Update app.py

app.py

@@ -26,6 +26,25 @@ scheduler = CommitScheduler(
 
 classifier = pipeline(model = CLS_MODEL_NAME, tokenizer = 'cardiffnlp/twitter-roberta-large-2022-154m')
 
+def clean_brackets(text):
+    return text.replace('{', '(').replace('}', ')')
+
+def clean_emojis(text, type:str = ''):
+    if type=='rem':
+        return demoji.replace(text, '')
+    elif type!='keep':
+        return demoji.replace_with_desc(text, type)
+    else:
+        return text
+
+def clean_hashtags(text, hashtags=['#irony', '#sarcasm','#not']):
+    for hashtag in hashtags:
+        text = re.sub(hashtag, '', text, flags=re.I)
+    return re.sub(r' +', r' ', text)
+
+def clean_text(text):
+    return re.sub(' {2,}', ' ',clean_emojis(clean_hashtags(clean_brackets(text)))).strip()
+
 def save_json(entry: str, result) -> None:
     with scheduler.lock:
         with JSON_DATASET_PATH.open("a") as f:
@@ -34,7 +53,7 @@ def save_json(entry: str, result) -> None:
             f.write("\n")
 
 def classif(text: str):
-    return classifier(text)
+    return classifier(clean_text(text))
 
 with gr.Blocks() as demo:
     with gr.Row():