Upload 3 files

main.py

@@ -0,0 +1,56 @@
+import streamlit as st
+import pickle
+import string
+from nltk.corpus import stopwords
+import nltk
+from nltk.stem.porter import PorterStemmer
+
+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'))
+
+st.title("Email/SMS SPAM Classifier")
+
+input_sms = st.text_area("Enter the message")
+
+if st.button('Predict'):
+
+    # 1. preprocess
+    transform_sms = transform_text(input_sms)
+    # 2. vectorize
+    vector_input = tfidf.transform([transform_sms])
+    # 3. predict
+    result = model.predict(vector_input)[0]
+    # 4. Display
+    if result == 1:
+        st.header("Spam")
+    else:
+        st.header("Not Spam")
+
+
+

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de35ca1483a8de27d7f79035ae47517ce748ed03b664b22f140119cc04f28cf6
+size 96605

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b0676c55b0b1836d7e18d17a2183444d4bf4cd1dcc6d914d10544f88470b27e
+size 160664