def main(): if 'WEIGHTED_SETS' not in dir(mg) and 'UNWEIGHTED_SETS' not in dir(mg): print( 'Define WEIGHTED_SETS and UNWEIGHTED_SETS in manager.py before using this module' ) return TXT_DIR = mg.dir(os.path.join(mg.WORKING_PATH, 'txts')) PDF_DIR = mg.dir(os.path.join(mg.INPUT_PATH, 'pdfs')) data = mg.get_data() convertToText.walkAndText(PDF_DIR, TXT_DIR) find_paragraphs(TXT_DIR, mg.WEIGHTED_SETS + mg.UNWEIGHTED_SETS, outfile=os.path.join(mg.WORKING_PATH, 'paragraphs')) sets = assoc_sets(data, TXT_DIR, mg.WEIGHTED_SETS, less_weighted_sets=mg.UNWEIGHTED_SETS) data['Sets'] = sets.values() mg.update_data()
import manager as mg, json, os data = mg.get_data() data = data[data['Data Use'] == 'Y'].dropna(subset=['Authors']) from biblio_reader import scholar_reader types = { auth: 'Contributor' in val for auth, val in scholar_reader.authors(data, 'Contributor').items() } contributors = { author for i, authors in zip(data['i'], data['Authors']) for author in authors.split(' & ') if i in mg.CONTR_PAPERS } with open( os.path.join(mg.dir(os.path.join('data', 'author-links')), 'objects.json'), 'w') as o: json.dump([{ 'name': auth, 'type': "Contributor" if types[auth] is True else 'Not a Contributor', 'depends': list({aff for aff in affils if aff != auth and aff != 'others'}) } for auth, affils in scholar_reader.authors( data, 'Authors', split=' & ').items() if auth != 'others'], o, sort_keys=True, indent=4)
import manager import simulation import matplotlib.pyplot as plt data = [ manager.get_data(x, x, simulation.Downside) for x in range(500, 501, 1) ] print("\t\t\t".join([str(i) for i in range(500, 501, 1)])) transform = [[ str(dat[i][0]) + "\t" + str(dat[i][1]) + "\t" + str(dat[i][2]) for dat in data ] for i in range(len(data[0]))] print("\n".join(["\t".join(T) for T in transform]))