用 Keras 實現單詞級的 one-hot 編碼 & 使用散列技巧的單詞級的 one-hot 編碼

from keras.preprocessing.text import Tokenizer

samples = ['The cat sat on the mat.', 'The dog ate my homework.']
tokenizer = Tokenizer(num_words=1000)
tokenizer.fit_on_texts(samples)
# sequences = tokenizer.texts_to_sequences(samples)
one_hot_results = tokenizer.texts_to_matrix(samples, mode='binary')
# word_index = tokenizer.word_index

# print('Found %s unique tokens.' % len(word_index))
print(one_hot_results)

使用散列技巧：

samples = ['The cat sat on the mat.', 'The dog ate my homework.']

dimensionality = 1000
max_length = 10
results = np.zeros((len(samples), max_length, dimensionality))
for i, sample in enumerate(samples):
　　for j, word in list(enumerate(sample.split()))[:max_length]:
　　　　index = abs(hash(word)) % dimensionality
　　　　results[i, j, index] = 1.