removing misc class

app.py

@@ -58,7 +58,7 @@ def preprocess(text):
     cleaned_text = cleaned_text.upper()
     
     # Remove unwanted words
-    words_to_remove = ["MPS", "POS", "BIL", "ONL", "BANGALORE", "PVT", "LTD", "INDIA", "LT"]
+    words_to_remove = ["MPS", "POS", "BIL", "ONL", "BANGALORE", "PVT", "LTD", "INDIA", "LT", "xxxxxxxxxxxx"]
     cleaned_text = " ".join([word for word in cleaned_text.split() if word not in words_to_remove])
     
     # Convert to lowercase
@@ -79,17 +79,17 @@ output = gr.Label(label="Output")
 
 #example object
 transactions_and_tags = [
-    ["MPS/TRUFFLES/202303261700/034587/Bangalore", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["MPS/TACO BELL/202304012247/108300/BANGALORE", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS XXXXXXXXXXXX0001 APOLLO PHARMACY", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["BIL/ONL/000471093694/1MG Techno/X7ZRUSVLURFQZO", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS XXXXXXXXXXXX1111 DECATHLON SPORTS", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS XXXXXXXXXXXX1111 IKEA INDIA PVT L", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS XXXXXXXXXXXX1111 WWW AMAZON IN", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["ME DC SI XXXXXXXXXXXX1111 SPOTIFY SI", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS/NETFLIX/1140920002/100623/17:25", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["POS XXXXXXXXXXXX1110 MAKEMYTRIP INDIA", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"],
-    ["BIL/ONL/000691178015/IRCTC Serv/XZZBX91LTCY1AZ", "Medical, Food, Shopping, Subscription, Travel, Miscellaneous"]
+    ["MPS/TRUFFLES/202303261700/034587/Bangalore", "Medical, Food, Shopping, Subscription, Travel"],
+    ["MPS/TACO BELL/202304012247/108300/BANGALORE", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS XXXXXXXXXXXX0001 APOLLO PHARMACY", "Medical, Food, Shopping, Subscription, Travel"],
+    ["BIL/ONL/000471093694/1MG Techno/X7ZRUSVLURFQZO", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS XXXXXXXXXXXX1111 DECATHLON SPORTS", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS XXXXXXXXXXXX1111 IKEA INDIA PVT L", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS XXXXXXXXXXXX1111 WWW AMAZON IN", "Medical, Food, Shopping, Subscription, Travel"],
+    ["ME DC SI XXXXXXXXXXXX1111 SPOTIFY SI", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS/NETFLIX/1140920002/100623/17:25", "Medical, Food, Shopping, Subscription, Travel"],
+    ["POS XXXXXXXXXXXX1110 MAKEMYTRIP INDIA", "Medical, Food, Shopping, Subscription, Travel"],
+    ["BIL/ONL/000691178015/IRCTC Serv/XZZBX91LTCY1AZ", "Medical, Food, Shopping, Subscription, Travel"]
 ]
 
 #create interface