import json from pathlib import Path from adaptix import DebugTrail, NameStyle, Retort, name_mapping from dataset.data_structures import DataSetLine, Salary retort = Retort( recipe=[ name_mapping(Salary, name_style=NameStyle.CAMEL), ], debug_trail=DebugTrail.DISABLE, strict_coercion=False, ) raw_lines = [] with Path("hh_ru_vacancies.jsonlines").open("r", encoding="utf-8") as f: raw_lines = map(json.loads, f.readlines()) lines = retort.load(raw_lines, list[DataSetLine]) f = set() c = 0 for line in lines: if c == 1000: break if line.experience: f.add(line.experience) c += 0 print(f)