DV_assignment3
Yenting, Liu
27/10/2019
Top 50 Spotify Songs - 2019
Prepare and overview for the whole data
library(readr)
library(magrittr)
library(ggplot2)
library(GGally)## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2library(dplyr)##
## Attaching package: 'dplyr'## The following object is masked from 'package:GGally':
##
## nasa## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionlibrary(Hmisc)## Loading required package: lattice## Loading required package: survival## Loading required package: Formula##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitslibrary(plotly)##
## Attaching package: 'plotly'## The following object is masked from 'package:Hmisc':
##
## subplot## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layouttop50 <- read_csv("Downloads/top50.csv")## Warning: Missing column names filled in: 'X1' [1]## Parsed with column specification:
## cols(
## X1 = col_double(),
## Track.Name = col_character(),
## Artist.Name = col_character(),
## Genre = col_character(),
## Beats.Per.Minute = col_double(),
## Energy = col_double(),
## Danceability = col_double(),
## Loudness..dB.. = col_double(),
## Liveness = col_double(),
## Valence. = col_double(),
## Length. = col_double(),
## Acousticness.. = col_double(),
## Speechiness. = col_double(),
## Popularity = col_double()
## )head(top50)## # A tibble: 6 x 14
## X1 Track.Name Artist.Name Genre Beats.Per.Minute Energy Danceability
## <dbl> <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 1 "Se\xf1or… Shawn Mend… cana… 117 55 76
## 2 2 China Anuel AA regg… 105 81 79
## 3 3 boyfriend… Ariana Gra… danc… 190 80 40
## 4 4 Beautiful… Ed Sheeran pop 93 65 64
## 5 5 Goodbyes … Post Malone dfw … 150 65 58
## 6 6 I Don't C… Ed Sheeran pop 102 68 80
## # … with 7 more variables: Loudness..dB.. <dbl>, Liveness <dbl>,
## # Valence. <dbl>, Length. <dbl>, Acousticness.. <dbl>,
## # Speechiness. <dbl>, Popularity <dbl>ggpairs(top50, columns = 5:14,axisLabels = "internal")
artist_count=top50 %>% group_by(Artist.Name) %>% summarise(count=n()) %>% arrange(desc(count))
artist_top20=artist_count %>% slice(1:20)
#order count(artistname)
artist_top20$Artist.Name=artist_top20$Artist.Name %>% factor(levels = artist_top20$Artist.Name[order(-artist_top20$count)])
a1= ggplot(artist_top20, aes(x = artist_top20$Artist.Name, y = count))
a1 + geom_bar(stat = "identity",fill = "dodgerblue3")+theme_minimal()+theme(axis.text.x=element_text(angle=45,hjust=1)) +labs(title = "Top20 artist in Spotify",x="Artist name",y="The count of artist")
genre_count=top50 %>% group_by(Genre) %>% summarise(count=n()) %>% arrange(desc(count))
genre_top20=genre_count %>% slice(1:20)
#order count(genre)
genre_top20$Genre=genre_top20$Genre %>% factor(levels = genre_top20$Genre[order(-genre_top20$count)])
g1=ggplot(genre_top20,aes(x=genre_top20$Genre,y=count))
g1+geom_bar(stat = "identity",fill = "dodgerblue3")+theme_minimal()+theme(axis.text.x=element_text(angle=45,hjust=1)) +labs(title = "Top20 genre in Spotify",x="Genre",y="The count of genre")
Explore the factor of Top50 music
As you can see Top20 genres diagram, we will find that most of music seem to be high beat or more energy (ex:dance pop and canadian hip hop). As a result, let me just find out.
#Beat
top50$beat_band=top50$Beats.Per.Minute %>% cut2(g=3,minmax = F)
top50$beat_band %>% summary()## [ 85,100) [100,136) [136,190]
## 19 16 15top50$beat_band=top50$beat_band %>% factor(labels = c("Low beat"," Medium","High beat"))
g3=ggplot(data = top50,aes(x=beat_band,y=top50$Popularity))
g3+geom_boxplot(fill=c("#FFD700", "#FFA500", "#FF7F00"))+labs(x="The level of beat",y="Popularity")
#Energy
top50$energy_band=top50$Energy %>% cut2(g=3,minmax = F)
top50$energy_band %>% summary()## [32,62) [62,72) [72,88]
## 17 17 16top50$energy_band=top50$energy_band %>% factor(labels = c("Less energy"," Medium","More energy"))
g4=ggplot(data = top50,aes(x=energy_band,y=top50$Popularity))
g4+geom_boxplot(fill=c("#FFD700", "#FFA500", "#FF7F00"))+labs(x="The level of energy",y="Popularity") 
#Danceability
top50$Danceability_band=top50$Danceability %>% cut2(g=3,minmax = F)
top50$Danceability_band %>% summary()## [29,70) [70,78) [78,90]
## 18 16 16top50$Danceability_band=top50$Danceability_band %>% factor(labels = c("Less danceable"," Medium","More danceable"))
g5=ggplot(data = top50,aes(x=Danceability_band,y=top50$Popularity))
g5+geom_boxplot(fill=c("#FFD700", "#FFA500", "#FF7F00"))+labs(x="The level of danceability",y="Popularity")
Multivariate data
m1=top50 %>% ggplot(aes(x=Beats.Per.Minute,y=Speechiness.,colour=Popularity))
m1+geom_point()+scale_fill_continuous(name="Popularity")+labs(x="Beat per minute",y="Speechiness")+ geom_smooth(method = "lm")+facet_grid(.~beat_band)
m2=top50 %>% ggplot(aes(x=Energy,y=Loudness..dB..,colour=Popularity))
m2+geom_point()+scale_fill_continuous(name="Popularity")+labs(x="Energy",y="Loudness")+ geom_smooth(method = "lm")
Interactive data visualisation
p1=top50 %>% plot_ly(x = ~Beats.Per.Minute, y = ~Speechiness.,
type = "scatter", mode = "markers",color =top50$energy_band,size=top50$Popularity) %>%
layout(yaxis = list(zeroline = F, title = "Beats.Per.Minute"),
xaxis = list(zeroline = FALSE, title = "Loudness..dB"))
p1## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.
## Warning: `line.width` does not currently support multiple values.Reference
Dataset resourced from : https://www.kaggle.com/leonardopena/top50spotify2019 and 50 songs 13 variables Data were stracted from: http://organizeyourmusic.playlistmachinery.com/