def __init__(self, **kwds):
super(TestRecommenderNonDeepLearning, self).__init__(**kwds)
def _pre_fit(self, learning_rate, neg_ratio, reg_rate, **kwds):
# used to declare variables and do the non-deep learning fit process, such as computing similarities and
# neighbours for knn-based models
self._info(
f'doing pre-fit with learning_rate={learning_rate}, neg_ratio={neg_ratio}, reg_rate={reg_rate}'
)
pass
def _sample_batch(self, batch_size, **kwds):
raise NotImplemented # since it's non-deep learning based, no need for batch training
def _predict_batch(self, batch_samples, **kwds):
raise NotImplemented # since it's non-deep learning based, no need for batch training
def _compute_batch_loss(self, predictions, desired_values, **kwds):
raise NotImplemented # since it's non-deep learning based, no need for batch training
def _predict(self, uid, iid, **kwds):
return 5 # predict for a (user, item) pair
ds_train = get_train_dataset('ml-100k', verbose=False)
print('TestRecommenderNonDeepLearning')
recommender = TestRecommenderNonDeepLearning(verbose=True)
recommender.fit(ds_train, epochs=2, batch_size=10)
print(recommender.predict(1, 1))
def train_interaction_ds():
return get_train_dataset('ml-100k')
from DRecPy.Recommender import CDAE
from DRecPy.Dataset import get_train_dataset
from DRecPy.Dataset import get_test_dataset
from DRecPy.Evaluation.Processes import ranking_evaluation
import time
ds_train = get_train_dataset('ml-100k')
ds_test = get_test_dataset('ml-100k')
start_train = time.time()
cdae = CDAE(hidden_factors=50, corruption_level=0.2, loss='bce', seed=10)
cdae.fit(ds_train,
learning_rate=0.001,
reg_rate=0.001,
epochs=50,
batch_size=64,
neg_ratio=5)
print("Training took", time.time() - start_train)
print(
ranking_evaluation(cdae,
ds_test,
k=[1, 5, 10],
novelty=True,
n_test_users=100,
n_pos_interactions=1,
n_neg_interactions=100,
generate_negative_pairs=True,
seed=10,
max_concurrent_threads=4,
verbose=True))
def test_get_train_dataset_4():
ret = get_train_dataset('bx')
assert (len(ret), len(ret.columns)) == (845183, 4)
assert next(ret.values(columns=['interaction', 'item', 'user'])) == \
{'user': 276762, 'item': '034544003X', 'interaction': 0}
def test_get_train_dataset_5():
ret = get_train_dataset('ml-1m')
assert (len(ret), len(ret.columns)) == (939809, 5)
assert next(ret.values(columns=['interaction', 'item', 'user', 'timestamp'])) == \
{'user': 1, 'item': 1193, 'interaction': 5, 'timestamp': 978300760}
def test_get_train_dataset_3():
ret = get_train_dataset('ml-100k', force_out_of_memory=True)
assert isinstance(ret, DatabaseInteractionDataset)
def test_get_train_dataset_2():
ret = get_train_dataset('ml-100k')
assert isinstance(ret, MemoryInteractionDataset)
def test_get_train_dataset_1():
ret = get_train_dataset('ml-100k')
assert (len(ret), len(ret.columns)) == (90570, 5)
assert next(ret.values(columns=['interaction', 'item', 'user', 'timestamp'])) == \
{'user': 1, 'item': 1, 'interaction': 5, 'timestamp': 874965758}
def test_get_train_dataset_0():
try:
get_train_dataset('')
except FileNotFoundError as e:
assert str(e) == '"" is not a valid dataset. Supported datasets: ml-100k, ml-1m, ml-10m, ml-20m, bx.'
from DRecPy.Dataset import get_train_dataset
from DRecPy.Dataset import get_test_dataset
from DRecPy.Dataset import get_full_dataset
from DRecPy.Dataset import available_datasets
print('Available datasets', available_datasets())
# Reading the ml-100k full dataset and prebuilt train and test datasets.
print('ml-100k full dataset', get_full_dataset('ml-100k'))
print('ml-100k train dataset', get_train_dataset('ml-100k'))
print('ml-100k test dataset', get_test_dataset('ml-100k'))
# Reading the ml-1m full dataset and generated train and test datasets using out of memory storage.
print('ml-1m full dataset', get_full_dataset('ml-1m', force_out_of_memory=True))
print('ml-1m train dataset', get_train_dataset('ml-1m', force_out_of_memory=True))
print('ml-1m test dataset', get_test_dataset('ml-1m', force_out_of_memory=True))
# Showcase some dataset operations
ds_ml = get_full_dataset('ml-100k')
print('Minimum rating value:', ds_ml.min('interaction'))
print('Unique rating values:', ds_ml.unique('interaction').values_list())
ds_ml.apply('interaction', lambda x: x / ds_ml.max('interaction')) # standardize the rating value
print('New values', ds_ml.values_list()[:5])