Update app.py

app.py

@@ -80,7 +80,7 @@ class Comments_Data_Module(pl.LightningDataModule):
         self.max_token_length = max_token_length
         self.tokenizer = AutoTokenizer.from_pre
 
-     def setup(self, stage = None):
+    def setup(self, stage = None):
     if stage in (None, "fit"):
       self.train_dataset = Comments_Dataset(self.train_path, attributes=self.attributes, tokenizer=self.tokenizer)
       self.val_dataset = Comments_Dataset(self.val_path, attributes=self.attributes, tokenizer=self.tokenizer, sample=None)
@@ -148,7 +148,6 @@ class Comment_Classifier(pl.LightningModule):
     warmup_steps = math.floor(total_steps * self.config['warmup'])
     scheduler = get_cosine_schedule_with_warmup(optimizer, warmup_steps, total_steps)
     return [optimizer],[scheduler]
-
     
 config = {
     'model_name': 'distilroberta-base',
@@ -161,6 +160,7 @@ config = {
     'n_epochs': 100
 }
 
+##tokenizer
 model_name = 'distilroberta-base'
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 
@@ -168,14 +168,9 @@ model = Comment_Classifier(config=config)
 model.load_state_dict(torch.load("model_state_dict.pt"))
 model.eval()
 
-
-
 def prepare_tokenized_review(raw_review):
-  # Remove HTML tags with BS
   review_text = BeautifulSoup(raw_review).get_text()
-  # Removing non-letters using a regular expression
   review_text = re.sub("[^a-zA-Z!?]"," ", review_text)
-  # Convert words to lower case and split them
   words = review_text.lower().split()
 
   return " ".join(words)
@@ -201,23 +196,16 @@ def run_inference(encoding):
     final_output = torch.softmax(output[1][0],dim=0).cpu()
     print(final_output.numpy().tolist())
     return final_output.numpy().tolist()
-
-
-
+      
 test_tweets = test_df["comment_text"].values
-#streamlit section
 models = ["distilroberta-base"]
 model_pointers = ["default: distilroberta-base"]
 
-# current_random_tweet = test_tweets[random.randint(0,len(test_tweets))]
-# current_random_tweet = prepare_tokenized_review(current_random_tweet)
 st.write("1. Hit the button to view and see the analyis of a random tweet")
 
 with st.form(key="init_form"):
     current_random_tweet = test_tweets[random.randint(0,len(test_tweets))]
     current_random_tweet = prepare_tokenized_review(current_random_tweet)
- 
-
 
     choice = st.selectbox("Choose Model", model_pointers)
 
@@ -230,8 +218,9 @@ with st.form(key="init_form"):
         df["Sentiment Score"] = max(result)
         st.table(df)
 
+
     next_tweet = st.form_submit_button("Next Tweet")
 
 if next_tweet:
     with st.spinner("Analyzing..."):
-        st.write("")
+        st.write("")