def test_bpmf_convergence(self):
n_user = 100
n_item = 200
n_feature = self.n_feature
ratings = make_ratings(n_user,
n_item,
20,
30,
self.rating_choices,
seed=self.seed)
bpmf1 = BPMF(n_user,
n_item,
n_feature,
seed=0,
max_rating=self.max_rat,
min_rating=self.min_rat,
converge=1e-2)
bpmf1.fit(ratings, n_iters=5)
rmse_1 = RMSE(bpmf1.predict(ratings[:, :2]), ratings[:, 2])
bpmf2 = BPMF(n_user,
n_item,
n_feature,
seed=0,
max_rating=self.max_rat,
min_rating=self.min_rat,
converge=1e-1)
bpmf2.fit(ratings, n_iters=5)
rmse_2 = RMSE(bpmf2.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse_1 < rmse_2)
def test_bpmf_with_random_data(self):
n_user = 1000
n_item = 2000
ratings = make_ratings(n_user,
n_item,
20,
30,
self.rating_choices,
seed=self.seed)
bpmf1 = BPMF(n_user,
n_item,
self.n_feature,
max_rating=self.max_rat,
min_rating=self.min_rat,
seed=self.seed)
bpmf1.fit(ratings, n_iters=1)
rmse_1 = RMSE(bpmf1.predict(ratings[:, :2]), ratings[:, 2])
bpmf2 = BPMF(n_user,
n_item,
self.n_feature,
max_rating=self.max_rat,
min_rating=self.min_rat,
seed=self.seed)
bpmf2.fit(ratings, n_iters=3)
rmse_2 = RMSE(bpmf2.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse_1 > rmse_2)
def test_bpmf_not_fitted_err(self):
with self.assertRaises(NotFittedError):
ratings = make_ratings(10,
10,
1,
5,
self.rating_choices,
seed=self.seed)
bpmf = BPMF(10, 10, self.n_feature)
bpmf.predict(ratings[:, :2])
def test_bpmf_convergence(self):
n_user = 100
n_item = 200
n_feature = self.n_feature
ratings = make_ratings(
n_user, n_item, 20, 30, self.rating_choices, seed=self.seed)
bpmf1 = BPMF(n_user, n_item, n_feature,
seed=0,
max_rating=self.max_rat,
min_rating=self.min_rat,
converge=1e-3)
bpmf1.fit(ratings, n_iters=5)
rmse_1 = RMSE(bpmf1.predict(ratings[:, :2]), ratings[:, 2])
bpmf2 = BPMF(n_user, n_item, n_feature,
seed=0,
max_rating=self.max_rat,
min_rating=self.min_rat,
converge=1e-2)
bpmf2.fit(ratings, n_iters=5)
rmse_2 = RMSE(bpmf2.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse_1 < rmse_2)
def test_bpmf_with_ml_100k_rating(self):
n_user = 943
n_item = 1682
n_feature = 10
ratings = self.ratings
bpmf = BPMF(n_user, n_item, n_feature,
max_rating=5.,
min_rating=1.,
seed=self.seed)
bpmf.fit(ratings, n_iters=30)
rmse = RMSE(bpmf.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse < 0.85)
def test_bpmf_with_ml_100k_rating(self):
n_user = 943
n_item = 1682
n_feature = 10
ratings = self.ratings
bpmf = BPMF(n_user,
n_item,
n_feature,
max_rating=5.,
min_rating=1.,
seed=self.seed)
bpmf.fit(ratings, n_iters=15)
rmse = RMSE(bpmf.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse < 0.85)
def test_bpmf_with_random_data(self):
n_user = 1000
n_item = 2000
ratings = make_ratings(
n_user, n_item, 20, 30, self.rating_choices, seed=self.seed)
bpmf1 = BPMF(n_user, n_item, self.n_feature,
max_rating=self.max_rat,
min_rating=self.min_rat,
seed=self.seed)
bpmf1.fit(ratings, n_iters=1)
rmse_1 = RMSE(bpmf1.predict(ratings[:, :2]), ratings[:, 2])
bpmf2 = BPMF(n_user, n_item, self.n_feature,
max_rating=self.max_rat,
min_rating=self.min_rat,
seed=self.seed)
bpmf2.fit(ratings, n_iters=3)
rmse_2 = RMSE(bpmf2.predict(ratings[:, :2]), ratings[:, 2])
self.assertTrue(rmse_1 > rmse_2)
train = ratings[:train_size]
validation = ratings[train_size:]
# models settings; do now the loop over several n_features.
results = pd.DataFrame(
columns=['Number of features', 'Train RMSE', 'Test RMSE'])
n_features_list = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]
eval_iters = 50
for n_feature in n_features_list:
print(
"n_user: %d, n_item: %d, n_feature: %d, training size: %d, validation size: %d"
% (n_user, n_item, n_feature, train.shape[0], validation.shape[0]))
bpmf = BPMF(n_user=n_user,
n_item=n_item,
n_feature=n_feature,
max_rating=5.,
min_rating=1.,
seed=0)
train_rmse_list, test_rmse_list = bpmf.fit(train,
validation,
n_iters=eval_iters)
row = pd.DataFrame({
'Number of features': n_feature,
'Train RMSE': train_rmse_list,
'Test RMSE': test_rmse_list
})
results = results.append(row)
results.to_csv("results/1M_movielens_features{}_iterations{}.csv".format(
# -*- coding: utf-8 -*-
"""
Created on Sun May 26 17:34:22 2019
@author: dblab
"""
import numpy as np
from recommend.bpmf import BPMF
from recommend.utils.evaluation import RMSE
from recommend.utils.datasets import load_movielens_1m_ratings
# load user ratings
ratings = load_movielens_1m_ratings('ml-1m/ratings.dat')
n_user = max(ratings[:, 0])
n_item = max(ratings[:, 1])
ratings[:,
(0, 1)] -= 1 # shift ids by 1 to let user_id & movie_id start from 0
# fit model
bpmf = BPMF(n_user=n_user,
n_item=n_item,
n_feature=10,
max_rating=5.,
min_rating=1.,
seed=0).fit(ratings, n_iters=20)
RMSE(bpmf.predict(ratings[:, :2]), ratings[:, 2]) # training RMSE
# predict ratings for user 0 and item 0 to 9:
print(bpmf.predict(np.array([[0, i] for i in range(10)])))
ratings = load_movielens_1m_ratings(rating_file)
n_user = max(ratings[:, 0])
n_item = max(ratings[:, 1])
# shift user_id & movie_id by 1. let user_id & movie_id start from 0
ratings[:, (0, 1)] -= 1
# split data to training & testing
train_pct = 0.9
rand_state.shuffle(ratings)
train_size = int(train_pct * ratings.shape[0])
train = ratings[:train_size]
validation = ratings[train_size:]
# models settings
n_feature = 20
eval_iters = 50
print("n_user: %d, n_item: %d, n_feature: %d, training size: %d, validation size: %d" % (
n_user, n_item, n_feature, train.shape[0], validation.shape[0]))
bpmf = BPMF(n_user=n_user, n_item=n_item, n_feature=n_feature,
max_rating=5., min_rating=1., seed=0)
bpmf.fit(train, n_iters=eval_iters)
train_preds = bpmf.predict(train[:, :2])
train_rmse = RMSE(train_preds, train[:, 2])
val_preds = bpmf.predict(validation[:, :2])
val_rmse = RMSE(val_preds, validation[:, 2])
print("after %d iteration, train RMSE: %.6f, validation RMSE: %.6f" %
(eval_iters, train_rmse, val_rmse))
from recommend.bpmf import BPMF
from recommend.utils.evaluation import RMSE
from recommend.utils.datasets import load_movielens_1m_ratings, load_movielens_movies, load_movielens_users
#load user ratings
from test import userInfo
ratings = load_movielens_1m_ratings('ml-1m/ratings.dat')
n_user = max(ratings[:, 0])
n_item = max(ratings[:, 1])
ratings[:, (0, 1)] -= 1 #shift ids by 1 to let user_id &movie_id start from 0
#fit model
bpmf = BPMF(n_user=n_user,
n_item=n_item,
n_feature=10,
max_rating=5.,
min_rating=1.,
seed=0).fit(ratings, n_iters=5)
#traing RMSE
rmse = RMSE(bpmf.predict(ratings[:, :2]), ratings[:, 2])
print("RMSE= 1 ---", rmse)
#predict rating for user 0 and item 0 to 9
#输入的用户id
userId = 5
#输入要推荐的电影集合item 0 to endmovieNum-1
endmovieNum = n_item
#输入要显示的前五个movie
topN = 5
array = bpmf.predict(np.array([[userId, i] for i in xrange(endmovieNum)]))
def test_bpmf_not_fitted_err(self):
with self.assertRaises(NotFittedError):
ratings = make_ratings(
10, 10, 1, 5, self.rating_choices, seed=self.seed)
bpmf = BPMF(10, 10, self.n_feature)
bpmf.predict(ratings[:, :2])