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(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(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)