def main():
logger.warning("Start building taxonomy")
# Load input: this includes reading network, text, and
# a background corpus for contrastive analysis
logger.info("Loading graph from file")
A, node_info = utils.load_graph(args.data_dir,
remove_citation=True,
force_undirected=True)
logger.info("Create HIN")
G = HIN(A, node_info)
logger.info("Load text")
corpus = utils.load_documents(args.data_dir)
motif_matchers = [
Motif_KPV(),
Motif_KPA(),
Motif_KP(),
Motif_KPVY(),
Motif_KPAA()
]
intermediate_dir = plib.Path(args.data_dir, "intermediate")
if not intermediate_dir.is_dir():
logger.warning(f"Creating intermediate dir {intermediate_dir}")
intermediate_dir.mkdir(parents=False)
# we collect all phrases
T = [] # terms / phrases
for info in node_info.values():
if info.node_type == "K":
T.append(info.entity_id)
D = corpus
tf_bg, idf_bg = utils.get_tf_idf_from_file(
plib.Path(args.data_dir, "background_documents.txt"), T)
taxo = Taxonomy(D, T, G)
builder = NetTaxo(motif_matchers,
tf_lift=args.tf_lift,
idf_lift=args.idf_lift,
damping=args.damping,
conf_motif=Motif_KPA().motif_name)
# set background corpus for contrastive analysis
builder.set_background(tf_bg, idf_bg)
builder.build(taxo, args.levels)
# save
output_dir = plib.Path(args.output_dir, config.unique_id)
if not output_dir.is_dir():
output_dir.mkdir(parents=True)
logger.info(f"Saving to {output_dir}")
taxo.save(output_dir)
logger.info("Saving complete")
# generate output
taxo.visualize(plib.Path(output_dir, f"vis.pdf"))
taxo.save_readable(output_dir)
