Mini Project done

analysis_queries.sql

@@ -0,0 +1,82 @@
+USE MusicAnalyticsDB;
+
+-- Which are the most popular tracks in the Spotify Top 50, and who performs them?
+SELECT
+    g.genre_name,
+    COUNT(*) AS tracks,
+    ROUND(AVG(t.popularity),2) AS average_popularity
+FROM Tracks t
+JOIN Genres g
+    ON t.genre_id = g.genre_id
+GROUP BY g.genre_name
+ORDER BY average_popularity DESC;
+
+-- Because many genres in our dataset only have one song, we will filter out genres represented by only one track.
+SELECT
+    g.genre_name,
+    COUNT(*) AS tracks,
+    ROUND(AVG(t.popularity),2) AS average_popularity
+FROM Tracks t
+JOIN Genres g
+    ON t.genre_id = g.genre_id
+GROUP BY g.genre_name
+HAVING COUNT(*) >= 2
+ORDER BY average_popularity DESC;
+
+-- Which genres have the highest average popularity among the Spotify Top 50 tracks?
+SELECT
+    g.genre_name,
+    COUNT(*) AS number_of_tracks,
+    ROUND(AVG(t.popularity),2) AS average_popularity
+FROM Tracks t
+JOIN Genres g
+    ON t.genre_id = g.genre_id
+GROUP BY g.genre_name
+ORDER BY average_popularity DESC;
+
+-- What are the average audio characteristics of highly popular songs?
+SELECT
+    ROUND(AVG(energy),2) AS avg_energy,
+    ROUND(AVG(danceability),2) AS avg_danceability,
+    ROUND(AVG(acousticness),2) AS avg_acousticness,
+    ROUND(AVG(speechiness),2) AS avg_speechiness
+FROM Audio_Features af
+JOIN Tracks t
+    ON af.track_id = t.track_id
+WHERE t.popularity >= 90;
+
+-- Which songs perform better than the average popularity of the Spotify Top 50?
+SELECT
+    track_name,
+    popularity
+FROM Tracks
+WHERE popularity >
+(
+    SELECT AVG(popularity)
+    FROM Tracks
+)
+ORDER BY popularity DESC;
+
+-- Which Grammy-nominated artists also achieve high popularity on Spotify?
+SELECT
+    a.artist_name,
+    COUNT(DISTINCT gn.nomination_id) AS nominations,
+    ROUND(AVG(t.popularity),2) AS avg_popularity
+FROM Artists a
+JOIN Grammy_Nominations gn
+    ON a.artist_id = gn.artist_id
+JOIN Tracks t
+    ON a.artist_id = t.artist_id
+GROUP BY a.artist_name
+ORDER BY nominations DESC, avg_popularity DESC;
+
+-- What are the average audio characteristics of the Spotify Top 50 songs?
+SELECT
+    ROUND(AVG(bpm),2) AS bpm,
+    ROUND(AVG(energy),2) AS energy,
+    ROUND(AVG(danceability),2) AS danceability,
+    ROUND(AVG(acousticness),2) AS acousticness,
+    ROUND(AVG(speechiness),2) AS speechiness,
+    ROUND(AVG(valence),2) AS valence
+FROM Audio_Features;
+

artists.csv

@@ -0,0 +1,39 @@
+artist_id,artist_name
+1,Shawn Mendes
+2,Anuel AA
+3,Ariana Grande
+4,Ed Sheeran
+5,Post Malone
+6,Lil Tecca
+7,Sam Smith
+8,Lil Nas X
+9,Billie Eilish
+10,Bad Bunny
+11,DJ Snake
+12,Lewis Capaldi
+13,Sech
+14,Drake
+15,Chris Brown
+16,J Balvin
+17,Y2K
+18,Lizzo
+19,MEDUZA
+20,Jhay Cortez
+21,Lunay
+22,Tones and I
+23,Ali Gatie
+24,Daddy Yankee
+25,The Chainsmokers
+26,Maluma
+27,Young Thug
+28,Katy Perry
+29,Martin Garrix
+30,Jonas Brothers
+31,Lauv
+32,Kygo
+33,Taylor Swift
+34,Lady Gaga
+35,Khalid
+36,ROSALÍA
+37,Marshmello
+38,Nicky Jam

audio_features.csv

@@ -0,0 +1,51 @@
+track_id,bpm,energy,danceability,loudness_db,liveness,valence,length,acousticness,speechiness
+1,117,55,76,-6,8,75,191,4,3
+2,105,81,79,-4,8,61,302,8,9
+3,190,80,40,-4,16,70,186,12,46
+4,93,65,64,-8,8,55,198,12,19
+5,150,65,58,-4,11,18,175,45,7
+6,102,68,80,-5,9,84,220,9,4
+7,180,64,75,-6,7,23,131,2,29
+8,111,68,48,-5,8,35,202,15,9
+9,136,62,88,-6,11,64,157,5,10
+10,135,43,70,-11,10,56,194,33,38
+11,176,62,61,-5,24,24,251,60,31
+12,96,71,82,-4,15,38,185,28,7
+13,110,41,50,-6,11,45,182,75,3
+14,176,79,73,-2,6,76,288,7,20
+15,101,50,83,-4,12,10,205,10,5
+16,93,45,70,-7,16,14,261,12,15
+17,176,65,75,-6,11,43,243,15,32
+18,90,48,76,-6,7,91,158,56,5
+19,130,39,84,-8,14,50,161,18,8
+20,158,62,72,-3,12,41,173,11,11
+21,124,74,68,-7,7,63,153,4,3
+22,154,59,70,-6,12,48,115,34,8
+23,92,79,81,-4,9,58,309,14,7
+24,92,78,80,-4,44,80,266,36,4
+25,135,45,67,-11,12,68,195,25,30
+26,124,82,69,-4,13,87,191,49,6
+27,98,59,82,-6,18,54,210,69,10
+28,96,46,73,-7,19,40,213,37,3
+29,94,86,74,-3,6,66,193,11,6
+30,93,79,64,-4,36,94,222,3,25
+31,85,51,29,-8,10,36,210,12,4
+32,140,32,78,-11,9,33,179,59,33
+33,96,71,78,-5,9,68,176,22,28
+34,98,59,80,-7,13,18,200,2,15
+35,100,88,77,-5,32,39,224,19,6
+36,114,72,66,-7,14,32,164,18,6
+37,176,70,75,-5,11,62,226,14,34
+38,152,82,72,-5,36,91,162,13,5
+39,138,73,84,-5,11,95,181,4,6
+40,95,56,81,-6,6,68,199,48,7
+41,104,68,69,-7,10,40,228,2,3
+42,85,68,77,-6,7,73,171,1,5
+43,96,39,57,-6,23,32,216,37,3
+44,136,40,90,-9,6,35,198,5,13
+45,98,69,88,-4,5,75,162,39,12
+46,88,62,66,-2,58,44,182,7,5
+47,176,75,67,-4,8,80,202,24,6
+48,100,79,69,-3,17,67,214,19,5
+49,104,70,59,-6,41,50,218,23,3
+50,95,79,75,-6,7,61,206,21,12

create_database.py

@@ -0,0 +1,30 @@
+import mysql.connector
+from pathlib import Path
+from getpass import getpass
+
+password = getpass("MySQL password: ")
+BASE_DIR = Path(__file__).resolve().parent
+
+connection = mysql.connector.connect(
+    host="localhost",
+    user="root",
+    password=password
+)
+
+cursor = connection.cursor()
+
+with open(BASE_DIR / "schema.sql", "r") as file:
+    sql_script = file.read()
+
+# Execute each SQL statement
+for statement in sql_script.split(";"):
+    statement = statement.strip()
+    if statement:
+        cursor.execute(statement)
+
+connection.commit()
+
+cursor.close()
+connection.close()
+
+print("Database and tables created successfully!")