Missing English words in words() about nltk HOT 5 CLOSED

# Download NLTK resources
nltk.download('words')
nltk.download('wordnet')

# Load NLTK words and WordNet lemmas
nltk_words = set(words.words())
wordnet_lemmas = set(lemma.name() for synset in wordnet.all_synsets() for lemma in synset.lemmas())

# Load Spacy model
nlp = spacy.load("en_core_web_sm")

# Extract Spacy vocabulary.
spacy_words = set([str(token) for token in nlp.vocab])

# Combine all sets
word_list = nltk_words.union(wordnet_lemmas).union(spacy_words)

def load_and_combine_word_sets():
    """
    Load words from NLTK, WordNet, SpaCy, and an XML file, then combine them into a single set.
    If a previously combined word set exists, it will be loaded from a file.
    """
    file_path = "_helps/word_list.pkl"

    # Check if a previously combined word set exists
    if os.path.exists(file_path):
        with open(file_path, "rb") as f:
            return pickle.load(f)

    # Load NLTK words and WordNet lemmas
    nltk_words = set(words.words())
    wordnet_lemmas = set(
        lemma.name() for synset in wordnet.all_synsets() for lemma in synset.lemmas()
    )

    # Load SpaCy model and extract vocabulary
    nlp = spacy.load("en_core_web_sm")
    spacy_words = set([str(token) for token in nlp.vocab])

    # Parse the XML file and extract words
    tree = ET.parse("_helps/english-wordnet-2022.xml")
    root = tree.getroot()
    new_words = set()
    for synset in root.findall(".//Synset"):
        example = synset.find("Example")
        if example is not None:
            example_text = example.text
            example_words = set(word_tokenize(example_text))
            new_words.update(example_words)

    # Combine all sets and add additional words
    combined_word_list = (
        nltk_words.union(wordnet_lemmas)
        .union(spacy_words)
        .union(new_words)
        .union(additional_words)
    )

    # Save the combined word set to a file
    with open(file_path, "wb") as f:
        pickle.dump(combined_word_list, f)

    print("Loaded word_list in load_and_combine_word_sets.")
    return combined_word_list

 >>> from nltk.stem import WordNetLemmatizer
 >>> wnl = WordNetLemmatizer()
 >>> print(wnl.lemmatize('dogs'))
 dog