exploring_stanza_9.py

# load the full text and put it through the pipeline
def load_text_doc(file_path):
    with open(file_path) as f:
        txt = f.read()
    return txt

moby_path = "moby_dick.txt"
moby_dick_text = load_text_doc(moby_path)
moby_dick = nlp(moby_dick_text)

print_doc_info(moby_dick)

# Num sentences:    9966
# Num tokens:       253928
# Num words:        253928
# Num entities:     7955