def test_structured_data_from_numpy_classifier(tmp_dir):
num_data = 500
data = common.structured_data(num_data)
x_train = data
y = np.random.randint(0, 3, num_data)
y_train = y
clf = ak.StructuredDataClassifier(directory=tmp_dir, max_trials=1)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
def test_structured_data_from_numpy_regressor(tmp_dir):
num_data = 500
data = common.structured_data(num_data)
x_train = data
y = np.random.rand(num_data, 1)
y_train = y
clf = ak.StructuredDataRegressor(directory=tmp_dir, max_trials=1)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
def test_structured_data_classifier_transform_new_data(tmp_dir):
num_data = 200
num_train = 100
data = common.structured_data(num_data)
x_train, x_test = data[:num_train], data[num_train:]
y = np.random.randint(0, 3, num_data)
y_train, y_test = y[:num_train], y[num_train:]
clf = ak.StructuredDataClassifier(directory=tmp_dir, max_trials=1)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_test, y_test))
def test_structured_data_assembler():
data = common.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)
assembler.assemble(node.StructuredDataInput())
def test_structured_data_from_numpy_classifier(tmp_dir):
num_data = 500
num_train = 400
data = common.structured_data(num_data)
x_train, x_test = data[:num_train], data[num_train:]
y = np.random.randint(0, 3, num_data)
y_train, y_test = y[:num_train], y[num_train:]
clf = ak.StructuredDataClassifier(directory=tmp_dir, max_trials=1)
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_data_from_numpy_col_name_classifier(tmp_dir):
num_data = 500
data = common.structured_data(num_data)
x_train = data
y = np.random.randint(0, 3, num_data)
y_train = y
clf = ak.StructuredDataClassifier(
column_names=common.COLUMN_NAMES_FROM_NUMPY,
directory=tmp_dir,
max_trials=1)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
def test_structured_data_from_numpy_col_type_classifier(tmp_dir):
num_data = 500
data = common.structured_data(num_data)
x_train = data
y = np.random.randint(0, 3, num_data)
y_train = y
with pytest.raises(ValueError) as info:
clf = ak.StructuredDataClassifier(
column_types=common.COLUMN_TYPES_FROM_NUMPY,
directory=tmp_dir,
max_trials=1)
clf.fit(x_train, y_train, epochs=2, validation_data=(x_train, y_train))
assert str(info.value) == 'Column names must be specified.'
def test_structured_data_input(tmp_dir):
num_data = 500
data = common.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)
