Model klasifikasi multi-kelas

Recurrent Neural Networks (RNN) untuk Pemodelan Bahasa dengan Keras

David Cecchini

Data Scientist

Tinjauan model klasifikasi Sentimen

# Build and compile the model
model = Sequential()

model.add(Embedding(10000, 128))

model.add(LSTM(128, dropout=0.2))

model.add(Dense(1, activation='sigmoid'))

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

Arsitektur model

Arsitektur yang sama dapat digunakan

# Build the model
model = Sequential()
model.add(Embedding(10000, 128))
model.add(LSTM(128, dropout=0.2))

# Output layer has `num_classes` units and uses `softmax`
model.add(Dense(num_classes, activation="softmax"))

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

Kumpulan data 20 News Group

Kumpulan Data 20 News Groups

Tersedia di sklearn.datasets import fetch_20newsgroups

# Import fungsi untuk memuat data
from sklearn.datasets import fetch_20newsgroups

# Unduh himpunan train dan test
news_train = fetch_20newsgroups(subset='train')

news_test = fetch_20newsgroups(subset='test')

Kumpulan data 20 News Group

Data memiliki atribut berikut:

news_train.DESCR: Dokumentasi.
news_train.data: Data teks.
news_train.filenames: Lokasi berkas di disk.
news_train.target: Indeks numerik kelas.
news_train.target_names: Nama unik tiap kelas.

Pra-pemrosesan data teks

# Import modules
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.utils import to_categorical

# Buat dan latih tokenizer
tokenizer = Tokenizer()
tokenizer.fit_on_texts(news_train.data)

# Buat variabel (X, Y)
X_train = tokenizer.texts_to_sequences(news_train.data)
X_train = pad_sequences(X_train, maxlen=400)
Y_train = to_categorical(news_train.target)

Pelatihan pada data

Latih model pada data latih

# Train the model
model.fit(X_train, Y_train, 
          batch_size=64, epochs=100)

# Evaluate on test data
model.evaluate(X_test, Y_test)

Ayo berlatih!

Recurrent Neural Networks (RNN) untuk Pemodelan Bahasa dengan Keras