!pip install transformers
import pandas as pd
from wordcloud import WordCloud
import seaborn as sns
import re
import string
from collections import Counter, defaultdict

from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer

import plotly.express as px
from plotly.subplots import make_subplots
import plotly.graph_objects as go
from plotly.offline import plot

import matplotlib.gridspec as gridspec
from matplotlib.ticker import MaxNLocator
import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
import warnings
warnings.filterwarnings('ignore')
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
stopWords_nltk = set(stopwords.words('english'))


import re
from typing import Union, List
class CleanText():
    """ clearing text except digits () . , word character """

    def __init__(self, clean_pattern = r"[^A-ZĞÜŞİÖÇIa-zğüı'şöç0-9.\"',()]"):
        self.clean_pattern =clean_pattern

    def __call__(self, text: Union[str, list]) -> List[List[str]]:

        if isinstance(text, str):
            docs = [[text]]

        if isinstance(text, list):
            docs = text

        text = [[re.sub(self.clean_pattern, " ", sent) for sent in sents] for sents in docs]

        return text
def remove_emoji(data):
    emoj = re.compile("["
        u"\U0001F600-\U0001F64F"  # emoticons
        u"\U0001F300-\U0001F5FF"  # symbols & pictographs
        u"\U0001F680-\U0001F6FF"  # transport & map symbols
        u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
        u"\U00002500-\U00002BEF"
        u"\U00002702-\U000027B0"
        u"\U00002702-\U000027B0"
        u"\U000024C2-\U0001F251"
        u"\U0001f926-\U0001f937"
        u"\U00010000-\U0010ffff"
        u"\u2640-\u2642"
        u"\u2600-\u2B55"
        u"\u200d"
        u"\u23cf"
        u"\u23e9"
        u"\u231a"
        u"\ufe0f"  # dingbats
        u"\u3030"
                      "]+", re.UNICODE)
    return re.sub(emoj, '', data)