def process(path_to_ini: str): """ Program main function """ input_paths, output_path = load_ini(path_to_ini) records = Records() load(records, input_paths["csv"], input_paths["json"], input_paths["encoding"]) records.output(output_path["fname"], output_path["encoding"])
empl_by_year = {} for ticker in tickers: empl_by_year[ticker] = Counter([]) if os.path.isdir(empl_path): if os.listdir(empl_path)[0].endswith('.csv'): csv_parser(processor, empl_by_year, empl_path, tickers, infer_tickers, primary_skills) else: json_parser(processor, empl_by_year, empl_path, tickers, infer_tickers, primary_skills) else: if empl_path.endswith('.csv'): print('Individual file processing supported only on json') sys.exit(1) else: json_parser(processor, empl_by_year, empl_path, tickers, infer_tickers, primary_skills) #block for annual counts. empl_changes_lst = rec.output() varlist = [ "type","ticker","yrmth", "birth","gender","skill1","skill2","cntry","edu","f_elite", "edu_faculty","raw_skills", "job_role","depmt","ind_next","tenure","nprom" ] empl_changes_df = pd.DataFrame(data=empl_changes_lst,columns=varlist) empl_changes_df.to_csv(r'../outputs/' + target + '.csv', index= False) empl_by_year = pd.DataFrame(empl_by_year).fillna(0).unstack().reset_index() empl_by_year.columns = ["ticker", "year", "employment"] empl_by_year.to_csv(r'../outputs/' + target + '_by_year.csv', index= False)