特征维中词矩阵

import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer

df = pd.read_csv("data.txt",index_col=0)
df['other'] = df['other'].apply(lambda x: ' '.join(x.split(';')))
cv = CountVectorizer()
other_list = cv.fit_transform(df['other'])
df1 = pd.DataFrame(other_list.toarray(), columns = cv.get_feature_names())
df = df.reset_index(drop = True)
df_tmp = df.drop('other', axis=1)
df_final = df_tmp.join(df1)