implicit_feedback_als_1.py

import random
import pandas as pd
import numpy as np

import scipy.sparse as sparse
from scipy.sparse.linalg import spsolve
from sklearn.preprocessing import MinMaxScaler

#-------------------------
# LOAD AND PREP THE DATA
#-------------------------
 
raw_data = pd.read_table('data/usersha1-artmbid-artname-plays.tsv')
raw_data = raw_data.drop(raw_data.columns[1], axis=1)
raw_data.columns = ['user', 'artist', 'plays']
 
 # Drop rows with missing values
 data = raw_data.dropna()
  
 # Convert artists names into numerical IDs
 data['user_id'] = data['user'].astype("category").cat.codes
 data['artist_id'] = data['artist'].astype("category").cat.codes
 
 # Create a lookup frame so we can get the artist names back in 
 # readable form later.
 item_lookup = data[['artist_id', 'artist']].drop_duplicates()
 item_lookup['artist_id'] = item_lookup.artist_id.astype(str)
 
 data = data.drop(['user', 'artist'], axis=1)
 
 # Drop any rows that have 0 plays
 data = data.loc[data.plays != 0]
 
 # Create lists of all users, artists and plays
 users = list(np.sort(data.user_id.unique()))
 artists = list(np.sort(data.artist_id.unique()))
 plays = list(data.plays)
 
 # Get the rows and columns for our new matrix
 rows = data.user_id.astype(int)
 cols = data.artist_id.astype(int)
 
 # Contruct a sparse matrix for our users and items containing number of plays
 data_sparse = sparse.csr_matrix((plays, (rows, cols)), shape=(len(users), len(artists)))

By having np.sort(data.user_id.unique())) and np.sort(data.artist_id.unique()), how are you ensuring that plays is mapped to the write user and artist?