import pandas as pd
df = pd.read_csv('http://bit.ly/kaggletrain', nrows=6)
cols = ['Embarked', 'Sex', 'Age', 'Fare']
X = df[cols]
from sklearn.preprocessing import OneHotEncoder
from sklearn.impute import SimpleImputer
from sklearn.linear_model import LogisticRegression
ohe = OneHotEncoder()
imp = SimpleImputer()
clf = LogisticRegression()
from sklearn.compose import make_column_transformer
from sklearn.pipeline import make_pipeline
ct = make_column_transformer(
(ohe, ['Embarked', 'Sex']),
(imp, ['Age']),
remainder='passthrough')
pipe = make_pipeline(ct, clf)
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
ct = ColumnTransformer(
[('encoder', ohe, ['Embarked', 'Sex']),
('imputer', imp, ['Age'])],
remainder='passthrough')
pipe = Pipeline([('preprocessor', ct), ('classifier', clf)])
© 2020 Data School. All rights reserved.