encoding_categorical.py

from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder
one_hot_encoder_gender = OneHotEncoder(handle_unknown='ignore')
one_hot_encoder_gender.fit(train[['Sex']])

# For Embarked column, there are some missing values. We need to first fill them then encode them.
imputer_Embarked = SimpleImputer(strategy='most_frequent', add_indicator=True)
imputer_Embarked.fit(train[['Embarked']])

transformed_Embarked = \
pd.DataFrame(imputer_Embarked.transform(train[['Embarked']]), 
             columns=['Embarked', 'Embarked_missing'], 
             index=train.index)

train = train.drop(columns=['Embarked']).join(transformed_Embarked)
# Do not forget to fill missing values in the validation and holdout sets

ordinal_encoder_city = OrdinalEncoder()
ordinal_encoder_city.fit(train[['Embarked']])