Update app.py

app.py

@@ -40,13 +40,15 @@ model, tokenizer, mlb = load_model_and_tokenizer()
 # ========== data loading ==========
 
 
+from datasets import load_dataset
+
 @st.cache_data
 def load_data():
-    X = pd.read_csv('X_text.csv')['text_clean'].astype(str)
-    Y = pd.read_csv('Y_tags.csv', converters={'Tags': eval})['Tags']
+    ds = load_dataset("Framby/SOF")['train']
+    X = pd.Series(ds['text_clean'])
+    Y = pd.Series(ds['Tags'])
     return X, Y
 
-
 X, Y = load_data()
 
 # ========== prediction function ==========