select(key_mode)   %>%
  group_by(key_mode) %>%
  count()            %>%
  arrange(desc(n))   %>%
  ungroup()          %>%
  top_n(5)           %>%
  mutate(ordered = row_number()) %>%
  
  ggplot(aes(x = reorder(key_mode,desc(ordered)), y = n, fill = n)) +
  geom_col() +
  coord_flip() +
  ggtitle("Five most common keys") +
  scale_fill_viridis_c(option="B", direction = -1,guide=F) +
  theme_minimal() +
  labs(y = "n",x = "key")

正如我们所看到的，spotifyr从spotify API获取了许多有趣的数据。让我们先来看看每张专辑的舞蹈性。“天生就会跑步”的可舞性最低，而“爱的隧道”的可舞性最高。

df                     %>% 
  group_by(album_name) %>%
  
  ggplot(aes(x    = danceability, 
             y    = reorder(album_name,desc(album_release_year)),
             fill = reorder(album_name,desc(album_release_year)))) +
  geom_density_ridges(colour = "snow") +
  scale_fill_viridis_d(option = "B", begin = .05, direction = -1, guide = F) +
  theme_minimal() +
  ggtitle("Danceability") +
  labs(y="album")

让我们把所有的特征放在同一个图中。

df %>% 
  gather(key = feature, value = measure, 
         danceability, energy, loudness, valence, tempo, acousticness) %>%
  group_by(album_name) %>%
  
  ggplot(aes(x    = measure, 
             y    = reorder(album_name,desc(album_release_year)), 
             fill = album_release_date)) +
  geom_density_ridges(rel_min_height = 0.005, legend = F, alpha = .9, size = .2, colour = "snow") +
  facet_wrap(~feature, scales = "free", ncol = 2) +
  scale_fill_viridis_d(option ="B" ,begin = .05) +
  theme_minimal() +
  theme(axis.text.y = element_text(size = 7)) +
  labs(y = "album name") +
  ggtitle("Springsteen albums in six features",
          subtitle = "Acousticness, danceability, energy, loudness, tempo and valence") +
  guides(fill = FALSE)

将各个特征之间的相关性形象化也会很有趣。energy和loudness是正相关的，而acousticness和loudness是负相关的，这不足为奇。

sign_test <- df %>% 
  select(acousticness,danceability,energy,loudness,tempo,valence) %>%
  cor_pmat()

df  %>% 
  select(acousticness,danceability,energy,loudness,tempo,valence) %>%
  cor() %>%
  ggcorrplot(type   = "lower", 
             p.mat  = sign_test,
             colors = c(inferno(5)[2], "snow", inferno(5)[4])) +
  ggtitle("Correlations between features",
          subtitle = "Non-significant correlations marked with X")

基于这些特性，我们还可以探索专辑在距离矩阵中的相似性。在这幅图中，橙色表示专辑之间的高度差异或很大的“距离”。

dfScale <- df %>%
  select(album_name,acousticness,danceability,energy,loudness,tempo,valence) %>%
  group_by(album_name) %>%
  summarise(acousticness = mean(scale(acousticness)),
            danceability = mean(scale(danceability)),
            energy       = mean(scale(energy)),
            loudness     = mean(scale(loudness)),
            tempo        = mean(scale(tempo)),
            valence      = mean(scale(valence))) %>%
  data.frame()

row.names(dfScale) <- dfScale$album_name

dfScale %<>% 
  select(-album_name) %>%
  data.frame()

df_dist <- get_dist(dfScale, stand = TRUE)

fviz_dist(df_dist,gradient = list(low = inferno(5)[2], mid = "white", high = inferno(5)[4])) +
  theme_minimal() +
  ggtitle("Distance matrix",
          subtitle  = "Similarity between albums based on all features") +
  theme(axis.text.x = element_text(hjust = 1,angle = 45),
        axis.title = element_blank())

为了获得更清晰的图像，我们可以使用ggiraphExtra包中的雷达图来探索专辑和特征之间的模式。

dfScale %>%
  mutate(albums = row.names(dfScale)) %>%
  ggRadar(aes(group = albums), 
        rescale = FALSE, legend.position = "none",
        size = 1, interactive = FALSE, use.label = TRUE) +
  facet_wrap(~albums) + 
  scale_y_discrete(breaks = NULL) +
  theme(axis.text.x = element_text(size = 10)) +
  theme_minimal() +
  theme(legend.position = "none") +
  scale_fill_viridis_d(option="B") +
  scale_colour_viridis_d(option="B")

最后一步，我们将了解如何使用分层和k-means聚类根据各种特征对专辑进行分组。我们首先使用factoExtra包中的fviz_nbclust()函数来计算聚类的最优数量。注意，函数中包含不同的方法来计算聚类的数量。默认情况下使用“silhouette”方法。

fviz_nbclust(dfScale, hcut) +
  ggtitle("Optimal Number of Clusters: H-Clustering")

df.hc <- hclust(dist(scale(dfScale)))

fviz_dend(df.hc, k = 3,
          cex = .9,
          k_colors = inferno(10)[c(4,7)],
          color_labels_by_k = TRUE, 
          rect = TRUE) +
  ggtitle("Hierachical Clustering")

fviz_nbclust(dfScale, kmeans) +
  ggtitle("Optimal Number of Clusters: K-means Clustering")

set.seed(324789)
km.res <- kmeans(dfScale, 2, nstart = 25)

fviz_cluster(km.res, data = dfScale,
             ellipse.type = "convex",
             repel = T,
             palette = inferno(10)[c(4,6,8)],
             ggtheme = theme_minimal(),
             main = "K-means Clustering")

作者：Peer Christensen 原文链接： https://peerchristensen.netlify.com/post/clustering-springsteen-albums-with-spotifyr/

版权声明： 作者保留权利。文章为作者独立观点，不代表数据人网立场。严禁修改，转载请注明原文链接:http://shujuren.org/article/807.html

数据人网： 数据人学习，交流和分享的平台，诚邀您创造和分享数据知识，共建和共享数据智库。