Skip to content
TheChatArchiveThe Chat Archive
gpt-4-0314· OpenAIAi2 WildChat-4.8M (AI2)

Tolong ubah vektor representasi kata analisis sentimen CNN-LSTM berikut yang awalnya…

  1. User

    Tolong ubah vektor representasi kata analisis sentimen CNN-LSTM berikut yang awalnya menggunakan Word2Vec menjadi menggunakan IndoBERT! "import numpy as np import pandas as pd import pickle from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from sklearn.metrics import confusion_matrix, classification_report, accuracy_score from keras.preprocessing.text import Tokenizer from keras.utils import pad_sequences from keras.models import Sequential from keras.layers import Embedding, Conv1D, MaxPooling1D, LSTM, Dense, GlobalMaxPooling1D from keras.callbacks import EarlyStopping, ModelCheckpoint import gensim from gensim.models import Word2Vec from keras.layers import Dropout from keras.regularizers import l2 from keras.utils import to_categorical

    Parameter untuk regularisasi L2

    l2_coeff = 0.01

    Membaca dataset

    data_list = pickle.load(open('pre_processed_berita_121_joined_FIX_parpolheuristic_added.pkl', 'rb')) data = pd.DataFrame(data_list, columns=['judul', 'isi', 'pre_processed', 'Label', 'Partai_Politik_Heuristic']) data['Isi Berita'] = data['pre_processed']

    Tokenisasi dan Padding

    max_words = 10000 # mengurangi jumlah kata maksimum max_len = 500 # mengurangi panjang input tokenizer = Tokenizer(num_words=max_words) tokenizer.fit_on_texts(data['Isi Berita']) sequences = tokenizer.texts_to_sequences(data['Isi Berita']) X = pad_sequences(sequences, maxlen=max_len) y = to_categorical(data['Label'].astype('category').cat.codes)

    Membagi data menjadi data latih dan data uji

    X_train, X_test, y_train, y_test, idx_train, idx_test = train_test_split(X, y, data.index, test_size=0.25, random_state=42)

    Membuka model word2vec

    path = 'idwiki_word2vec_300.model' id_w2v = gensim.models.word2vec.Word2Vec.load(path) wv = id_w2v.wv

    Membuat embeding matrix

    embedding_dim = id_w2v.vector_size embedding_matrix = np.zeros((max_words, embedding_dim))

    for word, i in tokenizer.word_index.items(): if i < max_words: try: embedding_vector = wv[word] embedding_matrix[i] = embedding_vector except KeyError: pass

    Membangun model CNN-LSTM dengan pre-trained Word2Vec

    num_filters = 64 lstm_units = 64

    model = Sequential([ Embedding(input_dim=10000, output_dim=300, input_length=500, weights=[embedding_matrix], trainable=False), Conv1D(64, 5, activation='relu', kernel_regularizer=l2(0.01)), MaxPooling1D(pool_size=4), Dropout(0.25), LSTM(64, return_sequences=False, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01), dropout=0.2), Dense(32, activation='relu', kernel_regularizer=l2(0.01)), Dropout(0.5), Dense(3, activation='softmax') ])

    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

    Melatih model dengan early stopping dan model checkpoint

    checkpoint = ModelCheckpoint('model_cnn_lstm.h5', save_best_only=True, monitor='val_accuracy', mode='max') early_stopping = EarlyStopping(monitor='val_loss', patience=10, verbose=1)

    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=50, batch_size=128)"

  2. Assistant

    Berikut ini cara menggantikan Word2Vec dengan IndoBERT menggunakan Hugging Face Transformer:

    Pertama, install library Hugging Face Transformer:

    !pip install transformers
    

    Lalu, ubah kode di atas dengan cara berikut (perhatikan bagian yang diubah):

    import numpy as np
    import pandas as pd
    import pickle
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import LabelEncoder
    from sklearn.metrics import confusion_matrix, classification_report, accuracy_score
    from keras.preprocessing.text import Tokenizer
    from keras.utils import pad_sequences
    from keras.models import Sequential
    from keras.layers import Embedding, Conv1D, MaxPooling1D, LSTM, Dense, GlobalMaxPooling1D
    from keras.callbacks import EarlyStopping, ModelCheckpoint
    from keras.layers import Dropout
    from keras.regularizers import l2
    from keras.utils import to_categorical
    from transformers import BertTokenizer, TFBertModel  # <-- Tambahkan ini 
    
    # Parameter untuk regularisasi L2
    l2_coeff = 0.01
    
    # Membaca dataset
    data_list = pickle.load(open('pre_processed_berita_121_joined_FIX_parpolheuristic_added.pkl', 'rb'))
    data = pd.DataFrame(data_list, columns=['judul', 'isi', 'pre_processed', 'Label', 'Partai_Politik_Heuristic'])
    data['Isi Berita'] = data['pre_processed']
    
    # Load pre-trained IndoBERT tokenizer dan model
    bert_model_name = 'indolem/indobert-base-uncased'
    tokenizer = BertTokenizer.from_pretrained(bert_model_name)
    bert_model = TFBertModel.from_pretrained(bert_model_name)
    
    # Tokenisasi menggunakan tokenizer IndoBERT
    input_encodings = tokenizer(
        data['Isi Berita'].to_list(),
        truncation=True,
        padding='max_length',
        max_length=128,
        return_tensors='tf'
    )
    
    X = input_encodings['input_ids']
    y = to_categorical(data['Label'].astype('category').cat.codes)
    
    # Membagi data menjadi data latih dan data uji
    X_train, X_test, y_train, y_test, idx_train, idx_test = train_test_split(X, y, data.index, test_size=0.25, random_state=42)
    
    # Membangun model CNN-LSTM dengan pre-trained IndoBERT
    model = Sequential([
        bert_model.layers[0],  # <-- Tambahkan ini (perhatikan ini adalah layer pertama dari "bert_model" di atas)
        Conv1D(64, 5, activation='relu', kernel_regularizer=l2(0.01)),
        MaxPooling1D(pool_size=4),
        Dropout(0.25),
        LSTM(64, return_sequences=False, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01), dropout=0.2),
        Dense(32, activation='relu', kernel_regularizer=l2(0.01)),
        Dropout(0.5),
        Dense(3, activation='softmax')
    ])
    
    model.layers[0].trainable = False  # <-- Jangan lupa menambahkan ini untuk membekukan layer bert
    
    model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
    
    # Melatih model dengan early stopping dan model checkpoint
    checkpoint = ModelCheckpoint('model_cnn_lstm.h5', save_best_only=True, monitor='val_accuracy', mode='max')
    early_stopping = EarlyStopping(monitor='val_loss', patience=10, verbose=1)
    
    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=50, batch_size=128)
    

    Perhatikan di atas kita menggunakan 128 sebagai jumlah token maksimum dari teks, Anda dapat menyesuaikannya sesuai kebutuhan Anda. Selain itu, CNN-LSTM akan menggunakan keluaran dari layer embedding BERT (yang telah dilatih) untuk analisis sentimen, daripada Word2Vec. Anda juga sebaiknya membekukan layer BERT selama pelatihan model CNN-LSTM untuk mengurangi TRAIN_TIME_MODEL & mengurangi konektifitas hingga 1. Anda bisa hapus line model.layers[0].trainable = False jika Anda ingin melanjutkan fine-tune dengan CNN-LSTM Anda.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.