import pandas as pd
df = pd.read_csv('http://bit.ly/kaggletrain')
X = df[['Name', 'Cabin']].dropna()
from sklearn.feature_extraction.text import CountVectorizer
vect = CountVectorizer()
from sklearn.compose import make_column_transformer
ct = make_column_transformer((vect, 'Name'), (vect, 'Cabin'))
ct.fit_transform(X)
<204x637 sparse matrix of type '<class 'numpy.longlong'>' with 1119 stored elements in Compressed Sparse Row format>
© 2020 Data School. All rights reserved.