Upload 5 files

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+import pickle
+import string
+import sklearn
+import nltk
+
+
+#Downloading NLTK libraries
+nltk.download('punkt')
+nltk.download('stopwords')
+
+from nltk.corpus import stopwords
+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_input("Enter the message")
+
+if st.button('Predict'):
+
+# 1. pre process
+  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")
+
+
+

main.py

@@ -0,0 +1,73 @@
+from flask import Flask, render_template, request
+import pickle
+import string
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem.porter import PorterStemmer
+
+app = Flask(__name__)
+
+# Downloading NLTK libraries
+nltk.download('punkt')
+nltk.download('stopwords')
+
+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)
+
+# Load the TF-IDF vectorizer and the model
+with open('vectorizer.pkl', 'rb') as f:
+    tfidf = pickle.load(f)
+
+with open('model.pkl', 'rb') as f:
+    model = pickle.load(f)
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    if request.method == 'POST':
+        input_sms = request.form['sms']
+
+        # Preprocess the input
+        transform_sms = transform_text(input_sms)
+
+        # Vectorize the input
+        vector_input = tfidf.transform([transform_sms])
+
+        # Predict
+        result = model.predict(vector_input)[0]
+        # Convert result to string
+        if result == 1:
+            result_text = "SPAM"
+        else:
+            result_text = "NOT SPAM"
+
+        # Return prediction result
+        return render_template('result.html', result=result_text)
+
+if __name__ == '__main__':
+    app.run(debug=True)

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d353a616171e314953eabebc9a78df13bb413ce897405b9a2f75bf66628f6b88
+size 96613

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e72be2ef2426d68ec215d4c53863d551f808d70afed6a7d168c70abd3052809
+size 181743