Spaces:
Sleeping
Sleeping
File size: 1,346 Bytes
18fb410 887180a 7300197 9cedfb2 af7387d 18fb410 552f284 db085d0 552f284 5caffca 5f9e365 18fb410 5f9e365 887180a 5f9e365 af7387d 5f9e365 |
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 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 |
import gradio as gr
import pickle
import string
from nltk.corpus import stopwords
import nltk
from nltk.stem.porter import PorterStemmer
import sklearn
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('corpus')
ps = PorterStemmer()
def transform_text(text):
text = text.lower()
text = nltk.word_tokenize(text)
y = []
for i in text:
if i.isalnum():
y.append(i)
text = y[:]
y.clear()
for i in text:
if i not in stopwords.words('english') and i not in string.punctuation:
y.append(i)
text = y[:]
y.clear()
for i in text:
y.append(ps.stem(i))
return " ".join(y)
tfidf = pickle.load(open('vectorizer.pkl','rb'))
model = pickle.load(open('model.pkl','rb'))
def predict_spam(input_sms):
# 1. Preprocess
transformed_sms = transform_text(input_sms)
# 2. Vectorize
vector_input = tfidf.transform([transformed_sms])
# 3. Predict
result = model.predict(vector_input)[0]
# 4. Display result
return "Spam" if result == 1 else "Not Spam"
title = "Email/SMS Spam Classifier"
inputs = gr.Text("Enter the message")
outputs = gr.Textbox(label='Results',lines = 20)
interface = gr.Interface(fn=predict_spam, inputs=inputs, outputs=outputs,title=title)
interface.launch(share=True) |