File size: 1,712 Bytes
672738d 671f972 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | MAX_LEN = 70
bertInput = bert_tokenizer.encode_plus(
data.Text[id_data],
add_special_tokens = True,
padding = 'max_length',
truncation = 'longest_first',
max_length = 50,
return_attention_mask = True,
return_token_type_ids = True
)
bertInput.keys()
def convert_example_to_feature(sentence):
return bert_tokenizer.encode_plus(
sentence,
add_special_tokens = True,
padding = 'max_length',
truncation = 'longest_first',
max_length = MAX_LEN,
return_attention_mask = True,
return_token_type_ids=True
)
def map_example_to_dict(input_ids, attention_masks, token_type_ids, label):
return {
"input_ids": input_ids, # Sebagai token embedding
"token_type_ids": token_type_ids, # Sebagai segment embedding
"attention_mask": attention_masks, # Sebagai filter informasi mana yang kalkulasi oleh model
}, label
def encode(data):
input_ids_list = []
token_type_ids_list = []
attention_mask_list = []
label_list = []
for label,sentence in data.to_numpy():
bert_input = convert_example_to_feature(sentence)
input_ids_list.append(bert_input['input_ids'])
token_type_ids_list.append(bert_input['token_type_ids'])
attention_mask_list.append(bert_input['attention_mask'])
label_list.append([label])
return tf.data.Dataset.from_tensor_slices((input_ids_list, attention_mask_list, token_type_ids_list, label_list)).map(map_example_to_dict)
EPOCHS = 2
BATCH_SIZE = 64
LEARNING_RATE = 5e-5
train_encode = encode(df_train).batch(BATCH_SIZE)
test_encode = encode(df_test).batch(BATCH_SIZE)
val_encode = encode(df_val).batch(BATCH_SIZE) |