exploring_stanza_6.py

def print_word_info(word):
    print(f"Text:\t{word.text}")
    print(f"Lemma: \t{word.lemma}")
    print(f"UPOS: \t{word.upos}")
    print(f"XPOS: \t{word.xpos}")

print_word_info(moby_p1.sentences[3].words[4])

# Text:     growing
# Lemma:    grow
# UPOS:     VERB
# XPOS:     VBG

def word_info_df(doc):
    """
    - Parameters: doc (a Stanza Document object)
    - Returns: A Pandas DataFrame object with one row for each token in
      doc, and columns for text, lemma, upos, and xpos.
    """
    rows = []
    for sentence in doc.sentences:
        for word in sentence.words:
            row = {
                "text": word.text,
                "lemma": word.lemma,
                "upos": word.upos,
                "xpos": word.xpos,
            }
            rows.append(row)
    return pd.DataFrame(rows)

word_info_df(moby_p1)

# 	text	lemma	upos	xpos
# 0	Call    call	VERB	VB
# 1	me      I   	PRON	PRP
# 2	Ishmael Ishmael	PROPN	NNP
# 3	.       .       PUNCT   .
# 4	Some	some	DET     DT