-
Notifications
You must be signed in to change notification settings - Fork 0
/
als.py
85 lines (62 loc) · 2.43 KB
/
als.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
import sys
import pandas as pd
import numpy as np
import scipy.sparse as sparse
from scipy.sparse.linalg import spsolve
import random
from sklearn.preprocessing import MinMaxScaler
import implicit
# Load the data like we did before
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 NaN columns
data = raw_data.dropna()
data = data.copy()
# Create a numeric user_id and artist_id column
data['user'] = data['user'].astype("category")
data['artist'] = data['artist'].astype("category")
data['user_id'] = data['user'].cat.codes
data['artist_id'] = data['artist'].cat.codes
# The implicit library expects data as a item-user matrix so we
# create two matricies, one for fitting the model (item-user)
# and one for recommendations (user-item)
sparse_item_user = sparse.csr_matrix((data['plays'].astype(float), (data['artist_id'], data['user_id'])))
sparse_user_item = sparse.csr_matrix((data['plays'].astype(float), (data['user_id'], data['artist_id'])))
# Initialize the als model and fit it using the sparse item-user matrix
model = implicit.als.AlternatingLeastSquares(factors=20, regularization=0.1, iterations=20)
# Calculate the confidence by multiplying it by our alpha value.
alpha_val = 15
data_conf = (sparse_item_user * alpha_val).astype('double')
#Fit the model
model.fit(data_conf)
#---------------------
# FIND SIMILAR ITEMS
#---------------------
# Find the 10 most similar to Jay-Z
item_id = 147068 #Jay-Z
n_similar = 10
# Use implicit to get similar items.
similar = model.similar_items(item_id, n_similar)
# Print the names of our most similar artists
for item in similar:
idx, score = item
print data.artist.loc[data.artist_id == idx].iloc[0]
#------------------------------
# CREATE USER RECOMMENDATIONS
#------------------------------
# Create recommendations for user with id 2025
user_id = 2025
# Use the implicit recommender.
recommended = model.recommend(user_id, sparse_user_item)
artists = []
scores = []
# Get artist names from ids
for item in recommended:
idx, score = item
artists.append(data.artist.loc[data.artist_id == idx].iloc[0])
scores.append(score)
# Create a dataframe of artist names and scores
recommendations = pd.DataFrame({'artist': artists, 'score': scores})
print recommendations
# source: https://medium.com/radon-dev/als-implicit-collaborative-filtering-5ed653ba39fe