Vektor representation of text, or multiple tokens

[Gitclop]

I am wondering how the final vektor is generated. is it a median of the token-vectors? Are they added?

        for row in data.index:
            doc = nlp(data.at[row, 'Text'])
            tokens = ' '.join(token.lemma_.lower() for token in doc if token.pos_ in (
                'NOUN',
                'PROPN',
                'VERB'
            ) and not token.is_stop and token.lower_ not in wordlist)
      
            data.at[row, 'Tokens'] = tokens

        data = data[data.Tokens != '']
        data.loc[:, ('Vektoren')] = data['Tokens'].map(lambda s: nlp(s).vector)

[victorialslocum]

By default, this is an average of the token vectors. Hope this helps!