Added preprocessing steps to app.py.

app.py

@@ -2,14 +2,38 @@
 import gradio as gr
 from sklearn.linear_model import LogisticRegression
 import pickle5 as pickle
+import re
+import string
+import nltk
+import re
+from nltk.corpus import stopwords
+nltk.download('stopwords')
+from sklearn.feature_extraction.text import CountVectorizer
 
 # file name
 lr_filename = 'logistic_regression.pkl'
 
+# Process input text, including removing stopwords, converting to lowercase, and removing punctuation
+def process_text(text):
+    text = stopwords.words('english')
+    text = str(text).lower()
+    text = re.sub(
+        f"[{re.escape(string.punctuation)}]", " ", text
+    )
+    text = " ".join(text.split())
+    return text
+
+# Vectorize input text
+vectorizer = CountVectorizer()
+def vectorize_text(text):
+    text = process_text(text)
+    text = [text]
+    return vectorizer.transform(text)
+
 # Load model from pickle file
 model = pickle.load(open(lr_filename, 'rb'))
 
-# Define function to make a prediction with the model
+
 def predict(text):
     return model.predict([text])