from transformers import pipeline
pipe = pipeline("text-classification", model="omykhailiv/bert-fake-news-recognition")
pipe.predict('Some text')

import re
import string
import spacy
from nltk.corpus import stopwords
lem = spacy.load('en_core_web_sm')
def testing_data_prep(text):
    """
    Args:
        text (str): The input text string.

    Returns:
        str: The preprocessed text string, or an empty string if the length
             does not meet the specified criteria (6 to 20 words).
    """
    # Convert text to lowercase for case-insensitive processing
    text = str(text).lower()

    # Remove HTML tags and their contents (e.g., "<tag>text</tag>")
    text = re.sub('<.*?>+\w+<.*?>', '', text)

    # Remove punctuation using regular expressions and string escaping
    text = re.sub('[%s]' % re.escape(string.punctuation), '', text)

    # Remove words containing alphanumeric characters followed by digits
    # (e.g., "model2023", "data10")
    text = re.sub('\w*\d\w*', '', text)

    # Remove newline characters
    text = re.sub('\n', '', text)

    # Replace multiple whitespace characters with a single space
    text = re.sub('\\s+', ' ', text)

    # Lemmatize words (convert them to their base form)
    text = lem(text)
    words = [word.lemma_ for word in text]
    
    # Removing stopwords, such as do, not, as, etc. (https://gist.github.com/sebleier/554280)
    new_filtered_words = [
    word for word in words if word not in stopwords.words('english')]
    if 20 >= len(new_filtered_words) >= 6:
      return ' '.join(new_filtered_words)
    return ' '

              precision    recall  f1-score   support

           0       0.93      0.94      0.94      3782
           1       0.95      0.94      0.95      4335

    accuracy                           0.94      8117
   macro avg       0.94      0.94      0.94      8117
weighted avg       0.94      0.94      0.94      8117

               precision    recall  f1-score   support

           0       0.93      0.88      0.90      2297
           1       0.89      0.93      0.91      2297

    accuracy                           0.91      4594
   macro avg       0.91      0.91      0.91      4594
weighted avg       0.91      0.91      0.91      4594

              precision    recall  f1-score   support

           0     0.9736    0.9750    0.9743     10455
           1     0.9726    0.9711    0.9718      9541

    accuracy                         0.9731     19996
   macro avg     0.9731    0.9731    0.9731     19996
weighted avg     0.9731    0.9731    0.9731     19996

              precision    recall  f1-score   support

           0       0.87      0.80      0.84       492
           1       0.82      0.89      0.85       508

    accuracy                           0.85      1000
   macro avg       0.85      0.85      0.85      1000
weighted avg       0.85      0.85      0.85      1000