-
-
Save amankharwal/00af11fbb7f536a9c3cd9e2b79955e4e to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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") | |
#print(data.head()) | |
data["labels"] = data["class"].map({0: "Hate Speech", 1: "Offensive Language", 2: "No Hate and Offensive"}) | |
#print(data.head()) | |
data = data[["tweet", "labels"]] | |
#print(data.head()) | |
import re | |
import nltk | |
stemmer = nltk.SnowballStemmer("english") | |
from nltk.corpus import stopwords | |
import string | |
stopword=set(stopwords.words('english')) | |
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) | |
#print(data.head()) | |
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() | |
clf.fit(X_train,y_train) | |
clf.score(X_test,y_test) | |
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(" ") | |
else: | |
sample = user | |
data = cv.transform([sample]).toarray() | |
a = clf.predict(data) | |
st.title(a) | |
hate_speech_detection() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment