METRICS = ['mrr']
MODELS = [
# Only item sets
#Countbased(),
#SVDRecommender(1000, use_title=False),
#AAERecommender(adversarial=True, use_title=False, n_epochs=55, embedding=VECTORS),
#AAERecommender(adversarial=False, n_epochs=1),
#VAERecommender(conditions=None, n_epochs=55, batch_size=1000),
#DAERecommender(conditions=None, n_epochs=55, batch_size=1000),
# Title-enhanced
#SVDRecommender(1000, use_title=True),
#AAERecommender(adversarial=True, use_side_info=True, n_epochs=55, embedding=VECTORS),
#AAERecommender(adversarial=False, use_side_info=["name"], n_epochs=5, embedding=VECTORS),
#DecodingRecommender(n_epochs=55, embedding=VECTORS)
VAERecommender(conditions=CONDITIONS, n_epochs=55, batch_size=1000),
DAERecommender(conditions=CONDITIONS, n_epochs=55, batch_size=1000),
# Generic condition all
#AAERecommender(adversarial=False, conditions=CONDITIONS, n_epochs=55),
#AAERecommender(adversarial=True, conditions=CONDITIONS, n_epochs=55),
#DecodingRecommender(conditions=CONDITIONS, n_epochs=55)
# Put more here...
]
def load(path):
""" Loads a single slice """
with open(path, 'r') as fhandle:
obj = json.load(fhandle)
return obj["playlists"]
'n_hidden': 100,
'normalize_inputs': True,
}
# Models without metadata
BASELINES = [
# RandomBaseline(),
# MostPopular(),
Countbased(),
SVDRecommender(1000, use_title=False),
]
RECOMMENDERS = [
AAERecommender(adversarial=False, lr=0.001, **ae_params),
AAERecommender(prior='gauss', gen_lr=0.001, reg_lr=0.001, **ae_params),
VAERecommender(conditions=None, **vae_params),
DAERecommender(conditions=None, **ae_params)
]
# Metadata to use
CONDITIONS = ConditionList([
('title', PretrainedWordEmbeddingCondition(VECTORS)),
# ('author', CategoricalCondition(embedding_dim=32, reduce="sum",
# sparse=True, embedding_on_gpu=True))
])
# Model with metadata (metadata used as set in CONDITIONS above)
CONDITIONED_MODELS = [
# TODO SVD can use only titles not generic conditions
SVDRecommender(1000, use_title=True),
AAERecommender(adversarial=False,
def main(year,
dataset,
min_count=None,
outfile=None,
drop=1,
baselines=False,
autoencoders=False,
conditioned_autoencoders=False,
all_metadata=True):
""" Main function for training and evaluating AAE methods on DBLP data """
assert baselines or autoencoders or conditioned_autoencoders, "Please specify what to run"
if all_metadata:
# V2 - all metadata
CONDITIONS = ConditionList([
('title', PretrainedWordEmbeddingCondition(VECTORS)),
('venue', PretrainedWordEmbeddingCondition(VECTORS)),
(
'author',
CategoricalCondition(
embedding_dim=32,
reduce="sum", # vocab_size=0.01,
sparse=False,
embedding_on_gpu=True))
])
else:
# V1 - only title metadata
CONDITIONS = ConditionList([
('title', PretrainedWordEmbeddingCondition(VECTORS))
])
#### CONDITOINS defined
ALL_MODELS = []
if baselines:
# Models without metadata
BASELINES = [
# RandomBaseline(),
# MostPopular(),
Countbased(),
SVDRecommender(1000, use_title=False)
]
ALL_MODELS += BASELINES
if not all_metadata:
# SVD can use only titles not generic conditions
ALL_MODELS += [SVDRecommender(1000, use_title=True)]
if autoencoders:
AUTOENCODERS = [
AAERecommender(adversarial=False,
conditions=None,
lr=0.001,
**AE_PARAMS),
AAERecommender(adversarial=True,
conditions=None,
gen_lr=0.001,
reg_lr=0.001,
**AE_PARAMS),
VAERecommender(conditions=None, **AE_PARAMS),
DAERecommender(conditions=None, **AE_PARAMS)
]
ALL_MODELS += AUTOENCODERS
if conditioned_autoencoders:
# Model with metadata (metadata used as set in CONDITIONS above)
CONDITIONED_AUTOENCODERS = [
AAERecommender(adversarial=False,
conditions=CONDITIONS,
lr=0.001,
**AE_PARAMS),
AAERecommender(adversarial=True,
conditions=CONDITIONS,
gen_lr=0.001,
reg_lr=0.001,
**AE_PARAMS),
DecodingRecommender(CONDITIONS,
n_epochs=100,
batch_size=1000,
optimizer='adam',
n_hidden=100,
lr=0.001,
verbose=True),
VAERecommender(conditions=CONDITIONS, **AE_PARAMS),
DAERecommender(conditions=CONDITIONS, **AE_PARAMS)
]
ALL_MODELS += CONDITIONED_AUTOENCODERS
print("Finished preparing models:", *ALL_MODELS, sep='\n\t')
path = DATA_PATH + ("dblp-ref/" if dataset == "dblp" else "acm.txt")
print("Loading data from", path)
papers = papers_from_files(path, dataset, n_jobs=4)
print("Unpacking {} data...".format(dataset))
bags_of_papers, ids, side_info = unpack_papers(papers)
del papers
bags = Bags(bags_of_papers, ids, side_info)
if args.compute_mi:
from aaerec.utils import compute_mutual_info
print("[MI] Dataset:", dataset)
print("[MI] min Count:", min_count)
tmp = bags.build_vocab(min_count=min_count, max_features=None)
mi = compute_mutual_info(tmp,
conditions=None,
include_labels=True,
normalize=True)
with open('mi.csv', 'a') as mifile:
print(dataset, min_count, mi, sep=',', file=mifile)
print("=" * 78)
exit(0)
log("Whole dataset:", logfile=outfile)
log(bags, logfile=outfile)
evaluation = Evaluation(bags, year, logfile=outfile)
evaluation.setup(min_count=min_count, min_elements=2, drop=drop)
with open(outfile, 'a') as fh:
print("~ Partial List + Titles + Author + Venue", "~" * 42, file=fh)
evaluation(ALL_MODELS, batch_size=1000)