def main(year, min_count=None, outfile=None):
""" Main function for training and evaluating AAE methods on IREON data """
if (CLEAN == True):
print("Loading data from", DATA_PATH)
papers = load(DATA_PATH)
print("Cleaning data...")
clean(CLEAN_DATA_PATH, papers)
print("Clean data in {}".format(CLEAN_DATA_PATH))
return
print("Loading data from", CLEAN_DATA_PATH)
papers = load(CLEAN_DATA_PATH)
print("Unpacking IREON data...")
bags_of_papers, ids, side_info = unpack_papers(papers)
del papers
bags = Bags(bags_of_papers, ids, side_info)
log("Whole dataset:", logfile=outfile)
log(bags, logfile=outfile)
evaluation = Evaluation(bags, year, logfile=outfile)
evaluation.setup(min_count=min_count, min_elements=2)
print("Loading pre-trained embedding", W2V_PATH)
with open(outfile, 'a') as fh:
print("~ Partial List", "~" * 42, file=fh)
evaluation(BASELINES + RECOMMENDERS)
with open(outfile, 'a') as fh:
print("~ Partial List + Titles", "~" * 42, file=fh)
evaluation(TITLE_ENHANCED)
def main():
CONFIG = {
'pub': ('/data21/lgalke/datasets/citations_pmc.tsv', 2011, 50),
'eco': ('/data21/lgalke/datasets/econbiz62k.tsv', 2012, 1)
}
print("Loading pre-trained embedding", W2V_PATH)
vectors = KeyedVectors.load_word2vec_format(W2V_PATH, binary=W2V_IS_BINARY)
CONDITIONS = ConditionList([
('title', PretrainedWordEmbeddingCondition(vectors, dim=0))
])
PARSER = argparse.ArgumentParser()
PARSER.add_argument('data', type=str, choices=['pub', 'eco'])
args = PARSER.parse_args()
DATA = CONFIG[args.data]
logfile = '/data22/ivagliano/test-irgan/' + args.data + '-decoder.log'
bags = Bags.load_tabcomma_format(DATA[0])
c_year = DATA[1]
evaluate = Evaluation(bags,
year=c_year,
logfile=logfile).setup(min_count=DATA[2],
min_elements=2)
user_num = evaluate.train_set.size()[0] + evaluate.test_set.size()[0]
item_num = evaluate.train_set.size()[1]
models = [IRGANRecommender(user_num, item_num, g_epochs=1, d_epochs=1, n_epochs=1, conditions=CONDITIONS)]
evaluate(models)
def main(year, min_count=None, outfile=None, drop=1):
""" Main function for training and evaluating AAE methods on IREON data """
if (CLEAN == True):
print("Loading data from", DATA_PATH)
papers = load(DATA_PATH)
print("Cleaning data...")
clean(CLEAN_DATA_PATH, papers)
print("Clean data in {}".format(CLEAN_DATA_PATH))
return
print("Loading data from", CLEAN_DATA_PATH)
papers = load(CLEAN_DATA_PATH)
print("Unpacking IREON data...")
# bags_of_papers, ids, side_info = unpack_papers(papers)
bags_of_papers, ids, side_info = unpack_papers_conditions(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: IREON (fiv)")
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('IREON', 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)
# Use only partial citations/labels list (no additional metadata)
with open(outfile, 'a') as fh:
print("~ Partial List", "~" * 42, file=fh)
evaluation(BASELINES + RECOMMENDERS)
# Use additional metadata (as defined in CONDITIONS for all models but SVD, which uses only titles)
with open(outfile, 'a') as fh:
print("~ Conditioned Models", "~" * 42, file=fh)
evaluation(CONDITIONED_MODELS)
def main(year, dataset, min_count=None, outfile=None, drop=1):
""" Main function for training and evaluating AAE methods on DBLP data """
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)
# To evaluate the baselines and the recommenders without metadata (or just the recommenders without metadata)
# with open(outfile, 'a') as fh:
# print("~ Partial List", "~" * 42, file=fh)
# evaluation(BASELINES + RECOMMENDERS)
# evaluation(RECOMMENDERS, batch_size=1000)
with open(outfile, 'a') as fh:
print("~ Partial List + Titles + Author + Venue", "~" * 42, file=fh)
# To evaluate SVD with titles
# evaluation(TITLE_ENHANCED)
evaluation(CONDITIONED_MODELS, batch_size=1000)
def main():
""" Evaluates the VAE Recommender """
CONFIG = {
'pub': ('/data21/lgalke/datasets/citations_pmc.tsv', 2011, 50),
'eco': ('/data21/lgalke/datasets/econbiz62k.tsv', 2012, 1)
}
PARSER = argparse.ArgumentParser()
PARSER.add_argument('data', type=str, choices=['pub', 'eco'])
args = PARSER.parse_args()
DATA = CONFIG[args.data]
logfile = '/data22/ivagliano/test-vae/' + args.data + '-hyperparams-opt.log'
bags = Bags.load_tabcomma_format(DATA[0])
c_year = DATA[1]
evaluate = Evaluation(bags, year=c_year,
logfile=logfile).setup(min_count=DATA[2],
min_elements=2)
print("Loading pre-trained embedding", W2V_PATH)
vectors = KeyedVectors.load_word2vec_format(W2V_PATH, binary=W2V_IS_BINARY)
params = {
#'n_epochs': 10,
'batch_size': 100,
'optimizer': 'adam',
# 'normalize_inputs': True,
}
CONDITIONS = ConditionList([('title',
PretrainedWordEmbeddingCondition(vectors))])
# 100 hidden units, 200 epochs, bernoulli prior, normalized inputs -> 0.174
# activations = ['ReLU','SELU']
# lrs = [(0.001, 0.0005), (0.001, 0.001)]
hcs = [(100, 50), (300, 100)]
epochs = [50, 100, 200, 500]
# dropouts = [(.2,.2), (.1,.1), (.1, .2), (.25, .25), (.3,.3)] # .2,.2 is best
# priors = ['categorical'] # gauss is best
# normal = [True, False]
# bernoulli was good, letz see if categorical is better... No
import itertools
models = [
VAERecommender(conditions=CONDITIONS,
**params,
n_hidden=hc[0],
n_code=hc[1],
n_epochs=e) for hc, e in itertools.product(hcs, epochs)
]
# models = [VAERecommender(conditions=CONDITIONS, **params)]
evaluate(models)
def main(year, dataset, min_count=None, outfile=None):
""" Main function for training and evaluating AAE methods on DBLP data """
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)
log("Whole dataset:", logfile=outfile)
log(bags, logfile=outfile)
evaluation = Evaluation(bags, year, logfile=outfile)
evaluation.setup(min_count=min_count, min_elements=2)
print("Loading pre-trained embedding", W2V_PATH)
with open(outfile, 'a') as fh:
print("~ Partial List", "~" * 42, file=fh)
evaluation(BASELINES + RECOMMENDERS)
with open(outfile, 'a') as fh:
print("~ Partial List + Titles", "~" * 42, file=fh)
evaluation(TITLE_ENHANCED)
PARSER = argparse.ArgumentParser()
PARSER.add_argument('dataset', type=str, help='path to dataset')
PARSER.add_argument('year', type=int, help='First year of the testing set.')
PARSER.add_argument('-m',
'--min-count',
type=int,
help='Pruning parameter',
default=50)
PARSER.add_argument('-o', '--outfile', type=str, default=None)
ARGS = PARSER.parse_args()
DATASET = Bags.load_tabcomma_format(ARGS.dataset, unique=True)
EVAL = Evaluation(DATASET, ARGS.year, logfile=ARGS.outfile)
EVAL.setup(min_count=ARGS.min_count, min_elements=2)
print("Loading pre-trained embedding", W2V_PATH)
VECTORS = KeyedVectors.load_word2vec_format(W2V_PATH, binary=W2V_IS_BINARY)
BASELINES = [
# RandomBaseline(),
# MostPopular(),
Countbased(),
SVDRecommender(1000, use_title=False),
]
ae_params = {
'n_code': 50,
'n_epochs': 100,
'embedding': VECTORS,
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)