from sklearn.feature_extraction import DictVectorizer
staff = [{'name': 'Steve Miller', 'age': 33.},
{'name': 'Lyndon Jones', 'age': 12.},
{'name': 'Baxter Morth', 'age': 18.}]
# Criando um objeto para o nosso dictionary vectorizer
vec = DictVectorizer()
vec.fit_transform(staff).toarray()
array([[33., 0., 0., 1.], [12., 0., 1., 0.], [18., 1., 0., 0.]])
vec.get_feature_names()
['age', 'name=Baxter Morth', 'name=Lyndon Jones', 'name=Steve Miller']