def _get_synthetic_data(num_users=100,
num_items=100,
num_interactions=10000,
randomness=0.01,
order=2,
random_state=None):
interactions = synthetic.generate_sequential(
num_users=num_users,
num_items=num_items,
num_interactions=num_interactions,
concentration_parameter=randomness,
order=order,
random_state=random_state)
print('Max prob {}'.format(
(np.unique(interactions.item_ids, return_counts=True)[1] /
num_interactions).max()))
train, test = user_based_train_test_split(interactions,
random_state=random_state)
train = train.to_sequence(max_sequence_length=10)
test = test.to_sequence(max_sequence_length=10)
return train, test
def _get_synthetic_data(num_users=100,
num_items=100,
num_interactions=10000,
randomness=0.01,
order=2,
max_sequence_length=10,
random_state=None):
interactions = synthetic.generate_sequential(num_users=num_users,
num_items=num_items,
num_interactions=num_interactions,
concentration_parameter=randomness,
order=order,
random_state=random_state)
print('Max prob {}'.format((np.unique(interactions.item_ids,
return_counts=True)[1] /
num_interactions).max()))
train, test = user_based_train_test_split(interactions,
random_state=random_state)
train = train.to_sequence(max_sequence_length=max_sequence_length,
step_size=None)
test = test.to_sequence(max_sequence_length=max_sequence_length,
step_size=None)
return train, test
def preprocess_generated(num_users = 100, num_items = 1000, num_interactions = 10000):
from spotlight.datasets.synthetic import generate_sequential
from spotlight.cross_validation import user_based_train_test_split
dataset = generate_sequential(num_users=num_users,
num_items=num_items,
num_interactions=num_interactions,
concentration_parameter=0.0001,
order=3)
dat = {key: dat for key, dat in zip(["train","test"], user_based_train_test_split(dataset))}
dat_seq = {key : val.to_sequence() for key, val in dat.items()}
ind2val = {}
ind2val['itemId'] = {idx : item for item, idx in enumerate(range(dataset.item_ids.max()))}
return dat, dat_seq, ind2val
import numpy as np
from spotlight.cross_validation import user_based_train_test_split
from spotlight.evaluation import sequence_mrr_score
from spotlight.sequence.implicit import ImplicitSequenceModel
from spotlight.datasets.synthetic import generate_sequential
dataset = generate_sequential(num_users=100,
num_items=1000,
num_interactions=10000,
concentration_parameter=0.01,
order=3)
train, test = user_based_train_test_split(dataset)
train = train.to_sequence()
test = test.to_sequence()
model = ImplicitSequenceModel(n_iter=3, representation='cnn', loss='bpr')
model.fit(train)
mrr = sequence_mrr_score(model, test)