1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
| train_data.Name.str.extract(' ([A-Za-z]+)\.', expand=False).unique().size
for data in combined_data: data['Title'] = data.Name.str.extract('([A-Za-z]+)\.', expand = False) data.drop('Name', axis = 1, inplace = True)
train_data.Title.value_counts()
least_occuring = [ 'Don', 'Rev', 'Dr', 'Mme', 'Ms', 'Major', 'Lady', 'Sir', 'Mlle', 'Col', 'Capt', 'Countess','Dona', 'Jonkheer'] for data in combined_data: data.Title = data.Title.replace(least_occuring, 'Rare')
title_mapping = {"Mr": 1, "Miss": 2, "Mrs": 3, "Master": 4, "Rare": 5} for data in combined_data: data['Title'] = data['Title'].map(title_mapping)
|