# Filter out records ( values in clean_body and tags) that have atleast one of the top tags

x=[] # To store the filtered clean_body values
y=[] # to store the corresponding tags
# Convert to list data type
lst_top_tags = list(top_tags)

for i in range(len(df['tags'])):
    temp=[]
    for tag in df['tags'][i]:
        if tag in lst_top_tags:
            temp.append(tag)

    if(len(temp)>1):
        x.append(df['Clean_Body'][i])
        y.append(temp)

model = model.to(device)

# Put model in evaluation mode
model.eval()

# Tracking variables 
pred_outs, true_labels = [], []
#i=0
# Predict 
for batch in pred_dataloader:
    # Add batch to GPU
    batch = tuple(t.to(device) for t in batch)
  
    # Unpack the inputs from our dataloader
    b_input_ids, b_attn_mask, b_labels = batch
 
    with torch.no_grad():
        # Forward pass, calculate logit predictions
        pred_out = model(b_input_ids,b_attn_mask)
        pred_out = torch.sigmoid(pred_out)
        # Move predicted output and labels to CPU
        pred_out = pred_out.detach().cpu().numpy()
        label_ids = b_labels.to('cpu').numpy()
        #i+=1
        # Store predictions and true labels
        #print(i)
        #print(outputs)
        #print(logits)
        #print(label_ids)
    pred_outs.append(pred_out)
    true_labels.append(label_ids)