This project analyzes the most streamed Spotify songs in 2024.

We explore: - Top artists and songs
- Temporal streaming trends
- Impact of collaborations

Dataset Source: Spotify (2024)
File: Most Streamed Spotify Songs 2024.csv

spotify <- read_csv("/Users/gayathrikota/Desktop/DAT 301 Project/Most Streamed Spotify Songs 2024.csv", 
                    locale = locale(encoding = "latin1"))
cols_to_clean <- c(
  'Spotify Streams', 'Spotify Playlist Count', 'Spotify Playlist Reach',
  'YouTube Views', 'YouTube Likes', 'TikTok Posts', 'TikTok Likes',
  'TikTok Views', 'YouTube Playlist Reach', 'AirPlay Spins', 'SiriusXM Spins',
  'Deezer Playlist Reach', 'Pandora Streams', 'Pandora Track Stations',
  'Soundcloud Streams', 'Shazam Counts'
)
char_cols <- spotify %>%
  select(all_of(cols_to_clean)) %>%
  select(where(is.character)) %>%
  colnames()
spotify <- spotify %>%
  mutate(across(all_of(char_cols), ~parse_number(.x))) %>%
  mutate(`Release Date` = mdy(`Release Date`))

  top_songs <- spotify %>%
  arrange(desc(`Spotify Streams`)) %>%
  slice_head(n = 10)

  top_artists <- spotify %>%
  group_by(Artist) %>%
  summarise(Total_Streams = sum(`Spotify Streams`, na.rm = TRUE)) %>%
  arrange(desc(Total_Streams)) %>%
  slice_head(n = 10)

  monthly_streams <- spotify %>%
  mutate(Month = floor_date(`Release Date`, "month")) %>%
  group_by(Month) %>%
  summarise(Total_Streams = sum(`Spotify Streams`, na.rm = TRUE))

collab_keywords <- c("feat", "ft", "&")
spotify <- spotify %>%
  mutate(Collaboration = str_detect(tolower(Track), paste(collab_keywords, collapse = "|")))

collab_stats <- spotify %>%
  group_by(Collaboration) %>%
  summarise(Average_Streams = mean(`Spotify Streams`, na.rm = TRUE))

• Top songs include MILLION DOLLAR BABY, and top artists like Taylor Swift, Kendrick Lamar
  
• Streaming was highest between March–May
  
• Collaborations received more streams than solo songs
  
• I practiced real data cleaning and visualization using R

This project gave me insights into music trends using data science!