Update app.py

app.py

@@ -1,13 +1,26 @@
 import gradio as gr
-from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.feature_extraction.text import CountVectorizer 
 from sklearn.feature_extraction.text import TfidfVectorizer
 import joblib
+from nltk.stem.porter import PorterStemmer
+import re
 
 # import warnings
 # from sklearn.exceptions import InconsistentVersionWarning
 # warnings.filterwarnings("ignore", category=InconsistentVersionWarning)
 
+ps = PorterStemmer()
 
+def preprocess_for_bow(text):
+    corpus = []
+    text = re.sub('[^a-zA-Z0-9$£€¥%]',' ',text)
+    text = text.lower()
+    text = text.split()
+    text = [ps.stem(t) for t in text if t not in stopwords.words('english')]
+    corpus.append(' '.join(text))
+
+    return corpus
+    
 vectorizer = joblib.load('./vectorizer.pkl')
 nb_classifier = joblib.load('./nb_classifier.pkl')
 tfidf_vectorizer = joblib.load('./tfidf_vectorizer.pkl')
@@ -16,6 +29,7 @@ random_forest = joblib.load('./random_forest.pkl')
 def classify(text,choice):
   corpus=[text]
   if(choice == 1):
+      corpus = preprocess_for_bow(text)
       features = vectorizer.transform(corpus).toarray()
       prediction = nb_classifier.predict(features)
   elif(choice == 2):