Kaggle_tweet_emotion_bert_transformers

import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import os
from tqdm import tqdm
import re
import inspect

import tensorflow as tf
from tensorflow import keras
# import tensorflow.keras.backend as K
from sklearn.model_selection import train_test_split
from nltk.corpus import stopwords
import nltk
import datetime
import transformers
from transformers import BertConfig,TFBertPreTrainedModel,BertTokenizer,TFBertMainLayer,TFBertModel



print("tf_version_ : ",tf.__version__)
print("transformers:",transformers.__version__)

tf_version_ :  2.0.0
transformers: 2.5.1

MAX_LENGTH = 36
BATCH_SIZE = 16

#Load data
path_home = r"/home/lowry/pro/kaggle_tweets/kaggle_tweets_emotion"
path_data = os.path.join(path_home,"data")
data_train = pd.read_csv(os.path.join(path_data,"train.csv"),encoding="utf-8")
data_test = pd.read_csv(os.path.join(path_data,"test.csv"),encoding="utf-8")
data_submit = pd.read_csv(os.path.join(path_data,"sample_submission.csv"),encoding="utf-8")

# data_clean
stopwords_english = stopwords.words("english")
# print(stopwords_english)
def cleanword(s):
    s = s.lower()
    temp = re.findall("http\S*",s)  
    for deletStr in temp:
        if deletStr != "":
            s = s.replace(deletStr," ")
    temp = re.findall("@\S*",s)
    for deletStr in temp:
        if deletStr != "":
            s = s.replace(deletStr," ")
    temp = re.findall("\d*",s)
    for deletStr in temp:
        if deletStr != "":
            s = s.replace(deletStr," ")
            
    temp = re.findall("\x89\S*",s)
    for deletStr in temp:
        if deletStr != "":
            s = s.replace(deletStr[:5]," ")

    s = s.replace("\n"," ")
    s = s.replace(","," ")
    s = s.replace(&#