-
-
Save amankharwal/692789da3d4a93a7816e91e35781624a 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
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.naive_bayes import MultinomialNB | |
data = pd.read_csv("https://raw.githubusercontent.com/amankharwal/SMS-Spam-Detection/master/spam.csv", encoding= 'latin-1') | |
data = data[["class", "message"]] | |
x = np.array(data["message"]) | |
y = np.array(data["class"]) | |
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 = MultinomialNB() | |
clf.fit(X_train,y_train) | |
import streamlit as st | |
st.title("Spam Detection System") | |
def spamdetection(): | |
user = st.text_area("Enter any Message or Email: ") | |
if len(user) < 1: | |
st.write(" ") | |
else: | |
sample = user | |
data = cv.transform([sample]).toarray() | |
a = clf.predict(data) | |
st.title(a) | |
spamdetection() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment