functions.py

def get_wordnet_pos(treebank_tag):
    if treebank_tag.startswith('J'):
        return wordnet.ADJ
    elif treebank_tag.startswith('V'):
        return wordnet.VERB
    elif treebank_tag.startswith('N'):
        return wordnet.NOUN
    elif treebank_tag.startswith('R'):
        return wordnet.ADV
    else:
        return wordnet.NOUN

lemmatizer = WordNetLemmatizer()

def preprocess_text(text):
    text = text.lower() # lowercase text
    tokens = word_tokenize(text) # tokenize
    filtered_words = [word for word in tokens if word.lower() not in stopword_list]
    lemmatized_words = [lemmatizer.lemmatize(w, get_wordnet_pos(w)) for w in filtered_words]
    lemmatized_clean = [word.translate(str.maketrans('', '', string.punctuation)) for word in lemmatized_words]
    return ' '.join(lemmatized_clean)

def text_model(df):
  df['preprocessed_text'] = df['Comment'].apply(preprocess_text)
  return df['preprocessed_text']

def prediction(model, X):
  y_pred = model.predict(X)
  predictions = np.argmax(y_pred, axis=1)
  for index, val in enumerate(predictions):
    if val == 0:
      print(f"Text {index} indicates the person is feeling FEAR")
    elif val == 1:
      print(f"Text {index} indicates the person is feeling ANGER")
    else:
      print(f"Text {index} indicates the person is feeling JOY")