Upload 5 files

app.py

@@ -0,0 +1,57 @@
+import streamlit as st
+import pickle
+import string
+from nltk.corpus import stopwords
+import nltk
+nltk.download('punkt')
+nltk.download('stopwords')
+nltk.download('corpus')
+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("SMS Spam Classifier")
+
+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])
+    # 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 sha256:25cedb79e6ec4d4a6910762b90d778c636614ab94611da97093b5f2100c5ba7c
+size 96605

nltk.txt

@@ -0,0 +1,2 @@
+stopwords
+punkt

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+nltk
+sklearn
+scikit-learn

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c0825aa38c71a5181d55e37a3cb810d15f38a52e3607640d434ad78b3d4696
+size 170105