raw_data['max_item'],
name='Test',
num_negatives=500)
train_sampler = StratifiedPointwiseSampler(pos_ratio=0.2,
batch_size=batch_size,
dataset=train_dataset,
num_process=5)
val_sampler = EvaluationSampler(batch_size=batch_size, dataset=val_dataset)
test_sampler = EvaluationSampler(batch_size=batch_size, dataset=test_dataset)
model = PMF(batch_size=batch_size,
total_users=train_dataset.total_users(),
total_items=train_dataset.total_items(),
dim_user_embed=dim_embed,
dim_item_embed=dim_embed,
save_model_dir='pmf_recommender/',
train=True,
serve=True)
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
model_trainer = ModelTrainer(model=model)
model_trainer.train(total_it=total_it,
eval_it=eval_it,
save_it=save_it,
train_sampler=train_sampler,
eval_samplers=[val_sampler, test_sampler],
evaluators=[auc_evaluator, recall_evaluator])
pos_ratio=pos_ratio)
#Model Trainer
eval_save_prefix = '/home/ubuntu/openrec/models/fhmf_models/{0}_{1}_{2}_{3}_{4}_{5}_{6}_{7}_{8}_{9}/'.format(
sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4], sys.argv[5],
sys.argv[6], sys.argv[7], sys.argv[8], sys.argv[9], sys.argv[10])
if dataset_name == "amazon_book":
eval_save_prefix = None
model_trainer = ImplicitModelTrainer(batch_size=batch_size,
test_batch_size=test_batch_size,
train_dataset=train_dataset,
model=fhmf_model,
sampler=sampler,
eval_save_prefix=eval_save_prefix)
#Evaluators
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[10, 50, 100, 300])
#mse_evaluator = MSE()
#Train
model_trainer.train(num_itr=num_itr,
display_itr=display_itr,
eval_datasets=[focused_val_set, focused_test_set],
evaluators=[auc_evaluator, recall_evaluator],
num_negatives=num_negatives)
elif recommender == "PMF":
model = PMF(batch_size=batch_size,
max_user=train_dataset.max_user(),
max_item=train_dataset.max_item(),
dim_embed=50,
opt='Adam',
trainset_path = "/Users/xuan/Documents/Specialization Project/openrec/dataset/citeulike/user_data_train.npy"
###
#
trainset = np.load(trainset_path)
trainset = trainset['user_id']
frequency = dict()
for i in trainset:
if i in frequency:
frequency[i] += 1
else:
frequency[i] = 1
#
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[10])
precision_evaluator = Precision(precision_at=[10])
ndcg_evaluator = NDCG(ndcg_at=[10])
f = open(infilename, 'rb')
p = pickle.load(f)
f.close()
score_per_user = dict()
count_per_user = dict()
for user in p['users']:
neg_scores = p['results'][user][:p['num_negatives']]
for i in range(len(p['user_items'][user][p['num_negatives'] : ])):
pos_score = p['results'][user][p['num_negatives'] + i]
rank_above = np.array([ float(np.sum(neg_scores > pos_score)) ])
total_items,
sortby='ts',
name='Test')
train_sampler = TemporalSampler(batch_size=batch_size,
max_seq_len=max_seq_len,
dataset=train_dataset,
num_process=1)
test_sampler = TemporalEvaluationSampler(dataset=test_dataset,
max_seq_len=max_seq_len)
model = VanillaYouTubeRec(batch_size=batch_size,
total_items=train_dataset.total_items(),
max_seq_len=max_seq_len,
dim_item_embed=dim_item_embed,
save_model_dir='vanilla_youtube_recommender/',
train=True,
serve=True)
model_trainer = ModelTrainer(model=model)
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[100, 200, 300, 400, 500])
model_trainer.train(total_iter=total_iter,
eval_iter=eval_iter,
save_iter=save_iter,
train_sampler=train_sampler,
eval_samplers=[test_sampler],
evaluators=[auc_evaluator, recall_evaluator])
total_users=total_users,
total_items=total_items,
sortby='ts',
name='Test')
train_sampler = TemporalSampler(batch_size=batch_size,
max_seq_len=max_seq_len,
dataset=train_dataset,
num_process=1)
test_sampler = TemporalEvaluationSampler(dataset=test_dataset,
max_seq_len=max_seq_len)
rnn_model = RNNRec(batch_size=batch_size,
dim_item_embed=dim_item_embed,
max_seq_len=max_seq_len,
total_items=train_dataset.total_items(),
num_units=num_units,
save_model_dir='rnn_recommender/',
train=True,
serve=True)
model_trainer = ModelTrainer(model=rnn_model)
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[100, 500])
model_trainer.train(total_iter=total_iter,
eval_iter=eval_iter,
save_iter=save_iter,
train_sampler=train_sampler,
eval_samplers=[test_sampler],
evaluators=[auc_evaluator, recall_evaluator])
