Million Songs Dataset Analysis using Python | Recommendation Engine | Machine Learning Tutorial

Immerse yourself in the world of music analysis with Python! This tutorial explores the Million Songs Dataset, delving into recommendation engine techniques and machine learning algorithms to uncover music insights and create personalized recommendations. Enhance your skills in data analysis, machine learning, and unlock the power of music recommendation. Join this comprehensive project tutorial to dive into the vast world of the Million Songs Dataset and revolutionize the way we discover and enjoy music. #MillionSongsDataset #Python #RecommendationEngine #MachineLearning #DataAnalysis #MusicRecommendation

In this project tutorial, we are going to build a recommendation engine of songs from the Million songs dataset depending on the user's song history and list recommended songs by popularity.

You can watch the step by step explanation video tutorial down below

Million Songs Dataset contains of two files: triplet_file and metadata_file. The triplet_file contains user_id, song_id and listen time. The metadata_file contains song_id, title, release, year and artist_name. Million Songs Dataset is a mixture of song from various website with the rating that users gave after listening to the song.

There are 3 types of recommendation system: content-based, collaborative and popularity.

Download the dataset here

import pandas as pd
 import numpy as np
 import Recommenders as Recommenders

Let us load the first data for processing

song_df_1 = pd.read_csv('triplets_file.csv')
 song_df_1.head()

Let us load the second data for processing

song_df_2 = pd.read_csv('song_data.csv')
 song_df_2.head()

Now we combine the two data into one

# combine both data
 song_df = pd.merge(song_df_1, song_df_2.drop_duplicates(['song_id']), on='song_id', how='left')
 song_df.head()

Let us see the length of the data

print(len(song_df_1), len(song_df_2))

2000000 1000000

len(song_df)

2000000

We are going to combine two keywords into a new feature

# creating new feature combining title and artist name
 song_df['song'] = song_df['title']+' - '+song_df['artist_name']
 song_df.head()

# taking top 10k samples for quick results
 song_df = song_df.head(10000)

# cumulative sum of listen count of the songs
 song_grouped = song_df.groupby(['song']).agg({'listen_count':'count'}).reset_index()
 song_grouped.head()

grouped_sum = song_grouped['listen_count'].sum()
 song_grouped['percentage'] = (song_grouped['listen_count'] / grouped_sum ) * 100
 song_grouped.sort_values(['listen_count', 'song'], ascending=[0,1])

pr = Recommenders.popularity_recommender_py()

pr.create(song_df, 'user_id', 'song')

Now we will display the top 10 popular songs

# display the top 10 popular songs
 pr.recommend(song_df['user_id'][5])

pr.recommend(song_df['user_id'][100])

ir = Recommenders.item_similarity_recommender_py()
 ir.create(song_df, 'user_id', 'song')

user_items = ir.get_user_items(song_df['user_id'][5])

Now we will display the song history from the user

# display user songs history
 for user_item in user_items:
  print(user_item)

# give song recommendation for that user
 ir.recommend(song_df['user_id'][5])

# give related songs based on the words
 ir.get_similar_items(['Oliver James - Fleet Foxes', 'The End - Pearl Jam'])

In this project tutorial, we have explored the Millions Songs dataset as a recommendation engine machine learning project. We explored the dataset with different recommendation engines, based on popularity and item content from the data by the user's song history.

Get the project notebook from here

Thanks for reading the article!!!

Check out more project videos from the YouTube channel Hackers Realm