main.py

"""
Attribution: https://github.com/AIPI540/AIPI540-Deep-Learning-Applications/

Jon Reifschneider
Brinnae Bent 

"""

import streamlit as st
from PIL import Image
import numpy as np
import os
import numpy as np
import pandas as pd
import pandas as pd
import os
import json
import pandas as pd
import torch
import numpy as np
import pandas as pd
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt

class NNColabFiltering(nn.Module):

    def __init__(self, n_playlists, n_artists, embedding_dim_users, embedding_dim_items, n_activations, rating_range):
        super().__init__()
        self.user_embeddings = nn.Embedding(num_embeddings=n_playlists,embedding_dim=embedding_dim_users)
        self.item_embeddings = nn.Embedding(num_embeddings=n_artists,embedding_dim=embedding_dim_items)
        self.fc1 = nn.Linear(embedding_dim_users+embedding_dim_items,n_activations)
        self.fc2 = nn.Linear(n_activations,1)
        self.rating_range = rating_range

    def forward(self, X):
        # Get embeddings for minibatch
        embedded_users = self.user_embeddings(X[:,0])
        embedded_items = self.item_embeddings(X[:,1])
        # Concatenate user and item embeddings
        embeddings = torch.cat([embedded_users,embedded_items],dim=1)
        # Pass embeddings through network
        preds = self.fc1(embeddings)
        preds = F.relu(preds)
        preds = self.fc2(preds)
        # Scale predicted ratings to target-range [low,high]
        preds = torch.sigmoid(preds) * (self.rating_range[1]-self.rating_range[0]) + self.rating_range[0]
        return preds

def generate_recommendations(artist_album, playlists, model, playlist_id, device, top_n=10, batch_size=1024):
    '''
    Loads the prefetched data from the output dir

    Inputs:
        artist_album: the dataframe containing the mappings for the artist and albums
        playlists: the dataframe containing the playlists contents
        model: the trained model
        playlist_id: the playlist id to generate recommendation for
        device: the gpu or cpu device define by torch
        top_n: the number of recommendations to generate
        batch_size: the batch size to use

    Returns:
        album: the recommended album
        playlists: the recommended artist
    '''
    model.eval()

    all_movie_ids = torch.tensor(artist_album['artist_album_id'].values, dtype=torch.long, device=device)
    user_ids = torch.full((len(all_movie_ids),), playlist_id, dtype=torch.long, device=device)

    all_predictions = torch.zeros(len(all_movie_ids), device=device)

    with torch.no_grad():
        for i in range(0, len(all_movie_ids), batch_size):
            batch_user_ids = user_ids[i:i+batch_size]
            batch_movie_ids = all_movie_ids[i:i+batch_size]

            input_tensor = torch.stack([batch_user_ids, batch_movie_ids], dim=1)
            batch_predictions = model(input_tensor).squeeze()
            all_predictions[i:i+batch_size] = batch_predictions

    predictions = all_predictions.cpu().numpy()
    albums_listened = set(playlists.loc[playlists['playlist_id'] == playlist_id, 'artist_album_id'].tolist())
    unlistened_mask = np.isin(artist_album['artist_album_id'].values, list(albums_listened), invert=True)

    top_indices = np.argsort(predictions[unlistened_mask])[-top_n:][::-1]
    recs = artist_album['artist_album_id'].values[unlistened_mask][top_indices]

    recs_names = artist_album.loc[artist_album['artist_album_id'].isin(recs)]
    album, artist = recs_names['album_name'].values, recs_names['artist_name'].values

    return album.tolist(), artist.tolist()   


def load_data():
    '''
    Loads the prefetched data from the output dir

    Inputs:

    Returns:
        artist_album: pandas DataFrame with the best sentiment score
        playlists: pandas DataFrame with the worst sentiment score
    '''
    artist_album = pd.read_csv(os.path.join(os.getcwd() + '/data/processed','artist_album.csv'))
    artist_album = artist_album[['artist_album_id','artist_album','artist_name','album_name']].drop_duplicates()
    playlists = pd.read_csv(os.path.join(os.getcwd() + '/data/processed','playlists.csv'))

    return artist_album, playlists

artist_album, playlists = load_data()
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = torch.load('models/recommender.pt', map_location=device)
    
if __name__ == '__main__':  
    
    st.header('Spotify Playlists')
    
    img1, img2 = st.columns(2)

    music_notes = Image.open('assets/music_notes.png')
    img1.image(music_notes, use_column_width=True)

    trumpet = Image.open('assets/trumpet.png')
    img2.image(trumpet, use_column_width=True)
    
    with st.sidebar:
        playlist_name = st.selectbox(
            "Playlist Selection",
            (   list(set(playlists['name'].dropna()))            )
        )
    playlist_id = playlists['playlist_id'][playlists['name'] == playlist_name].values[0]
    albums, artists = generate_recommendations(artist_album, playlists, model, playlist_id, device)
    
    st.dataframe(data=playlists[['artist_name','album_name','track_name']][playlists['playlist_id'] == playlist_id])
    
    st.write(f"*Recommendations for playlist:* {playlists['name'][playlists['playlist_id'] == playlist_id].values[0]}")
    col1, col2 = st.columns(2)
    with col1:
        st.write(f'Artist')
    with col2:
        st.write(f'Album')
        
    for album, artist in zip(albums, artists):     
        with col1:
            st.write(f"**{artist}**")
        with col2:
            st.write(f"**{album}**")