if __name__ == "__main__":
fg = FilterGolden()
dd = DatasetDexter()
wd = WikipediaDataset()
dexter_json_doc_list = dd.get_dexter_dataset(
FileLocations.get_dropbox_dexter_path(), 'saliency-dataset.json')
golden_saliency_by_entid_by_docid = dd.get_golden_saliency_by_entid_by_docid(
dexter_json_doc_list, wd)
#check which are still valid
wikititle_by_id = wd.get_wikititle_by_id()
not_found_count = 0
count = 0
multiple_wid_count = 0
for docid in golden_saliency_by_entid_by_docid.keys():
for entity_id in golden_saliency_by_entid_by_docid[docid].keys():
n_entity_id = wd.get_wikititle_id_from_id(entity_id)
wikititle1 = ''
wikititle2 = ''
if entity_id in wikititle_by_id:
wikititle1 = wikititle_by_id[entity_id]
if n_entity_id in wikititle_by_id:
wikititle2 = wikititle_by_id[n_entity_id]
print('not_salient_list:' + str(not_salient_list))
print('salient_list:' + str(salient_list))
if __name__ == "__main__":
filename = FileLocations.get_dropbox_intermediate_path() + 'sel.pickle'
build_model = False
# smb = SelModelBuilder()
# if build_model:
# sentiment_processor = smb.train_and_save_model(filename)
# else:
# sentiment_processor = SentimentProcessor()
# sentiment_processor.load_model(filename)
dd = DatasetDexter()
wikipediaDataset = WikipediaDataset()
document_list = dd.get_dexter_dataset(
path=FileLocations.get_dropbox_dexter_path())
spotter = GoldenSpotter(document_list, wikipediaDataset)
golden_saliency_by_entid_by_docid = dd.get_golden_saliency_by_entid_by_docid(
document_list, wikipediaDataset)
wikititle_by_id = wikipediaDataset.get_wikititle_by_id()
show_doc_info(2)