raw_data['max_user'] = 99473
raw_data['max_item'] = 450166
batch_size = 8000
test_batch_size = 1000
display_itr = 5000
train_dataset = ImplicitDataset(raw_data['train_data'], raw_data['max_user'], raw_data['max_item'], name='Train')
val_dataset = ImplicitDataset(raw_data['val_data'], raw_data['max_user'], raw_data['max_item'], name='Val')
test_dataset = ImplicitDataset(raw_data['test_data'], raw_data['max_user'], raw_data['max_item'], name='Test')
model = BPR(batch_size=batch_size, max_user=train_dataset.max_user(), max_item=train_dataset.max_item(),
dim_embed=100, opt='Adam', sess_config=None, l2_reg=0.001)
sampler = PairwiseSampler(batch_size=batch_size, dataset=train_dataset, num_process=5)
model_trainer = ImplicitModelTrainer(batch_size=batch_size, test_batch_size=test_batch_size,
train_dataset=train_dataset, model=model, sampler=sampler,
eval_save_prefix="bpr-amazon")
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
precision_evaluator = Precision(precision_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
ndcg_evaluator = NDCG(ndcg_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
model.load("bpr-amazon")
model_trainer._eval_manager = ImplicitEvalManager(evaluators=[auc_evaluator, recall_evaluator, ndcg_evaluator, precision_evaluator])
model_trainer._num_negatives = 200
model_trainer._exclude_positives([train_dataset, val_dataset, test_dataset])
model_trainer._sample_negatives(seed=10)
model_trainer._eval_save_prefix = "bpr-amazon-test"
model_trainer._evaluate_partial(test_dataset)
max_item=train_dataset.max_item(),
dim_embed=50,
opt='Adam',
sess_config=None,
l2_reg=0.1)
sampler = PairwiseSampler(batch_size=batch_size,
dataset=train_dataset,
num_process=5)
model_trainer = ImplicitModelTrainer(batch_size=batch_size,
test_batch_size=test_batch_size,
train_dataset=train_dataset,
model=cml_model,
sampler=sampler,
eval_save_prefix="cml-citeulike")
auc_evaluator = AUC()
recall_evaluator = Recall(recall_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
precision_evaluator = Precision(
precision_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
ndcg_evaluator = NDCG(ndcg_at=[10, 20, 30, 40, 50, 60, 70, 80, 90, 100])
cml_model.load("cml-citeulike")
model_trainer._eval_manager = ImplicitEvalManager(evaluators=[
auc_evaluator, recall_evaluator, ndcg_evaluator, precision_evaluator
])
model_trainer._num_negatives = 200
model_trainer._exclude_positives([test_dataset])
model_trainer._sample_negatives(seed=10)
model_trainer._eval_save_prefix = "cml-citeulike-test"
model_trainer._evaluate_partial(test_dataset)
dataset=train_dataset,
num_process=4)
model_trainer = ImplicitModelTrainer(batch_size=batch_size,
test_batch_size=test_batch_size,
train_dataset=train_dataset,
model=model,
sampler=sampler,
eval_save_prefix="pmf-yahoo",
item_serving_size=666)
auc_evaluator = AUC()
model.load("pmf-yahoo")
model_trainer._eval_manager = ImplicitEvalManager(evaluators=[auc_evaluator])
model_trainer._num_negatives = 200
model_trainer._exclude_positives(
[train_dataset, test_dataset_pos, test_dataset_neg])
model_trainer._sample_negatives(seed=10)
model_trainer._eval_save_prefix = "pmf-yahoo-test-pos"
model_trainer._evaluate_partial(test_dataset_pos)
model_trainer._eval_save_prefix = "pmf-yahoo-test-neg"
model_trainer._evaluate_partial(test_dataset_neg)
def eq(infilename, infilename_neg, trainfilename, gamma=-1.0):
infile = open(infilename, 'rb')
infile_neg = open(infilename_neg, 'rb')
P = pickle.load(infile)
infile.close()
P_neg = pickle.load(infile_neg)
infile_neg.close()
