-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathapp.py
64 lines (47 loc) · 1.54 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
import streamlit as st
import pandas as pd
import pickle
import string
from nltk.corpus import stopwords
import nltk
from PIL import Image
from nltk.stem.porter import PorterStemmer
image = Image.open(r'C:\Users\pc\ML\Projects\Recc Book\myimage.jpg')
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 = pd.read_pickle(r'C:\Users\pc\ML\Projects\Spam project\vectorizer.pkl')
model = pd.read_pickle(r'C:\Users\pc\ML\Projects\Spam project\model.pkl')
st.title("Email/SMS Spam Classifier")
st.sidebar.write('Built By -')
st.sidebar.title('Rishabh Vyas')
st.sidebar.image(image,caption='Machine Learning Engineer',width=160)
st.sidebar.write('E-mail - rishabhvyas472@gmail.com')
input_sms = st.text_area("Enter the message")
if st.button('Predict'):
# 1. preprocess
transformed_sms = transform_text(input_sms)
# 2. vectorize
vector_input = tfidf.transform([transformed_sms]).toarray()
# 3. predict
result = model.predict(vector_input)[0]
# 4. Display
if result == 1:
st.header("Spam")
else:
st.header("Not Spam")