def test_naive_model(model: MultinomialNB, vocabulary: CountVectorizer):
# Get data, ignore train and test
_, _, (x_test, y_test) = sentiment_140.load_data()
starttime = time.time()
x_test = vocabulary.transform(x_test)
acc = model.score(x_test, y_test)
endtime = time.time()
return acc, endtime - starttime
def test_keras_model(model: Sequential, tokenizer, arguments):
"""Test model on sentiment140 dataset. Both accuracy and throughput."""
if arguments["maxlen"]:
maxlen = arguments["maxlen"]
else:
maxlen = 0
# Get data, ignore train and test
_, _, (x_test, y_test) = sentiment_140.load_data()
starttime = time.time()
x_test = tokenizer.texts_to_sequences(x_test)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
score, acc = model.evaluate(x_test, y_test)
endtime = time.time()
return score, acc, endtime - starttime
# Convolution
kernel_size = 5
filters = 64
pool_size = 4
# RNN
rnn_output_size = 70
# Training
batch_size = 512
epochs = 5
print('Loading data...')
(x_train, y_train), (x_val, y_val), (x_test,
y_test) = sentiment_140.load_data()
print('Fitting tokenizer...')
tokenizer = Tokenizer()
tokenizer.fit_on_texts(np.concatenate((x_train, x_val, x_test)))
print('Convert text to sequences')
x_train = tokenizer.texts_to_sequences(x_train)
x_val = tokenizer.texts_to_sequences(x_val)
x_test = tokenizer.texts_to_sequences(x_test)
print(len(x_train), 'train sequences')
print(len(x_val), 'validation sequences')
print(len(x_test), 'test sequences')
print('Pad sequences (samples x time)')
# Convolution
kernel_size = 5
filters = 96
pool_size = 4
# RNN
rnn_output_size = 70
# Training
batch_size = 512
epochs = 5
print('Loading data...')
(x_train, y_train), (x_val, y_val), (x_test, y_test) = sentiment_140.load_data()
print('Fitting tokenizer...')
tokenizer = Tokenizer()
tokenizer.fit_on_texts(np.concatenate((x_train, x_val, x_test)))
print('Convert text to sequences')
x_train = tokenizer.texts_to_sequences(x_train)
x_val = tokenizer.texts_to_sequences(x_val)
x_test = tokenizer.texts_to_sequences(x_test)
print('Pad sequences (samples x time)')
x_train = sequence.pad_sequences(x_train, maxlen=maxlen)
x_val = sequence.pad_sequences(x_val, maxlen=maxlen)
x_test = sequence.pad_sequences(x_test, maxlen=maxlen)
