def test_io_api(tmp_dir):
(image_x, train_y), (test_x, test_y) = mnist.load_data()
(text_x, train_y), (test_x, test_y) = common.imdb_raw()
num_instances = 20
image_x = image_x[:num_instances]
text_x = text_x[:num_instances]
structured_data_x = common.generate_structured_data(
num_instances=num_instances)
classification_y = common.generate_one_hot_labels(
num_instances=num_instances, num_classes=3)
regression_y = common.generate_data(num_instances=num_instances,
shape=(1, ))
# Build model and train.
automodel = ak.AutoModel(
inputs=[ak.ImageInput(),
ak.TextInput(),
ak.StructuredDataInput()],
outputs=[
ak.RegressionHead(metrics=['mae']),
ak.ClassificationHead(loss='categorical_crossentropy',
metrics=['accuracy'])
],
directory=tmp_dir,
max_trials=2,
seed=common.SEED)
automodel.fit([image_x, text_x, structured_data_x],
[regression_y, classification_y],
epochs=2,
validation_split=0.2)
def test_structured_data_input_col_type_without_name():
num_data = 500
train_x = common.generate_structured_data(num_data)
with pytest.raises(ValueError) as info:
input_node = node.StructuredDataInput(
column_types=common.COLUMN_TYPES_FROM_NUMPY)
input_node.fit(train_x)
assert str(info.value) == 'Column names must be specified.'
def test_feature_engineering(tmp_dir):
dataset = common.generate_structured_data(dtype='dataset')
feature = preprocessor_module.FeatureEngineering()
feature.column_names = common.COLUMN_NAMES_FROM_NUMPY
feature.column_types = common.COLUMN_TYPES_FROM_NUMPY
new_dataset = run_preprocessor(feature, dataset,
common.generate_data(dtype='dataset'),
tf.float32, tmp_dir)
assert isinstance(new_dataset, tf.data.Dataset)
def test_structured_data_assembler():
data = common.generate_structured_data()
dataset = tf.data.Dataset.from_tensor_slices(data)
assembler = meta_model.StructuredDataAssembler()
for line in dataset:
assembler.update(line)
input_node = node.StructuredDataInput()
assembler.assemble(input_node)
assert isinstance(input_node.out_blocks[0], ak.StructuredDataBlock)
def test_feature_engineering():
dataset = common.generate_structured_data(dtype='dataset')
feature = preprocessor_module.FeatureEngineering()
feature.input_node = ak.StructuredDataInput(
column_names=common.COLUMN_NAMES_FROM_NUMPY,
column_types=common.COLUMN_TYPES_FROM_NUMPY)
new_dataset = run_preprocessor(feature, dataset,
common.generate_data(dtype='dataset'),
tf.float32)
assert isinstance(new_dataset, tf.data.Dataset)
def test_structured_data_assembler():
data = common.generate_structured_data()
dataset = tf.data.Dataset.from_tensor_slices(data)
assembler = meta_model.StructuredDataAssembler(
column_names=common.COLUMN_NAMES_FROM_NUMPY)
for line in dataset:
assembler.update(line)
input_node = node.StructuredDataInput()
assembler.assemble(input_node)
assert input_node.column_types == common.COLUMN_TYPES_FROM_NUMPY
def test_structured_data_from_numpy_classifier(tmp_dir):
num_data = 500
num_train = 400
data = common.generate_structured_data(num_data)
x_train, x_test = data[:num_train], data[num_train:]
y = common.generate_one_hot_labels(num_instances=num_data, num_classes=3)
y_train, y_test = y[:num_train], y[num_train:]
clf = ak.StructuredDataClassifier(directory=tmp_dir,
max_trials=1,
seed=common.SEED)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
assert clf.predict(x_test).shape == (len(y_test), 3)
def test_structured_data_from_numpy_regressor(tmp_dir):
num_data = 500
num_train = 400
data = common.generate_structured_data(num_data)
x_train, x_test = data[:num_train], data[num_train:]
y = common.generate_data(num_instances=num_data, shape=(1, ))
y_train, y_test = y[:num_train], y[num_train:]
clf = ak.StructuredDataRegressor(directory=tmp_dir,
max_trials=1,
seed=common.SEED)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
assert clf.predict(x_test).shape == (len(y_test), 1)
def test_structured_regressor(init, fit):
num_data = 500
train_x = common.generate_structured_data(num_data)
train_y = common.generate_data(num_instances=100, shape=(1,))
clf = ak.StructuredDataRegressor(
column_names=common.COLUMN_NAMES_FROM_NUMPY,
directory=tmp_dir,
max_trials=1,
seed=common.SEED)
clf.fit(train_x, train_y, epochs=2, validation_data=(train_x, train_y))
assert init.called
assert fit.called
def test_structured_classifier(init, fit):
num_data = 500
train_x = common.generate_structured_data(num_data)
train_y = common.generate_one_hot_labels(num_instances=num_data, num_classes=3)
clf = ak.StructuredDataClassifier(
column_names=common.COLUMN_NAMES_FROM_NUMPY,
directory=tmp_dir,
max_trials=1,
seed=common.SEED)
clf.fit(train_x, train_y, epochs=2, validation_data=(train_x, train_y))
assert init.called
assert fit.called
def test_structured_data_input(tmp_dir):
num_data = 500
data = common.generate_structured_data(num_data)
x_train = data
y = np.random.randint(0, 3, num_data)
y_train = y
input_node = ak.StructuredDataInput(
column_names=common.COLUMN_NAMES_FROM_NUMPY,
column_types=common.COLUMN_TYPES_FROM_NUMPY)
output_node = input_node
output_node = ak.StructuredDataBlock()(output_node)
output_node = ak.ClassificationHead(loss='categorical_crossentropy',
metrics=['accuracy'])(output_node)
auto_model = ak.GraphAutoModel(input_node,
output_node,
directory=tmp_dir,
max_trials=1)
auto_model.fit(x_train,
y_train,
epochs=1,
validation_data=(x_train, y_train))
auto_model.predict(x_train)
