-
Notifications
You must be signed in to change notification settings - Fork 0
/
app.py
68 lines (50 loc) · 1.64 KB
/
app.py
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
60
61
62
63
64
65
66
67
68
import streamlit as st
import pickle
import string
import nltk
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
# Download necessary NLTK data
nltk.download('punkt')
nltk.download('stopwords')
# Initialize the PorterStemmer
ps = PorterStemmer()
# Load the pickled TfidfVectorizer and classifier model
tfidf = pickle.load(open('vectorizer.pkl', 'rb'))
clf = pickle.load(open('model.pkl', 'rb'))
def transform_text(text):
# Convert to lowercase
text = text.lower()
# Tokenize the text
text = nltk.word_tokenize(text)
# Remove special characters and stopwords, and apply stemming
y = []
for i in text:
if i.isalnum() and i not in stopwords.words('english') and i not in string.punctuation:
y.append(ps.stem(i))
return " ".join(y)
# Streamlit app title
st.title('SMS Spam Classifier')
# Text input for the SMS
input_sms = st.text_area('Enter your SMS')
# Button for prediction
btn_inp = st.button("Click Here to Check")
if btn_inp:
# Transform the input text
transformed_text = transform_text(input_sms)
# Display transformed text for debugging
# st.write("Transformed Text:", transformed_text)
# Vectorize the transformed text
input_vector = tfidf.transform([transformed_text])
# Display input vector for debugging
# st.write("Input Vector:", input_vector)
# Make a prediction
result = clf.predict(input_vector)[0]
prob=clf.predict_proba(input_vector)
prob_1=prob[0][1]
st.write(f"Probability of Spam: {prob_1*100:.2f}%")
# Display the result
if result == 1:
st.header("Spam")
else:
st.header("Not Spam")