1{2 "task_id": "F1-dev-01",3 "n_unique_firms": 400,4 "n_missing_revenue": 6,5 "n_analysed": 394,6 "mean_revenue_musd": 249.962076142132,7 "median_revenue_musd": 162.30599999999998,8 "mean_employees": 1101.435,9 "mean_revenue_raw": 30695.882310502282,10 "feasibility": "complete",11 "feasibility_reason": null,12 "data_issues": [13 {14 "issue": "45 exact duplicate rows (45 firms appear twice with identical values in all columns)",15 "handling": "dropped the repeated rows, kept one row per firm (exclusion step 1)"16 },17 {18 "issue": "mixed revenue units: 60 distinct firms report revenue in USD_thousands, the others in USD_millions",19 "handling": "converted to millions USD by dividing USD_thousands values by 1000 (exclusion step 2, recode, no rows removed)"20 },21 {22 "issue": "6 distinct firms with unknown (empty) revenue (7 raw rows including duplicates): F0048, F0121, F0129, F0269, F0348, F0399",23 "handling": "excluded from revenue aggregates and analytic.csv (exclusion step 3); kept for n_unique_firms and mean_employees"24 }25 ],26 "n_input_rows": {27 "firms.csv": 44528 },29 "random_seed": null,30 "sd_revenue_musd": 274.3033045641327,31 "se_mean_revenue_musd": 13.81920084215236,32 "n_exact_duplicate_rows": 45,33 "n_firms_usd_thousands": 60,34 "mean_employees_analysed": 1095.647208121827435}