Spaces:
Sleeping
Sleeping
Abhinav Jangra
commited on
Commit
·
75f6b3f
1
Parent(s):
136d7b4
Upload app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pickle
|
| 3 |
+
import string
|
| 4 |
+
from nltk.corpus import stopwords
|
| 5 |
+
import nltk
|
| 6 |
+
nltk.download('punkt')
|
| 7 |
+
nltk.download('stopwords')
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
from nltk.stem.porter import PorterStemmer
|
| 11 |
+
|
| 12 |
+
ps=PorterStemmer()
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def transform_text(text):
|
| 18 |
+
text=text.lower()
|
| 19 |
+
text=nltk.word_tokenize(text)
|
| 20 |
+
|
| 21 |
+
y=[]
|
| 22 |
+
for i in text:
|
| 23 |
+
if i.isalnum():
|
| 24 |
+
y.append(i)
|
| 25 |
+
|
| 26 |
+
text=y[:]
|
| 27 |
+
y.clear()
|
| 28 |
+
|
| 29 |
+
for i in text:
|
| 30 |
+
if i not in stopwords.words('english') and i not in string.punctuation:
|
| 31 |
+
y.append(i)
|
| 32 |
+
|
| 33 |
+
text=y[:]
|
| 34 |
+
y.clear()
|
| 35 |
+
|
| 36 |
+
for i in text:
|
| 37 |
+
y.append(ps.stem(i))
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
return " ".join(y)
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
|
| 44 |
+
tfidf=pickle.load(open('vectorizer.pkl','rb'))
|
| 45 |
+
model=pickle.load(open('model.pkl','rb'))
|
| 46 |
+
|
| 47 |
+
st.title("EMAIL/SMS SPAM CLASSIFIER")
|
| 48 |
+
|
| 49 |
+
#follow documentation for syntax and fn
|
| 50 |
+
|
| 51 |
+
input_sms=st.text_input("Enter the message :)")
|
| 52 |
+
|
| 53 |
+
if st.button('predict'):
|
| 54 |
+
|
| 55 |
+
#1.preprocess
|
| 56 |
+
transformed_sms=transform_text(input_sms)
|
| 57 |
+
#2.vectorize
|
| 58 |
+
vector_input=tfidf.transform([transformed_sms])
|
| 59 |
+
#3.predict
|
| 60 |
+
result=model.predict(vector_input)[0]
|
| 61 |
+
#4.display
|
| 62 |
+
|
| 63 |
+
if result==1:
|
| 64 |
+
st.header("make some friends loner")
|
| 65 |
+
|
| 66 |
+
else:
|
| 67 |
+
st.header("not spam uwu")
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
|