Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
from nltk.util import pr
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
data = pd.read_csv("twitter.csv")
data["labels"] = data["class"].map({0: "Hate Speech", 1: "Offensive Language", 2: "No Hate and Offensive"})
data = data[["tweet", "labels"]]
import re
import nltk
stemmer = nltk.SnowballStemmer("english")
from nltk.corpus import stopwords
import string
def clean(text):
text = str(text).lower()
text = re.sub('\[.*?\]', '', text)
text = re.sub('https?://\S+|www\.\S+', '', text)
text = re.sub('<.*?>+', '', text)
text = re.sub('[%s]' % re.escape(string.punctuation), '', text)
text = re.sub('\n', '', text)
text = re.sub('\w*\d\w*', '', text)
text = [word for word in text.split(' ') if word not in stopword]
text=" ".join(text)
text = [stemmer.stem(word) for word in text.split(' ')]
text=" ".join(text)
return text
data["tweet"] = data["tweet"].apply(clean)
x = np.array(data["tweet"])
y = np.array(data["labels"])
cv = CountVectorizer()
X = cv.fit_transform(x) # Fit the Data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
clf = DecisionTreeClassifier(),y_train)
def hate_speech_detection():
import streamlit as st
st.title("Hate Speech Detection")
user = st.text_area("Enter any Tweet: ")
if len(user) < 1:
st.write(" ")
sample = user
data = cv.transform([sample]).toarray()
a = clf.predict(data)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment