File size: 2,972 Bytes
607d7d8 24f4f25 7fb9647 a6b7d4d dc010b2 a6b7d4d 6671142 dc010b2 6671142 dc010b2 7912a62 dc010b2 607d7d8 dc010b2 607d7d8 6671142 607d7d8 d856118 b88b222 607d7d8 264cc06 7ce7c66 dc010b2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import streamlit as st
from transformers import pipeline
from textblob import TextBlob
from transformers import BertForSequenceClassification, AdamW, BertConfig
st.set_page_config(layout='wide', initial_sidebar_state='expanded')
col1, col2= st.columns(2)
with col1:
st.title("Spamd: Turkish Spam Detector")
st.markdown("Message spam detection tool for Turkish language. Due the small size of the dataset, I decided to go with transformers technology Google BERT. Using the Turkish pre-trained model BERTurk, I imporved the accuracy of the tool by 18 percent compared to the previous model which used fastText.")
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'
pred = 'Predicted Class: '+ prediction
with col2:
st.header(pred)
with col2:
text = st.text_input("Enter the text you'd like to analyze for spam.")
if text or st.button('Analyze'):
predict(text)
import torch
import numpy as np
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-turkish-uncased")
from transformers import AutoModel
model = BertForSequenceClassification.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]
#st.write('Input', namestr(new_sentence, globals()),': \n', new_sentence)
|