/
Recomender.py
87 lines (60 loc) · 2.77 KB
/
Recomender.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Apr 20 22:13:12 2018
@author: kaim
Number of users = 943 | Number of movies = 1682
User-based CF RMSE: 3.124021413841147
Item-based CF RMSE: 3.451685296987593
The sparsity level of MovieLens100K is 93.7%
SVD = 20:
User-based CF MSE: 2.7191063144135477
SVD = 10:
User-based CF MSE: 2.678385972496664
"""
import numpy as np
import pandas as pd
from sklearn import cross_validation as cv
header = ['user_id', 'item_id', 'rating', 'timestamp']
df = pd.read_csv('ml-100k/u.data', sep='\t', names=header)
n_users = df.user_id.unique().shape[0]
n_items = df.item_id.unique().shape[0]
print('Number of users = ' + str(n_users) + ' | Number of movies = ' + str(n_items))
train_data, test_data = cv.train_test_split(df, test_size=0.25)
train_data_matrix = np.zeros((n_users, n_items))
for line in train_data.itertuples():
train_data_matrix[line[1]-1, line[2]-1] = line[3]
test_data_matrix = np.zeros((n_users, n_items))
for line in test_data.itertuples():
test_data_matrix[line[1]-1, line[2]-1] = line[3]
from sklearn.metrics.pairwise import pairwise_distances
user_similarity = pairwise_distances(train_data_matrix, metric='cosine')
item_similarity = pairwise_distances(train_data_matrix.T, metric='cosine')
def predict(ratings, similarity, type='user'):
if type == 'user':
mean_user_rating = ratings.mean(axis=1)
#You use np.newaxis so that mean_user_rating has same format as ratings
ratings_diff = (ratings - mean_user_rating[:, np.newaxis])
pred = mean_user_rating[:, np.newaxis] + similarity.dot(ratings_diff) / np.array([np.abs(similarity).sum(axis=1)]).T
elif type == 'item':
pred = ratings.dot(similarity) / np.array([np.abs(similarity).sum(axis=1)])
return pred
item_prediction = predict(train_data_matrix, item_similarity, type='item')
user_prediction = predict(train_data_matrix, user_similarity, type='user')
from sklearn.metrics import mean_squared_error
from math import sqrt
def rmse(prediction, ground_truth):
prediction = prediction[ground_truth.nonzero()].flatten()
ground_truth = ground_truth[ground_truth.nonzero()].flatten()
return sqrt(mean_squared_error(prediction, ground_truth))
print('User-based CF RMSE: ' + str(rmse(user_prediction, test_data_matrix)))
print('Item-based CF RMSE: ' + str(rmse(item_prediction, test_data_matrix)))
sparsity=round(1.0-len(df)/float(n_users*n_items),3)
print('The sparsity level of MovieLens100K is ' + str(sparsity*100) + '%')
import scipy.sparse as sp
from scipy.sparse.linalg import svds
#get SVD components from train matrix. Choose k.
u, s, vt = svds(train_data_matrix, k = 10)
s_diag_matrix=np.diag(s)
X_pred = np.dot(np.dot(u, s_diag_matrix), vt)
print('User-based CF MSE: ' + str(rmse(X_pred, test_data_matrix)))