CMU Arctic sentence ID mapping
Part of a dataset I'm working on
• 8 min read
from pathlib import Path
BASE = Path("/Users/joregan/Playing/work-2026/arctic")
RXR = BASE / "cmu_us_rxr_arctic" / "etc" / "txt.done.data"
def read_text(file: Path):
text_pairs = {}
with open(file) as f:
for line in f.readlines():
text_start = line.find('"')
text_end = line.rfind('"')
text = line[text_start + 1:text_end]
text_id = line[1:text_start].strip()
text_pairs[text_id] = text
return text_pairs
rxr_ids = {k: v for k, v in read_text(RXR).items()}
def norm_word(word: str):
if word in ["--", "-"]:
return ""
return word.lower().strip(".,!?;:\"()")
def norm_sentence(sentence: str):
return " ".join([norm_word(w) for w in sentence.split(" ") if norm_word(w) != ""])
reverse_rxr_ids = {norm_sentence(v): k for k, v in rxr_ids.items()}
remapped = {}
for subset in BASE.glob("cmu_us_*_arctic"):
person = subset.name.split("_")[2]
for file in subset.glob("etc/txt.done.data"):
for pair in read_text(file).items():
sentence = norm_sentence(pair[1])
if sentence not in reverse_rxr_ids:
if pair[0] not in rxr_ids:
rxr_ids[pair[0]] = pair[1]
reverse_rxr_ids[sentence] = pair[0]
elif person == "awb" and "-" in sentence:
sentence_no_hyphen = sentence.replace("-", " ")
if sentence_no_hyphen in reverse_rxr_ids and reverse_rxr_ids[sentence_no_hyphen] != pair[0]:
if not person in remapped:
remapped[person] = {}
remapped[person][pair[0]] = reverse_rxr_ids[sentence_no_hyphen]
else:
print(f"Missing: {pair[0]} {person} {sentence}")
else:
if sentence in reverse_rxr_ids and reverse_rxr_ids[sentence] != pair[0]:
if not person in remapped:
remapped[person] = {}
remapped[person][pair[0]] = reverse_rxr_ids[sentence]
Missing: arctic_b0028 jmk lord fitzhugh is the key to this whole situation Missing: arctic_a0335 awb this is no place fer you Missing: arctic_a0336 awb he'll knock yeh off a few sticks in no time Missing: arctic_a0433 awb her true course had been west 0.75 south Missing: arctic_a0557 awb jack london waikiki beach honolulu oahu t.h Missing: arctic_a0567 awb an hallucination began to trouble him Missing: arctic_b0211 awb this is 1880 Missing: arctic_b0234 awb and watch out for wet feet,' was his parting advice Missing: arctic_b0419 awb to begin with i read late Missing: arctic_b0426 awb there were orange green gold green and a copper green Missing: arctic_b0445 awb he sat beside the gendarme and beamed
SIMILAR = {
"jmk": {
"arctic_b0028": "arctic_b0028"
},
"awb": {
"arctic_a0335": "arctic_a0333",
"arctic_a0336": "arctic_a0334",
"arctic_a0433": "arctic_c0036",
"arctic_a0557": "arctic_a0554",
"arctic_b0211": "arctic_b0211",
"arctic_b0234": "arctic_b0234"
}
}
remapped["awb"]
{'arctic_a0075': 'arctic_a0074',
'arctic_a0076': 'arctic_a0075',
'arctic_a0077': 'arctic_a0076',
'arctic_a0078': 'arctic_a0077',
'arctic_a0079': 'arctic_c0026',
'arctic_a0080': 'arctic_a0078',
'arctic_a0081': 'arctic_a0079',
'arctic_a0082': 'arctic_a0080',
'arctic_a0083': 'arctic_a0081',
'arctic_a0084': 'arctic_a0082',
'arctic_a0085': 'arctic_a0083',
'arctic_a0086': 'arctic_a0084',
'arctic_a0087': 'arctic_a0085',
'arctic_a0088': 'arctic_a0086',
'arctic_a0089': 'arctic_a0087',
'arctic_a0090': 'arctic_a0088',
'arctic_a0092': 'arctic_a0090',
'arctic_a0093': 'arctic_a0091',
'arctic_a0095': 'arctic_a0093',
'arctic_a0096': 'arctic_a0094',
'arctic_a0097': 'arctic_a0095',
'arctic_a0098': 'arctic_a0096',
'arctic_a0099': 'arctic_a0097',
'arctic_a0100': 'arctic_a0098',
'arctic_a0101': 'arctic_a0099',
'arctic_a0102': 'arctic_a0100',
'arctic_a0104': 'arctic_a0102',
'arctic_a0105': 'arctic_a0103',
'arctic_a0106': 'arctic_a0104',
'arctic_a0107': 'arctic_a0105',
'arctic_a0108': 'arctic_a0106',
'arctic_a0109': 'arctic_a0107',
'arctic_a0110': 'arctic_a0108',
'arctic_a0111': 'arctic_a0109',
'arctic_a0112': 'arctic_a0110',
'arctic_a0113': 'arctic_a0111',
'arctic_a0114': 'arctic_a0112',
'arctic_a0115': 'arctic_a0113',
'arctic_a0116': 'arctic_a0114',
'arctic_a0117': 'arctic_a0115',
'arctic_a0118': 'arctic_a0116',
'arctic_a0119': 'arctic_a0117',
'arctic_a0120': 'arctic_a0118',
'arctic_a0121': 'arctic_a0119',
'arctic_a0122': 'arctic_a0120',
'arctic_a0123': 'arctic_a0121',
'arctic_a0124': 'arctic_a0122',
'arctic_a0125': 'arctic_a0123',
'arctic_a0126': 'arctic_a0124',
'arctic_a0127': 'arctic_a0125',
'arctic_a0128': 'arctic_a0126',
'arctic_a0129': 'arctic_a0127',
'arctic_a0130': 'arctic_a0128',
'arctic_a0131': 'arctic_a0129',
'arctic_a0132': 'arctic_a0130',
'arctic_a0133': 'arctic_a0131',
'arctic_a0134': 'arctic_a0132',
'arctic_a0135': 'arctic_a0133',
'arctic_a0136': 'arctic_a0134',
'arctic_a0137': 'arctic_a0135',
'arctic_a0138': 'arctic_a0136',
'arctic_a0139': 'arctic_a0137',
'arctic_a0140': 'arctic_a0138',
'arctic_a0141': 'arctic_a0139',
'arctic_a0142': 'arctic_a0140',
'arctic_a0143': 'arctic_a0141',
'arctic_a0144': 'arctic_a0142',
'arctic_a0145': 'arctic_a0143',
'arctic_a0146': 'arctic_a0144',
'arctic_a0147': 'arctic_a0145',
'arctic_a0148': 'arctic_a0146',
'arctic_a0149': 'arctic_a0147',
'arctic_a0150': 'arctic_a0148',
'arctic_a0151': 'arctic_a0149',
'arctic_a0153': 'arctic_a0151',
'arctic_a0154': 'arctic_a0152',
'arctic_a0155': 'arctic_a0153',
'arctic_a0156': 'arctic_a0154',
'arctic_a0157': 'arctic_a0155',
'arctic_a0158': 'arctic_a0156',
'arctic_a0159': 'arctic_a0157',
'arctic_a0160': 'arctic_a0158',
'arctic_a0161': 'arctic_a0159',
'arctic_a0162': 'arctic_a0160',
'arctic_a0163': 'arctic_a0161',
'arctic_a0164': 'arctic_a0162',
'arctic_a0165': 'arctic_a0163',
'arctic_a0166': 'arctic_a0164',
'arctic_a0168': 'arctic_a0166',
'arctic_a0169': 'arctic_a0167',
'arctic_a0170': 'arctic_a0168',
'arctic_a0171': 'arctic_a0169',
'arctic_a0172': 'arctic_a0170',
'arctic_a0173': 'arctic_a0171',
'arctic_a0174': 'arctic_a0172',
'arctic_a0175': 'arctic_a0173',
'arctic_a0176': 'arctic_a0174',
'arctic_a0177': 'arctic_a0175',
'arctic_a0178': 'arctic_a0176',
'arctic_a0179': 'arctic_a0177',
'arctic_a0180': 'arctic_a0178',
'arctic_a0182': 'arctic_a0180',
'arctic_a0183': 'arctic_a0181',
'arctic_a0184': 'arctic_a0182',
'arctic_a0185': 'arctic_a0183',
'arctic_a0186': 'arctic_a0184',
'arctic_a0187': 'arctic_a0185',
'arctic_a0188': 'arctic_a0186',
'arctic_a0189': 'arctic_a0187',
'arctic_a0190': 'arctic_a0188',
'arctic_a0191': 'arctic_a0189',
'arctic_a0192': 'arctic_a0190',
'arctic_a0193': 'arctic_a0191',
'arctic_a0194': 'arctic_a0192',
'arctic_a0195': 'arctic_a0193',
'arctic_a0196': 'arctic_a0194',
'arctic_a0197': 'arctic_a0195',
'arctic_a0198': 'arctic_a0196',
'arctic_a0199': 'arctic_a0197',
'arctic_a0200': 'arctic_a0198',
'arctic_a0201': 'arctic_a0199',
'arctic_a0202': 'arctic_a0200',
'arctic_a0203': 'arctic_a0201',
'arctic_a0204': 'arctic_a0202',
'arctic_a0205': 'arctic_a0203',
'arctic_a0206': 'arctic_a0204',
'arctic_a0207': 'arctic_a0205',
'arctic_a0208': 'arctic_a0206',
'arctic_a0209': 'arctic_a0207',
'arctic_a0210': 'arctic_a0208',
'arctic_a0211': 'arctic_a0209',
'arctic_a0212': 'arctic_a0210',
'arctic_a0213': 'arctic_a0211',
'arctic_a0214': 'arctic_a0212',
'arctic_a0215': 'arctic_a0213',
'arctic_a0216': 'arctic_a0214',
'arctic_a0217': 'arctic_a0215',
'arctic_a0218': 'arctic_a0216',
'arctic_a0219': 'arctic_a0217',
'arctic_a0220': 'arctic_a0218',
'arctic_a0221': 'arctic_a0219',
'arctic_a0222': 'arctic_a0220',
'arctic_a0223': 'arctic_a0221',
'arctic_a0224': 'arctic_a0222',
'arctic_a0225': 'arctic_a0223',
'arctic_a0226': 'arctic_a0224',
'arctic_a0227': 'arctic_a0225',
'arctic_a0228': 'arctic_a0226',
'arctic_a0229': 'arctic_a0227',
'arctic_a0230': 'arctic_a0228',
'arctic_a0231': 'arctic_a0229',
'arctic_a0232': 'arctic_a0230',
'arctic_a0233': 'arctic_a0231',
'arctic_a0234': 'arctic_a0232',
'arctic_a0235': 'arctic_a0233',
'arctic_a0236': 'arctic_a0234',
'arctic_a0237': 'arctic_a0235',
'arctic_a0238': 'arctic_a0236',
'arctic_a0239': 'arctic_a0237',
'arctic_a0240': 'arctic_a0238',
'arctic_a0241': 'arctic_a0239',
'arctic_a0242': 'arctic_a0240',
'arctic_a0243': 'arctic_a0241',
'arctic_a0244': 'arctic_a0242',
'arctic_a0245': 'arctic_a0243',
'arctic_a0246': 'arctic_a0244',
'arctic_a0247': 'arctic_a0245',
'arctic_a0248': 'arctic_a0246',
'arctic_a0250': 'arctic_a0248',
'arctic_a0251': 'arctic_a0249',
'arctic_a0252': 'arctic_a0250',
'arctic_a0253': 'arctic_a0251',
'arctic_a0254': 'arctic_a0252',
'arctic_a0255': 'arctic_a0253',
'arctic_a0256': 'arctic_a0254',
'arctic_a0257': 'arctic_a0255',
'arctic_a0258': 'arctic_a0256',
'arctic_a0259': 'arctic_a0257',
'arctic_a0261': 'arctic_a0259',
'arctic_a0262': 'arctic_a0260',
'arctic_a0263': 'arctic_a0261',
'arctic_a0264': 'arctic_a0262',
'arctic_a0265': 'arctic_a0263',
'arctic_a0266': 'arctic_a0264',
'arctic_a0267': 'arctic_a0265',
'arctic_a0268': 'arctic_a0266',
'arctic_a0269': 'arctic_a0267',
'arctic_a0270': 'arctic_a0268',
'arctic_a0271': 'arctic_a0269',
'arctic_a0272': 'arctic_a0270',
'arctic_a0273': 'arctic_a0271',
'arctic_a0274': 'arctic_a0272',
'arctic_a0275': 'arctic_a0273',
'arctic_a0276': 'arctic_a0274',
'arctic_a0277': 'arctic_a0275',
'arctic_a0278': 'arctic_a0276',
'arctic_a0279': 'arctic_a0277',
'arctic_a0280': 'arctic_a0278',
'arctic_a0281': 'arctic_a0279',
'arctic_a0282': 'arctic_a0280',
'arctic_a0283': 'arctic_a0281',
'arctic_a0284': 'arctic_a0282',
'arctic_a0285': 'arctic_a0283',
'arctic_a0286': 'arctic_a0284',
'arctic_a0287': 'arctic_a0285',
'arctic_a0288': 'arctic_a0286',
'arctic_a0289': 'arctic_a0287',
'arctic_a0290': 'arctic_a0288',
'arctic_a0291': 'arctic_a0289',
'arctic_a0292': 'arctic_a0290',
'arctic_a0293': 'arctic_a0291',
'arctic_a0295': 'arctic_a0293',
'arctic_a0296': 'arctic_a0294',
'arctic_a0297': 'arctic_a0295',
'arctic_a0298': 'arctic_a0296',
'arctic_a0299': 'arctic_a0297',
'arctic_a0300': 'arctic_a0298',
'arctic_a0302': 'arctic_a0300',
'arctic_a0303': 'arctic_a0301',
'arctic_a0304': 'arctic_a0302',
'arctic_a0305': 'arctic_a0303',
'arctic_a0306': 'arctic_a0304',
'arctic_a0307': 'arctic_a0305',
'arctic_a0308': 'arctic_a0306',
'arctic_a0309': 'arctic_a0307',
'arctic_a0310': 'arctic_a0308',
'arctic_a0311': 'arctic_a0309',
'arctic_a0312': 'arctic_a0310',
'arctic_a0313': 'arctic_a0311',
'arctic_a0314': 'arctic_a0312',
'arctic_a0315': 'arctic_a0313',
'arctic_a0316': 'arctic_a0314',
'arctic_a0317': 'arctic_a0315',
'arctic_a0318': 'arctic_a0316',
'arctic_a0319': 'arctic_a0317',
'arctic_a0320': 'arctic_a0318',
'arctic_a0321': 'arctic_a0319',
'arctic_a0322': 'arctic_a0320',
'arctic_a0323': 'arctic_a0321',
'arctic_a0324': 'arctic_a0322',
'arctic_a0325': 'arctic_a0323',
'arctic_a0326': 'arctic_a0324',
'arctic_a0327': 'arctic_a0325',
'arctic_a0328': 'arctic_a0326',
'arctic_a0329': 'arctic_a0327',
'arctic_a0330': 'arctic_a0328',
'arctic_a0331': 'arctic_a0329',
'arctic_a0332': 'arctic_a0330',
'arctic_a0333': 'arctic_a0331',
'arctic_a0334': 'arctic_a0332',
'arctic_a0337': 'arctic_a0335',
'arctic_a0338': 'arctic_a0336',
'arctic_a0339': 'arctic_a0337',
'arctic_a0340': 'arctic_a0338',
'arctic_a0341': 'arctic_a0339',
'arctic_a0342': 'arctic_a0340',
'arctic_a0344': 'arctic_a0342',
'arctic_a0345': 'arctic_a0343',
'arctic_a0346': 'arctic_a0344',
'arctic_a0347': 'arctic_a0345',
'arctic_a0348': 'arctic_a0346',
'arctic_a0349': 'arctic_a0347',
'arctic_a0350': 'arctic_a0348',
'arctic_a0351': 'arctic_a0349',
'arctic_a0352': 'arctic_a0350',
'arctic_a0353': 'arctic_a0351',
'arctic_a0354': 'arctic_a0352',
'arctic_a0355': 'arctic_a0353',
'arctic_a0356': 'arctic_a0354',
'arctic_a0357': 'arctic_a0355',
'arctic_a0358': 'arctic_a0356',
'arctic_a0359': 'arctic_a0357',
'arctic_a0360': 'arctic_a0358',
'arctic_a0361': 'arctic_a0359',
'arctic_a0362': 'arctic_a0360',
'arctic_a0363': 'arctic_a0361',
'arctic_a0364': 'arctic_a0362',
'arctic_a0365': 'arctic_a0363',
'arctic_a0366': 'arctic_a0364',
'arctic_a0367': 'arctic_a0365',
'arctic_a0368': 'arctic_a0366',
'arctic_a0369': 'arctic_a0367',
'arctic_a0370': 'arctic_a0368',
'arctic_a0371': 'arctic_a0369',
'arctic_a0372': 'arctic_a0370',
'arctic_a0373': 'arctic_a0371',
'arctic_a0374': 'arctic_a0372',
'arctic_a0375': 'arctic_a0373',
'arctic_a0376': 'arctic_a0374',
'arctic_a0377': 'arctic_a0375',
'arctic_a0378': 'arctic_a0376',
'arctic_a0379': 'arctic_a0377',
'arctic_a0380': 'arctic_a0378',
'arctic_a0381': 'arctic_a0379',
'arctic_a0382': 'arctic_a0380',
'arctic_a0383': 'arctic_a0381',
'arctic_a0384': 'arctic_a0382',
'arctic_a0385': 'arctic_a0383',
'arctic_a0386': 'arctic_a0384',
'arctic_a0387': 'arctic_a0385',
'arctic_a0388': 'arctic_a0386',
'arctic_a0389': 'arctic_a0387',
'arctic_a0390': 'arctic_a0388',
'arctic_a0391': 'arctic_a0389',
'arctic_a0393': 'arctic_a0391',
'arctic_a0394': 'arctic_a0392',
'arctic_a0395': 'arctic_a0393',
'arctic_a0396': 'arctic_a0394',
'arctic_a0397': 'arctic_a0395',
'arctic_a0398': 'arctic_a0396',
'arctic_a0399': 'arctic_a0397',
'arctic_a0400': 'arctic_a0398',
'arctic_a0401': 'arctic_a0399',
'arctic_a0402': 'arctic_a0400',
'arctic_a0403': 'arctic_a0401',
'arctic_a0404': 'arctic_a0402',
'arctic_a0405': 'arctic_a0403',
'arctic_a0406': 'arctic_a0404',
'arctic_a0407': 'arctic_a0405',
'arctic_a0408': 'arctic_a0406',
'arctic_a0409': 'arctic_a0407',
'arctic_a0410': 'arctic_a0408',
'arctic_a0411': 'arctic_a0409',
'arctic_a0412': 'arctic_a0410',
'arctic_a0413': 'arctic_a0411',
'arctic_a0414': 'arctic_a0412',
'arctic_a0415': 'arctic_a0413',
'arctic_a0416': 'arctic_a0414',
'arctic_a0417': 'arctic_a0415',
'arctic_a0418': 'arctic_a0416',
'arctic_a0419': 'arctic_a0417',
'arctic_a0420': 'arctic_a0418',
'arctic_a0421': 'arctic_a0419',
'arctic_a0422': 'arctic_a0420',
'arctic_a0423': 'arctic_a0421',
'arctic_a0424': 'arctic_a0422',
'arctic_a0425': 'arctic_a0423',
'arctic_a0426': 'arctic_a0424',
'arctic_a0428': 'arctic_a0426',
'arctic_a0429': 'arctic_a0427',
'arctic_a0430': 'arctic_a0428',
'arctic_a0431': 'arctic_a0429',
'arctic_a0432': 'arctic_a0430',
'arctic_a0434': 'arctic_a0431',
'arctic_a0435': 'arctic_a0432',
'arctic_a0436': 'arctic_a0433',
'arctic_a0437': 'arctic_a0434',
'arctic_a0438': 'arctic_a0435',
'arctic_a0439': 'arctic_a0436',
'arctic_a0440': 'arctic_a0437',
'arctic_a0441': 'arctic_a0438',
'arctic_a0442': 'arctic_a0439',
'arctic_a0443': 'arctic_a0440',
'arctic_a0444': 'arctic_a0441',
'arctic_a0445': 'arctic_a0442',
'arctic_a0446': 'arctic_a0443',
'arctic_a0447': 'arctic_a0444',
'arctic_a0448': 'arctic_a0445',
'arctic_a0449': 'arctic_a0446',
'arctic_a0450': 'arctic_a0447',
'arctic_a0451': 'arctic_a0448',
'arctic_a0452': 'arctic_a0449',
'arctic_a0453': 'arctic_a0450',
'arctic_a0454': 'arctic_a0451',
'arctic_a0455': 'arctic_a0452',
'arctic_a0456': 'arctic_a0453',
'arctic_a0457': 'arctic_a0454',
'arctic_a0458': 'arctic_a0455',
'arctic_a0459': 'arctic_c0035',
'arctic_a0460': 'arctic_a0457',
'arctic_a0462': 'arctic_a0459',
'arctic_a0463': 'arctic_a0460',
'arctic_a0464': 'arctic_a0461',
'arctic_a0465': 'arctic_a0462',
'arctic_a0466': 'arctic_a0463',
'arctic_a0467': 'arctic_a0464',
'arctic_a0468': 'arctic_a0465',
'arctic_a0469': 'arctic_a0466',
'arctic_a0470': 'arctic_a0467',
'arctic_a0471': 'arctic_a0468',
'arctic_a0472': 'arctic_a0469',
'arctic_a0473': 'arctic_a0470',
'arctic_a0474': 'arctic_a0471',
'arctic_a0475': 'arctic_a0472',
'arctic_a0476': 'arctic_a0473',
'arctic_a0477': 'arctic_a0474',
'arctic_a0478': 'arctic_a0475',
'arctic_a0479': 'arctic_a0476',
'arctic_a0480': 'arctic_a0477',
'arctic_a0481': 'arctic_a0478',
'arctic_a0482': 'arctic_a0479',
'arctic_a0483': 'arctic_a0480',
'arctic_a0484': 'arctic_a0481',
'arctic_a0485': 'arctic_a0482',
'arctic_a0486': 'arctic_a0483',
'arctic_a0487': 'arctic_a0484',
'arctic_a0488': 'arctic_a0485',
'arctic_a0489': 'arctic_a0486',
'arctic_a0490': 'arctic_a0487',
'arctic_a0491': 'arctic_a0488',
'arctic_a0492': 'arctic_a0489',
'arctic_a0493': 'arctic_a0490',
'arctic_a0494': 'arctic_a0491',
'arctic_a0495': 'arctic_a0492',
'arctic_a0496': 'arctic_a0493',
'arctic_a0497': 'arctic_a0494',
'arctic_a0498': 'arctic_a0495',
'arctic_a0499': 'arctic_a0496',
'arctic_a0500': 'arctic_a0497',
'arctic_a0501': 'arctic_a0498',
'arctic_a0502': 'arctic_a0499',
'arctic_a0503': 'arctic_a0500',
'arctic_a0504': 'arctic_a0501',
'arctic_a0505': 'arctic_a0502',
'arctic_a0506': 'arctic_a0503',
'arctic_a0507': 'arctic_a0504',
'arctic_a0508': 'arctic_a0505',
'arctic_a0509': 'arctic_a0506',
'arctic_a0510': 'arctic_a0507',
'arctic_a0511': 'arctic_a0508',
'arctic_a0512': 'arctic_a0509',
'arctic_a0513': 'arctic_a0510',
'arctic_a0514': 'arctic_a0511',
'arctic_a0515': 'arctic_a0512',
'arctic_a0516': 'arctic_a0513',
'arctic_a0517': 'arctic_a0514',
'arctic_a0518': 'arctic_a0515',
'arctic_a0519': 'arctic_a0516',
'arctic_a0520': 'arctic_a0517',
'arctic_a0521': 'arctic_a0518',
'arctic_a0522': 'arctic_a0519',
'arctic_a0523': 'arctic_a0520',
'arctic_a0524': 'arctic_a0521',
'arctic_a0525': 'arctic_a0522',
'arctic_a0526': 'arctic_a0523',
'arctic_a0527': 'arctic_a0524',
'arctic_a0528': 'arctic_a0525',
'arctic_a0529': 'arctic_a0526',
'arctic_a0530': 'arctic_a0527',
'arctic_a0531': 'arctic_a0528',
'arctic_a0532': 'arctic_a0529',
'arctic_a0533': 'arctic_a0530',
'arctic_a0534': 'arctic_a0531',
'arctic_a0535': 'arctic_a0532',
'arctic_a0536': 'arctic_a0533',
'arctic_a0537': 'arctic_a0534',
'arctic_a0538': 'arctic_a0535',
'arctic_a0539': 'arctic_a0536',
'arctic_a0540': 'arctic_a0537',
'arctic_a0541': 'arctic_a0538',
'arctic_a0542': 'arctic_a0539',
'arctic_a0544': 'arctic_a0541',
'arctic_a0545': 'arctic_a0542',
'arctic_a0546': 'arctic_a0543',
'arctic_a0547': 'arctic_a0544',
'arctic_a0548': 'arctic_a0545',
'arctic_a0549': 'arctic_a0546',
'arctic_a0550': 'arctic_a0547',
'arctic_a0551': 'arctic_a0548',
'arctic_a0552': 'arctic_a0549',
'arctic_a0553': 'arctic_a0550',
'arctic_a0554': 'arctic_a0551',
'arctic_a0555': 'arctic_a0552',
'arctic_a0556': 'arctic_a0553',
'arctic_a0558': 'arctic_a0555',
'arctic_a0559': 'arctic_a0556',
'arctic_a0560': 'arctic_a0557',
'arctic_a0561': 'arctic_a0558',
'arctic_a0562': 'arctic_a0559',
'arctic_a0563': 'arctic_a0560',
'arctic_a0564': 'arctic_a0561',
'arctic_a0565': 'arctic_a0562',
'arctic_a0566': 'arctic_a0563',
'arctic_a0568': 'arctic_a0564',
'arctic_a0569': 'arctic_a0565',
'arctic_a0570': 'arctic_a0566',
'arctic_a0571': 'arctic_a0567',
'arctic_a0572': 'arctic_a0568',
'arctic_a0573': 'arctic_a0569',
'arctic_a0574': 'arctic_a0570',
'arctic_a0575': 'arctic_a0571',
'arctic_a0576': 'arctic_a0572',
'arctic_a0577': 'arctic_a0573',
'arctic_a0578': 'arctic_a0574',
'arctic_a0579': 'arctic_a0575',
'arctic_a0580': 'arctic_a0576',
'arctic_a0581': 'arctic_a0577',
'arctic_a0582': 'arctic_a0578',
'arctic_a0583': 'arctic_a0579',
'arctic_a0584': 'arctic_a0580',
'arctic_a0585': 'arctic_a0581',
'arctic_a0586': 'arctic_a0582',
'arctic_a0587': 'arctic_a0583',
'arctic_a0588': 'arctic_a0584',
'arctic_a0589': 'arctic_a0585',
'arctic_a0590': 'arctic_a0586',
'arctic_a0591': 'arctic_a0587',
'arctic_a0593': 'arctic_a0589',
'arctic_a0594': 'arctic_a0590',
'arctic_a0595': 'arctic_a0591',
'arctic_a0596': 'arctic_a0592',
'arctic_a0597': 'arctic_a0593',
'arctic_b0420': 'arctic_b0419',
'arctic_b0421': 'arctic_b0420',
'arctic_b0422': 'arctic_b0421',
'arctic_b0423': 'arctic_b0422',
'arctic_b0424': 'arctic_b0423',
'arctic_b0425': 'arctic_b0424',
'arctic_b0427': 'arctic_b0426',
'arctic_b0428': 'arctic_b0427',
'arctic_b0429': 'arctic_b0428',
'arctic_b0430': 'arctic_b0429',
'arctic_b0431': 'arctic_b0430',
'arctic_b0432': 'arctic_b0431',
'arctic_b0433': 'arctic_b0432',
'arctic_b0435': 'arctic_b0434',
'arctic_b0436': 'arctic_b0435',
'arctic_b0437': 'arctic_b0436',
'arctic_b0438': 'arctic_b0437',
'arctic_b0439': 'arctic_b0438',
'arctic_b0440': 'arctic_b0439',
'arctic_b0441': 'arctic_b0440',
'arctic_b0442': 'arctic_b0441',
'arctic_b0443': 'arctic_b0442',
'arctic_b0444': 'arctic_b0443',
'arctic_b0446': 'arctic_b0444',
'arctic_b0447': 'arctic_b0445',
'arctic_b0448': 'arctic_b0446',
'arctic_b0449': 'arctic_b0447',
'arctic_b0450': 'arctic_b0448',
'arctic_b0451': 'arctic_b0449',
'arctic_b0452': 'arctic_b0450',
'arctic_b0454': 'arctic_b0452',
'arctic_b0455': 'arctic_b0453',
'arctic_b0456': 'arctic_b0454',
'arctic_b0457': 'arctic_b0455',
'arctic_b0458': 'arctic_b0456',
'arctic_b0459': 'arctic_b0457',
'arctic_b0460': 'arctic_b0458',
'arctic_b0461': 'arctic_b0459',
'arctic_b0462': 'arctic_b0460',
'arctic_b0463': 'arctic_b0461',
'arctic_b0464': 'arctic_b0462',
'arctic_b0465': 'arctic_b0463',
'arctic_b0466': 'arctic_b0464',
'arctic_b0467': 'arctic_b0465',
'arctic_b0468': 'arctic_b0466',
'arctic_b0469': 'arctic_b0467',
'arctic_b0470': 'arctic_b0468',
'arctic_b0471': 'arctic_b0469',
'arctic_b0472': 'arctic_b0470',
'arctic_b0473': 'arctic_b0471',
'arctic_b0474': 'arctic_b0472',
'arctic_b0475': 'arctic_b0473',
'arctic_b0476': 'arctic_b0474',
'arctic_b0477': 'arctic_b0475',
'arctic_b0478': 'arctic_b0476',
'arctic_b0479': 'arctic_b0477',
'arctic_b0480': 'arctic_b0478',
'arctic_b0481': 'arctic_b0479',
'arctic_b0482': 'arctic_b0480',
'arctic_b0483': 'arctic_b0481',
'arctic_b0484': 'arctic_b0482',
'arctic_b0485': 'arctic_b0483',
'arctic_b0486': 'arctic_b0484',
'arctic_b0487': 'arctic_b0485',
'arctic_b0488': 'arctic_b0486',
'arctic_b0489': 'arctic_b0487',
'arctic_b0490': 'arctic_b0488',
'arctic_b0491': 'arctic_b0489',
'arctic_b0492': 'arctic_b0490',
'arctic_b0494': 'arctic_b0492',
'arctic_b0495': 'arctic_b0493',
'arctic_b0496': 'arctic_b0494',
'arctic_b0497': 'arctic_b0495',
'arctic_b0498': 'arctic_b0496',
'arctic_b0499': 'arctic_b0497',
'arctic_b0500': 'arctic_b0498',
'arctic_b0501': 'arctic_b0499',
'arctic_b0502': 'arctic_b0500',
'arctic_b0503': 'arctic_b0501',
'arctic_b0504': 'arctic_b0502',
'arctic_b0505': 'arctic_b0503',
'arctic_b0506': 'arctic_b0504',
'arctic_b0507': 'arctic_b0505',
'arctic_b0508': 'arctic_b0506',
'arctic_b0509': 'arctic_b0507',
'arctic_b0510': 'arctic_b0508',
'arctic_b0511': 'arctic_b0509',
'arctic_b0512': 'arctic_b0510',
'arctic_b0513': 'arctic_b0511',
'arctic_b0514': 'arctic_b0512',
'arctic_b0515': 'arctic_b0513',
'arctic_b0517': 'arctic_b0515',
'arctic_b0518': 'arctic_b0516',
'arctic_b0519': 'arctic_b0517',
'arctic_b0520': 'arctic_b0518',
'arctic_b0521': 'arctic_b0519',
'arctic_b0522': 'arctic_b0520',
'arctic_b0523': 'arctic_b0521',
'arctic_b0524': 'arctic_b0522',
'arctic_b0525': 'arctic_b0523',
'arctic_b0526': 'arctic_b0524',
'arctic_b0527': 'arctic_b0525',
'arctic_b0528': 'arctic_b0526',
'arctic_b0529': 'arctic_b0527',
'arctic_b0530': 'arctic_b0528',
'arctic_b0531': 'arctic_b0529',
'arctic_b0532': 'arctic_b0530',
'arctic_b0533': 'arctic_b0531',
'arctic_b0534': 'arctic_b0532',
'arctic_b0535': 'arctic_b0533',
'arctic_b0536': 'arctic_b0534',
'arctic_b0537': 'arctic_b0535',
'arctic_b0538': 'arctic_b0536',
'arctic_b0539': 'arctic_b0537',
'arctic_b0540': 'arctic_b0538',
'arctic_b0541': 'arctic_b0539'}
import json
with open("arctic-remapped-ids.json", "w") as f:
json.dump(remapped, f, indent=4)