exploring_stanza_10.py

# select person entities
def select_person_entities(doc):
    return [ent for ent in doc.entities if ent.type == "PERSON"]

def person_df(doc):
    """
    - Parameters: doc (a Stanza Document object)
    - Returns: A Pandas DataFrame with one row for each entity in doc
      that has a "PERSON" type, and and columns text, type, start_char, 
      and the sentiment of the sentence in which the entity appears.
    """
    rows = []
    persons = select_person_entities(doc)
    for person in persons:
        row = {
            "text": person.text,
            "type": person.type,
            "start_char": person.start_char,
            "end_char": person.end_char,
            "sentence_sentiment": sentiment_descriptor(person._sent)
        }
        rows.append(row)
    return pd.DataFrame(rows)

characters = person_df(moby_dick)
display(characters.head())

#   text            type    start_char  end_char    sentence_sentiment
# 0 Ishmael         PERSON  29          36          neutral
# 1 Cato            PERSON  890         894         neutral
# 2 Tiger-lilies    PERSON  4226        4238        neutral
# 3 Jove            PERSON  4988        4992        neutral
# 4 Narcissus       PERSON  5080        5089        negative