File size: 1,656 Bytes
f583409 503e370 f583409 503e370 f583409 8eb7f24 e815272 8eb7f24 f583409 8eb7f24 f583409 b38636e f583409 e815272 f583409 e815272 f583409 b38636e e815272 b38636e e815272 f583409 e815272 |
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 |
import tensorflow as tf
import streamlit as st
from transformers import BertTokenizer
from Sastrawi.Stemmer.StemmerFactory import StemmerFactory
from transformers import TFBertForSequenceClassification
# Fungsi untuk memuat model BERT dan tokenizer
PRE_TRAINED_MODEL = 'indobenchmark/indobert-base-p2'
bert_tokenizer = BertTokenizer.from_pretrained(PRE_TRAINED_MODEL)
bert_model = TFBertForSequenceClassification.from_pretrained(PRE_TRAINED_MODEL, num_labels=2)
bert_model.load_weights('model.h5')
# Inisialisasi stemmer dari Sastrawi
stemmer = StemmerFactory().create_stemmer() # Membuat stemmer Sastrawi
def preprocess_text(text):
# Menggunakan Sastrawi untuk stemming
stemmed_text = stemmer.stem(text.lower())
return stemmed_text
def predict_sentiment(text):
preprocessed_text = preprocess_text(text) # Pra-pemrosesan teks dengan Sastrawi
input_ids = tf.constant(bert_tokenizer.encode(preprocessed_text, add_special_tokens=True))[None, :] # Menambahkan token khusus [CLS] dan [SEP]
logits = bert_model(input_ids)[0]
probabilities = tf.nn.softmax(logits, axis=1)
sentiment = tf.argmax(probabilities, axis=1)
return sentiment.numpy()[0]
# Judul aplikasi
st.title('Prediksi Sentimen menggunakan BERT')
# Input teks
text = st.text_area('Masukkan teks', '')
# Tombol untuk memprediksi sentimen
if st.button('Cek'):
if text.strip() == '':
st.warning('Masukkan teks terlebih dahulu.')
st.write
else:
sentiment = predict_sentiment(text)
st.write("Hasil Sentiment :")
if sentiment == 0:
st.write('Negatif')
else:
st.write('Positif')
|