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

Ubah kode ini dengan Stratified K Foldnya menggunakan data training, dan lakukan…

  1. User

    Ubah kode ini dengan Stratified K Foldnya menggunakan data training, dan lakukan pengujian pada data testing setelah semua proses k fold selesai! import pickle import pandas as pd import numpy as np from keras.preprocessing.text import Tokenizer from keras.utils import pad_sequences from keras.models import Sequential from keras.layers import Embedding, LSTM, Dense, Dropout, Conv1D, GlobalMaxPooling1D, Reshape from keras.layers import Flatten from keras.utils import to_categorical from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score, classification_report import gensim from keras.regularizers import l2 from keras.callbacks import EarlyStopping from keras.optimizers import Adam

    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)

    Menggunakan pre-trained word2vec Bahasa Indonesia

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

    Membuat matriks embedding

    embedding_dim = 300 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 from sklearn.model_selection import StratifiedKFold

    Inisialisasi StratifiedKFold

    n_splits = 5 skf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)

    Konversi kategori target ke nilai numerik

    y_categorical = data['Label'].astype('category').cat.codes

    Menyimpan akurasi dan report untuk setiap lipatan

    accuracies = [] class_reports = []

    iter_num = 1

    histories = []

    for train_index, test_index in skf.split(X, y_categorical): print("\nTraining and evaluating model for fold", iter_num)

    # Membagi data berdasarkan indeks dari lipatan saat ini
    X_train, X_test = X[train_index], X[test_index]
    y_train, y_test = y[train_index], y[test_index]
    
    # Membangun model untuk lipatan saat ini
    model = Sequential()
    model.add(Embedding(max_words, embedding_dim, weights=[embedding_matrix], input_length=max_len, trainable=False))
    model.add(LSTM(200, return_sequences=True, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01)))
    model.add(Conv1D(256, 3, activation='relu', kernel_regularizer=l2(0.01)))
    model.add(GlobalMaxPooling1D())
    model.add(Dropout(0.1))
    Reshape((-1, 256)),
    model.add(Flatten())
    model.add(Dropout(0.5))
    model.add(Dense(32, activation='relu', kernel_regularizer=l2(0.01)))
    model.add(Dropout(0.2))
    model.add(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=50, batch_size=128, callbacks=[callback_es])
    histories.append(history)
    model.save('LSTM-CNN_Word2Vec_Tertinggi_LSTM200_CNN256_' + str(iter_num) + '.h5')
    
    # Evaluasi model pada lipatan saat ini
    y_pred = model.predict(X_test)
    y_pred_labels = np.argmax(y_pred, axis=1)
    y_test_labels = np.argmax(y_test, axis=1)
    
    # Menghitung akurasi
    accuracy = accuracy_score(y_test_labels, y_pred_labels)
    print("Fold", iter_num, "Accuracy: {:.2f}%".format(accuracy * 100))
    
    # Classification report
    class_report = classification_report(y_test_labels, y_pred_labels)
    
    # Menambahkan akurasi dan report ke daftar
    accuracies.append(accuracy)
    class_reports.append(class_report)
    
    iter_num += 1
    

    Mengevaluasi model

    y_pred = model.predict(X_test) y_pred = np.argmax(y_pred, axis=1) y_true = np.argmax(y_test, axis=1)

    Menambahkan kolom hasil prediksi ke DataFrame data

    data['Label_Hasil_Prediksi'] = None # inisialisasi kolom dengan None data.loc[idx_test, 'Label_Hasil_Prediksi'] = y_pred

    Export ke file CSV

    data.to_csv('hasil_2_BARU_19MEI.csv', columns=['judul', 'isi', 'Label', 'Label_Hasil_Prediksi', 'Partai_Politik_Heuristic'], index=False, sep=';')

    Menghitung akurasi

    accuracy = accuracy_score(y_true, y_pred) print(f"Akurasi: {accuracy}")

    Menampilkan classification report

    report = classification_report(y_true, y_pred, target_names=['Negatif', 'Netral', 'Positif']) print("Classification Report:") print(report)

  2. Assistant

    Berikut ini adalah kode yang telah dimodifikasi dengan menggunakan Stratified K-Fold pada data training dan melakukan uji pada data testing setelah proses K-Fold selesai:

    import pickle
    import pandas as pd
    import numpy as np
    from keras.preprocessing.text import Tokenizer
    from keras.utils import pad_sequences
    from keras.models import Sequential
    from keras.layers import Embedding, LSTM, Dense, Dropout, Conv1D, GlobalMaxPooling1D, Reshape
    from keras.layers import Flatten
    from keras.utils import to_categorical
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score, classification_report
    import gensim
    from keras.regularizers import l2 
    from keras.callbacks import EarlyStopping
    from keras.optimizers import Adam
    from sklearn.model_selection import StratifiedKFold
    
    # 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
    max_len =  500
    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)
    
    # Menggunakan pre-trained word2vec Bahasa Indonesia
    path = 'idwiki_word2vec_300.model'
    id_w2v = gensim.models.word2vec.Word2Vec.load(path)
    wv = id_w2v.wv
    
    # Membuat matriks embedding
    embedding_dim = 300
    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
    
    # Membagi data menjadi data latih dan data uji
    X_train_full, X_test, y_train_full, y_test, idx_train_full, idx_test = train_test_split(X, y, data.index, test_size=0.25, random_state=42)
    
    n_splits = 5
    skf = StratifiedKFold(n_splits=n_splits, shuffle=True, random_state=42)
    
    y_categorical = data['Label'].astype('category').cat.codes
    
    accuracies = []
    class_reports = []
    
    iter_num = 1
    
    histories = []
    
    for train_index, val_index in skf.split(X_train_full, y_categorical[idx_train_full]):
        print("\nTraining and evaluating model for fold", iter_num)
    
        X_train, X_val = X_train_full[train_index], X_train_full[val_index]
        y_train, y_val = y_train_full[train_index], y_train_full[val_index]
    
        model = Sequential()
        model.add(Embedding(max_words, embedding_dim, weights=[embedding_matrix], input_length=max_len, trainable=False))
        model.add(LSTM(200, return_sequences=True, kernel_regularizer=l2(0.01), recurrent_regularizer=l2(0.01)))
        model.add(Conv1D(256, 3, activation='relu', kernel_regularizer=l2(0.01)))
        model.add(GlobalMaxPooling1D())
        model.add(Dropout(0.1))
        Reshape((-1, 256)),
        model.add(Flatten())
        model.add(Dropout(0.5))
        model.add(Dense(32, activation='relu', kernel_regularizer=l2(0.01)))
        model.add(Dropout(0.2))
        model.add(Dense(3, 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)
        
        model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
    
        history = model.fit(X_train, y_train, validation_data=(X_val, y_val), epochs=50, batch_size=128, callbacks=[callback_es])
        histories.append(history)
    
        iter_num += 1
    
    # Evaluate the final model on X_test and y_test
    y_pred = model.predict(X_test)
    y_pred_labels = np.argmax(y_pred, axis=1)
    y_test_labels = np.argmax(y_test, axis=1)
    
    # Menghitung akurasi
    accuracy = accuracy_score(y_test_labels, y_pred_labels)
    print("Final Model Accuracy: {:.2f}%".format(accuracy * 100))
    
    # Menampilkan classification report
    report = classification_report(y_true=y_test_labels, y_pred=y_pred_labels, target_names=['Negatif', 'Netral', 'Positif'])
    print("Classification Report:")
    print(report)
    
    data['Label_Hasil_Prediksi'] = None
    data.loc[idx_test, 'Label_Hasil_Prediksi'] = y_pred_labels
    data.to_csv('hasil_2_BARU_19MEI.csv', columns=['judul', 'isi', 'Label', 'Label_Hasil_Prediksi', 'Partai_Politik_Heuristic'], index=False, sep=';')
    
  3. User

    di bagian ini:

    Evaluate the final model on X_test and y_test

    y_pred = model.predict(X_test) y_pred_labels = np.argmax(y_pred, axis=1) y_test_labels = np.argmax(y_test, axis=1)

    model.predict itu pakai model fold ke berapa?

  4. Assistant

    Saya minta maaf atas kesalahan tersebut. Kode di atas hanya menggunakan model dari fold terakhir untuk evaluasi pada data tes (X_test dan y_test). Agar lebih akurat, Anda perlu menggunakan semua model dari setiap fold untuk menghitung rata-rata prediksi dan kemudian mengevaluasinya pada data tes.

    Berikut adalah kode yang dimodifikasi:

    # ... (kodenya sama seperti sebelumnya)
    
    # Menyimpan semua model
    models = []
    
    for train_index, val_index in skf.split(X_train_full, y_categorical[idx_train_full]):
        print("\nTraining and evaluating model for fold", iter_num)
    
        # ... (kodenya sama seperti sebelumnya)
    
        # Simpan model untuk lipatan ini
        models.append(model)
        iter_num += 1
    
    # Memprediksi pada data uji menggunakan semua model dan menghitung prediksi rata-rata
    y_preds = [model.predict(X_test) for model in models]  # prediksi menggunakan setiap model
    y_preds_mean = np.mean(y_preds, axis=0)  # menghitung rata-rata prediksi
    
    y_pred_labels = np.argmax(y_preds_mean, axis=1)
    y_test_labels = np.argmax(y_test, axis=1)
    
    # Menghitung akurasi
    accuracy = accuracy_score(y_test_labels, y_pred_labels)
    print("Final Model Accuracy: {:.2f}%".format(accuracy * 100))
    
    # Menampilkan classification report
    report = classification_report(y_true=y_test_labels, y_pred=y_pred_labels, target_names=['Negatif', 'Netral', 'Positif'])
    print("Classification Report:")
    print(report)
    
    data['Label_Hasil_Prediksi'] = None
    data.loc[idx_test, 'Label_Hasil_Prediksi'] = y_pred_labels
    data.to_csv('hasil_2_BARU_19MEI.csv', columns=['judul', 'isi', 'Label', 'Label_Hasil_Prediksi', 'Partai_Politik_Heuristic'], index=False, sep=';')
    

    Dalam kode di atas, kita menyimpan semua model dari setiap fold dalam list models dan kemudian menggunakan semua model tersebut untuk memprediksi pada data tes. Selanjutnya, kita menghitung rata-rata prediksi dan menggunakan hasil tersebut untuk menghitung akurasi dan menampilkan laporan klasifikasi.

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