Update app.py

app.py

@@ -1,56 +1,113 @@
-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")
-
-
-
+# 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")
+
+import streamlit as st
+import pickle
+import string
+import nltk
+from nltk.corpus import stopwords
+from nltk.stem.porter import PorterStemmer
+
+# Download NLTK resources if not already downloaded
+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)
+
+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")
+
+