File size: 1,233 Bytes
09e06d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
import requests
import streamlit as st
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
# tokenizer
from transformers import AutoTokenizer, DistilBertTokenizerFast
# sequence tagging model + training-related 
from transformers import DistilBertForTokenClassification, Trainer, TrainingArguments
import numpy as np
import pandas as pd
import torch
import json
import sys
import os
#from datasets import load_metric
from sklearn.metrics import classification_report
from pandas import read_csv
from sklearn.linear_model import LogisticRegression
import sklearn.model_selection
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.model_selection import GridSearchCV
from sklearn.pipeline import Pipeline, FeatureUnion
import math
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_recall_fscore_support
from sklearn.model_selection import train_test_split
#from sklearn.metrics import make_scorer
import json
import re
import numpy as np 
import pandas as pd
import re
import nltk