Amanda自然语言处理技术教程.docx

labels = [1, 1, 0] #

tokenizer = Tokenizer(num_words=10000, oov_token='<OOV>')

tokenizer.fit_on_texts(texts)

sequences = tokenizer.texts_to_sequences(texts)

padded_sequences = pad_sequences(sequences, maxlen=100)

model = tf.keras.Sequential([

tf.keras.layers.Embedding(10000, 16, input_length=100),

tf.keras.layers.GlobalAveragePooling1D(),

import pandas as pd

from sklearn.model_selection import train_test_split

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Embedding, LSTM, Dense

data = pd.DataFrame({

X_train, X_test, y_train, y_test = train_test_split(texts, sentiments, test_size=0.2)

model = Sequential([

Embedding(10000, 16),

LSTM(64),

Dense(1, activation='sigmoid')

])

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

model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test))

from tensorflow.keras.models import Model

from tensorflow.keras.layers import Input, LSTM, Dense

target_texts = ['I love you']

input_tokenizer = Tokenizer()

target_tokenizer = Tokenizer()

input_tokenizer.fit_on_texts(input_texts)

target_tokenizer.fit_on_texts(target_texts)

decoder_inputs = Input(shape=(None,))

decoder_embedding = Embedding(len(target_tokenizer.word_index) + 1, 256)

decoder_lstm = LSTM(256, return_sequences=True, return_state=True)

decoder_outputs, _, _ = decoder_lstm(decoder_embedding(decoder_inputs), initial_state=encod

er_states)

decoder_dense = Dense(len(target_tokenizer.word_index) + 1, activation='softmax')

decoder_outputs = decoder_dense(decoder_outputs)

model = Model([encoder_inputs, decoder_inputs], decoder_outputs)