Update app.py

app.py

@@ -1,6 +1,5 @@
 from sklearn.feature_extraction.text import TfidfVectorizer
 from TurkishStemmer import TurkishStemmer
-import nltk
 import string
 # import for loading python objects (scikit-learn models)
 import pickle
@@ -8,8 +7,8 @@ import streamlit as st
 import sklearn
 
 def custom_tokenizer_with_Turkish_stemmer(text):
-    # my text was unicode so I had to use the unicode-specific translate function. If your documents are strings, you will need to use a different `translate` function here. `Translated` here just does search-replace. See the trans_table: any matching character in the set is replaced with `None`
-    tokens = [word for word in nltk.word_tokenize(text.translate(trans_table))]
+    # tokenize text
+    tokens = text.split(" ")
     stems = [stemmerTR.stem(item.lower()) for item in tokens]
     return stems
 
@@ -34,7 +33,6 @@ def predictSMSdata(test_text):
     predicted = classifier.predict(tfidf_vectorizer_vectors_test)
     print(categories[predicted[0]])
 
-trans_table = {ord(c): None for c in string.punctuation + string.digits}
 stemmerTR = TurkishStemmer()
 
 text = st.text_area("enter some text!")