Today I re-cleaned the primary data for the second round of the survey. Reduced the number of pseudo-unique names and patronymics. Converted respondents' dates of birth from text to date and verified their correctness. Found about 80 errors (for example, people born in 2023 and 2064). In the part of names, when entering, the Latin letter 'i' was used instead of the Ukrainian one. In addition, I found 9 cases of missing names or patronymics (surname or first name written twice) Time spent: 4h
Комментарии
Отправить комментарий