Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- #Checking count of how many values have age as zero
- print(data.loc[data['dob_years'] == 0]['dob_years'].count())
- #Calculating mean ages for respective family status and storing them
- civil_partnership_mean_age = data.groupby('family_status')['dob_years'].mean()[0]
- divorced_mean_age = data.groupby('family_status')['dob_years'].mean()[1]
- married_mean_age = data.groupby('family_status')['dob_years'].mean()[2]
- unmarried_mean_age = data.groupby('family_status')['dob_years'].mean()[3]
- widow_mean_age = data.groupby('family_status')['dob_years'].mean()[4]
- print(civil_partnership_mean_age)
- print(divorced_mean_age)
- print(married_mean_age)
- print(unmarried_mean_age)
- print(widow_mean_age)
- def replace_0 (row):
- family= data.loc[data['family_status']]
- dob = data.loc[data['dob_years']]
- if dob == 0:
- if family =='civil partnership':
- return civil_partnership_mean_age
- elif family =='divorced':
- return divorced_mean_age
- elif family =='married':
- return married_mean_age
- elif family =='unmarried':
- return unmarried_mean_age
- elif family == 'widow / widower':
- return widow_mean_age
- return dob
- replace_0(data.loc[:,'dob_years'])
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement