def create_vocab():
DBHelperMethod.connect_to_db()
dataset = DBHelperMethod.load_data_set()
chars = dp.load_nn_input_dataset_string(dataset[:, [0, 6]])
vocab, vocab_inv = dp.build_vocab(chars)
return vocab, vocab_inv, chars, dataset
def get_testing_data():
DBHelperMethod.connect_to_db()
training_dataset = DBHelperMethod.load_dataset_by_type("testing")
x = dp.load_nn_input_dataset_string(training_dataset[:, [0, 6]])
y = dp.load_nn_labels_dataset_string(training_dataset[:, [0, 1]])
return x, y
def load_testing_data():
Dp.establish_db_connection()
testing_dataset = Dp.load_dataset_by_type("testing")
x = Dp.load_nn_input_dataset_string(testing_dataset[:, [0, 6]])
y = Dp.load_nn_labels_dataset_string(testing_dataset[:, [0, 1]])
sent_num, sen_len = Dp.load_nn_seq_lengths(testing_dataset[:, [3]])
sentences_padded, vocabulary, vocabulary_inv = Dp.pad_sentences(x, sen_len, 4, 10)
return sentences_padded, y, vocabulary, vocabulary_inv
def load_testing_data():
dp.establish_db_connection()
testing_dataset = dp.load_testing_dataset()
x = dp.load_nn_input_dataset_string(testing_dataset[:, [0, 6]])
y = dp.load_nn_labels_dataset_string(testing_dataset[:, [0, 1]])
sent_num, sen_len = dp.load_nn_seq_lengths(testing_dataset[:, [3]])
sentences_padded, vocabulary, vocabulary_inv = dp.pad_sentences(x, sen_len, 4, 10)
testing_words = np.take(testing_dataset, 4, axis=1)
input_testing_letters = np.take(testing_dataset, 0, axis=1)
op_testing_letters = np.take(testing_dataset, 5, axis=1)
sent_num = np.take(testing_dataset, 3, axis=1)
letters_loc = np.take(testing_dataset, 6, axis=1)
undiac_word = np.take(testing_dataset, 7, axis=1)
return sentences_padded, y, vocabulary, vocabulary_inv, testing_words, input_testing_letters, op_testing_letters,\
sent_num, letters_loc, undiac_word
def load_testing_data():
dp.establish_db_connection()
testing_dataset = DBHelperMethod.load_dataset_by_type("testing")
#testing_dataset = DBHelperMethod.load_dataset_by_type_and_sentence_number_for_testing_purpose("testing", 2838)
x = dp.load_nn_input_dataset_string(testing_dataset[:, [0, 6]])
y = dp.load_nn_labels_dataset_string(testing_dataset[:, [0, 1]])
sent_num, sen_len = dp.load_nn_seq_lengths(testing_dataset[:, [3]])
sentences_padded, vocabulary, vocabulary_inv = dp.pad_sentences1(
x, sen_len, req_char_index, window_size)
testing_words = np.take(testing_dataset, 4, axis=1)
input_testing_letters = np.take(testing_dataset, 0, axis=1)
op_testing_letters = np.take(testing_dataset, 5, axis=1)
sent_num = np.take(testing_dataset, 3, axis=1)
letters_loc = np.take(testing_dataset, 6, axis=1)
undiac_word = np.take(testing_dataset, 7, axis=1)
return sentences_padded, y, vocabulary, vocabulary_inv, testing_words, input_testing_letters, op_testing_letters,\
sent_num, letters_loc, undiac_word
