Update pages/17_RNN_News.py

pages/17_RNN_News.py

@@ -51,25 +51,22 @@ def load_data():
     vocab = build_vocab_from_iterator(yield_tokens(train_iter), specials=["<unk>", "<pad>"])
     vocab.set_default_index(vocab["<unk>"])
 
-    # Define the text and label processing pipelines globally
-    global text_pipeline, label_pipeline
-    text_pipeline = lambda x: vocab(tokenizer(x))
-    label_pipeline = lambda x: int(x) - 1
+    return vocab, tokenizer, list(train_iter), list(test_iter)
 
-    # Create DataLoaders
-    train_dataset = list(train_iter)
-    test_dataset = list(test_iter)
+# Initialize global pipelines
+vocab, tokenizer, train_dataset, test_dataset = load_data()
+text_pipeline = lambda x: vocab(tokenizer(x))
+label_pipeline = lambda x: int(x) - 1
 
-    train_size = int(0.8 * len(train_dataset))
-    valid_size = len(train_dataset) - train_size
-    train_dataset, valid_dataset = random_split(train_dataset, [train_size, valid_size])
+# Create DataLoaders
+train_size = int(0.8 * len(train_dataset))
+valid_size = len(train_dataset) - train_size
+train_dataset, valid_dataset = random_split(train_dataset, [train_size, valid_size])
 
-    BATCH_SIZE = 64
-    train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
-    valid_loader = DataLoader(valid_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
-    test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
-
-    return vocab, train_loader, valid_loader, test_loader
+BATCH_SIZE = 64
+train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
+valid_loader = DataLoader(valid_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
+test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch)
 
 # Function to train the network
 def train_network(net, iterator, optimizer, criterion, epochs):
@@ -116,7 +113,6 @@ def evaluate_network(net, iterator, criterion):
 
 # Load data
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-vocab, train_loader, valid_loader, test_loader = load_data()
 
 # Streamlit interface
 st.title("RNN for Text Classification on AG News Dataset")