deep_gru_lstm_utility_functions.py

EOS = chr(10) # End of sentence

def build_vocabulary() -> list:
    # builds a vocabulary using ASCII characters
    vocabulary = [chr(i) for i in range(10, 128)]
    return vocabulary

def word2index(vocabulary: list, word: str) -> int:
    # returns the index of 'word' in the vocabulary
    return vocabulary.index(word)

def words2onehot(vocabulary: list, words: list) -> np.ndarray:
    # transforms the list of words given as argument into
    # a one-hot matrix representation using the index in the vocabulary
    n_words = len(words)
    n_voc = len(vocabulary)
    indices = np.array([word2index(vocabulary, word) for word in words])
    a = np.zeros((n_words, n_voc))
    a[np.arange(n_words), indices] = 1
    return a