Skip to content
TheChatArchiveThe Chat Archive
gpt-4-0314· openaiHugging Face Suzhen/CodeChat

pada kode analisis sentimen berikut, tambahkan model CNN-LSTM ke kodenya dan atur…

  1. User

    pada kode analisis sentimen berikut, tambahkan model CNN-LSTM ke kodenya dan atur sedemikian rupa, tambahkan kode lain jika diperlukan! Kode analisis sentimen: import pickle import pandas as pd import numpy as np import torch from torch.utils.data import Dataset from sklearn.model_selection import train_test_split from sklearn.metrics import classification_report, accuracy_score

    from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer

    Membaca dataset

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

    Tentukan label

    sentiment_mapping = {'Positif': 0, 'Negatif': 1, 'Netral': 2} data['Label'] = data['Label'].map(sentiment_mapping)

    Split dataset

    train_texts, test_texts, train_labels, test_labels = train_test_split(data['Isi Berita'].tolist(), data['Label'].tolist(), test_size=0.20, random_state=42)

    Load tokenizer dan model

    tokenizer = AutoTokenizer.from_pretrained('indolem/indobert-base-uncased') model = AutoModelForSequenceClassification.from_pretrained('indolem/indobert-base-uncased', num_labels=len(sentiment_mapping))

    Atur dataset

    class NewsDataset(Dataset): def init(self, texts, labels, tokenizer, max_len): self.texts = texts self.labels = labels self.tokenizer = tokenizer self.max_len = max_len

    def __len__(self):
        return len(self.texts)
    
    def __getitem__(self, index):
        text = str(self.texts[index])
        label = self.labels[index]
        inputs = self.tokenizer.encode_plus(
            text, add_special_tokens=True, max_length=self.max_len, padding='max_length', truncation=True
        )
    
        return {'input_ids': torch.tensor(inputs['input_ids'], dtype=torch.long),
                'attention_mask': torch.tensor(inputs['attention_mask'], dtype=torch.long),
                'labels': torch.tensor(label, dtype=torch.long)
                }
    

    max_len = 400 train_dataset = NewsDataset(train_texts, train_labels, tokenizer, max_len) test_dataset = NewsDataset(test_texts, test_labels, tokenizer, max_len)"

    Kode CNN-LSTM: " # Membangun model untuk lipatan saat ini model = Sequential([ Embedding(input_dim=10000, output_dim=300, input_length=500, weights=[embedding_matrix], trainable=False), Conv1D(256, 3, activation='relu', kernel_regularizer=l2(0.01)), GlobalMaxPooling1D(), Dropout(0.5), Reshape((-1, 256)), LSTM(200, return_sequences=False, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01)), Dropout(0.7), Dense(32, activation='relu', kernel_regularizer=l2(0.01)), Dropout(0.5), Dense(3, activation='softmax') ])

    # Buat callback early stopping
    callback_es = EarlyStopping(monitor='val_loss', patience=5, verbose=1, restore_best_weights=True)
    
    initial_learning_rate = 0.0001
    optimizer = Adam(learning_rate=initial_learning_rate)
    
    # Kompilasi model
    model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
    
    # Latih model dengan menggunakan learning rate scheduler dan early stopping dalam callbacks
    history = model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=100, batch_size=128, callbacks=[callback_es])"
    

    di akhir tambahkan kode akurasi dan classification report: "# Menguji model predictions, true_labels, _ = trainer.predict(test_dataset) predicted_labels = np.argmax(predictions, axis=1) print(classification_report(test_labels, predicted_labels)) print("Accuracy: ", accuracy_score(test_labels, predicted_labels))"

  2. Assistant

    Untuk menambahkan model CNN-LSTM ke kode analisis sentimen di atas, kita perlu membuat beberapa modifikasi pada kode. Pertama, kita bisa menggunakan Tokenizer dari transformer untuk menggantikan metode preprocessing yang ada. Kemudian, kita perlu menggantikan model Sequential dengan model LSTM dan CNN baru. Berikut adalah kode yang telah dimodifikasi:

    import pickle
    import pandas as pd
    import numpy as np
    import torch
    from torch.utils.data import Dataset
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import classification_report, accuracy_score
    
    from transformers import AutoTokenizer, TrainingArguments, Trainer
    from keras.utils import to_categorical
    from keras.preprocessing.sequence import pad_sequences
    from keras.models import Sequential
    from keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dropout, Reshape, LSTM, Dense
    from keras.callbacks import EarlyStopping
    from keras.optimizers import Adam
    from keras.regularizers import l2
    
    # Membaca dataset
    data_list = pickle.load(open('filtered_pre_processed_berita_joined_done.pkl', 'rb'))
    data = pd.DataFrame(data_list, columns=['judul', 'isi', 'pre_processed', 'Label', 'Nama_Pelabel'])
    data['Isi Berita'] = data['pre_processed']
    
    # Tentukan label
    sentiment_mapping = {'Positif': 0, 'Negatif': 1, 'Netral': 2}
    data['Label'] = data['Label'].map(sentiment_mapping)
    
    # Split dataset
    train_texts, test_texts, train_labels, test_labels = train_test_split(data['Isi Berita'].tolist(), data['Label'].tolist(), test_size=0.20, random_state=42)
    
    # Load tokenizer dan model
    tokenizer = AutoTokenizer.from_pretrained('indolem/indobert-base-uncased')
    
    def encode(texts, tokenizer, max_len=500):
        input_ids = []
        for text in texts:
            input_dict = tokenizer.encode_plus(text, add_special_tokens=True, max_length=max_len, padding='max_length', truncation=True)
            input_ids.append(input_dict['input_ids'])
        return np.array(input_ids)
    
    train_input_ids = encode(train_texts, tokenizer)
    test_input_ids = encode(test_texts, tokenizer)
    
    # One-hot encode labels
    train_one_hot_labels = to_categorical(train_labels)
    test_one_hot_labels = to_categorical(test_labels)
    
    # CNN-LSTM model
    model = Sequential([
        Embedding(input_dim=tokenizer.vocab_size,
                  output_dim=300,
                  input_length=500,
                  mask_zero=True,
                  ),
        Conv1D(256, 3, activation='relu', kernel_regularizer=l2(0.01)),
        GlobalMaxPooling1D(),
        Dropout(0.5),
        Reshape((-1, 256)),
        LSTM(200, return_sequences=False, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01)),
        Dropout(0.7),
        Dense(32, activation='relu', kernel_regularizer=l2(0.01)),
        Dropout(0.5),
        Dense(len(sentiment_mapping), activation='softmax')
    ])
    
    callback_es = EarlyStopping(monitor='val_loss', patience=5, verbose=1, restore_best_weights=True)
    initial_learning_rate = 0.0001
    optimizer = Adam(learning_rate=initial_learning_rate)
    
    # Kompilasi model
    model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
    
    # Latih model
    history = model.fit(train_input_ids, train_one_hot_labels, validation_data=(test_input_ids, test_one_hot_labels), epochs=100, batch_size=128, callbacks=[callback_es])
    
    # Menguji model
    predictions = model.predict(test_input_ids)
    predicted_labels = np.argmax(predictions, axis=1)
    print(classification_report(test_labels, predicted_labels))
    print("Accuracy: ", accuracy_score(test_labels, predicted_labels))
    

    Perlu dicatat bahwa dalam contoh ini, kita menggunakan tokenizer dari model IndoBERT dan tidak menggunakan pretrained embedding. Anda dapat menyesuaikan kode ini sesuai kebutuhan Anda, misalnya, dengan memasukkan pretrained embedding atau mengubah parameter lainnya.

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