app.py

import streamlit as st
from transformers import pipeline
from textblob import TextBlob




st.set_page_config(layout='wide', initial_sidebar_state='expanded')
st.title("Spamd: Turkish Spam Detector")
st.markdown("Enter the text you'd like to analyze for spam.")
text = st.text_input("Enter the text you'd like to analyze for spam.")

"""Spamd_SpamDetector_Turkish_BERT_22.09.2022.ipynb

Original file is located at
    https://colab.research.google.com/drive/1QuorqAuLsmomesZHsaQHEZgzbPEM8YTH
"""



import torch
import numpy as np

from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-turkish-uncased")
from transformers import AutoModel
model = AutoModel.from_pretrained("NimaKL/spamd_model")

token_id = []
attention_masks = []

def preprocessing(input_text, tokenizer):
  '''
  Returns <class transformers.tokenization_utils_base.BatchEncoding> with the following fields:
    - input_ids: list of token ids
    - token_type_ids: list of token type ids
    - attention_mask: list of indices (0,1) specifying which tokens should considered by the model (return_attention_mask = True).
  '''
  return tokenizer.encode_plus(
                        input_text,
                        add_special_tokens = True,
                        max_length = 32,
                        pad_to_max_length = True,
                        return_attention_mask = True,
                        return_tensors = 'pt'
                   )

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
#Used for printing the name if the variables. Removing it will not intrupt the project.
def namestr(obj, namespace):
    return [name for name in namespace if namespace[name] is obj]

def predict(new_sentence):
    # We need Token IDs and Attention Mask for inference on the new sentence
    test_ids = []
    test_attention_mask = []

    # Apply the tokenizer
    encoding = preprocessing(new_sentence, tokenizer)

    # Extract IDs and Attention Mask
    test_ids.append(encoding['input_ids'])
    test_attention_mask.append(encoding['attention_mask'])
    test_ids = torch.cat(test_ids, dim = 0)
    test_attention_mask = torch.cat(test_attention_mask, dim = 0)

    # Forward pass, calculate logit predictions
    with torch.no_grad():
      output = model(test_ids.to(device), token_type_ids = None, attention_mask = test_attention_mask.to(device))

    prediction = 'Spam' if np.argmax(output.logits.cpu().numpy()).flatten().item() == 1 else 'Normal'

    
    st.write('Input', namestr(new_sentence, globals()),': \n', new_sentence) 
      # Remove the namestr(new_sentence, globals()) in case of an error      
    st.write('Predicted Class: ', prediction,'\n----------------------------------\n')
    
predict(text)



'''
@software{stefan_schweter_2020_3770924,
  author       = {Stefan Schweter},
  title        = {BERTurk - BERT models for Turkish},
  month        = apr,
  year         = 2020,
  publisher    = {Zenodo},
  version      = {1.0.0},
  doi          = {10.5281/zenodo.3770924},
  url          = {https://doi.org/10.5281/zenodo.3770924}
}
'''