Jovian
Sign In
Learn practical skills, build real-world projects, and advance your career
4 years ago

Toxic comment classification

Library imports

import pandas as pd
import numpy as np
import re
from sklearn.feature_extraction.text import ENGLISH_STOP_WORDS
from nltk.stem.porter import PorterStemmer
import emoji
import string
import spacy
nlp = spacy.load("en_core_web_sm")
from collections import Counter

Data

toxic_data = pd.read_csv('./data/jigsaw-toxic-comment-classification-challenge/train.csv')