def test_invalid_tuner_name_error(tmp_path):
with pytest.raises(ValueError) as info:
ak.AutoModel(
ak.ImageInput(), ak.RegressionHead(), directory=tmp_path, tuner="unknown"
)
assert "Expected the tuner argument to be one of" in str(info.value)
def main():
deaths, recoveries, cases, deaths_validation, recoveries_validation, cases_validation = get_dfs()
X, y = get_ds(deaths, recoveries, cases)
X_train, X_test, y_train, y_test = train_test_split(X, y)
data = convert_dfs(deaths_validation, recoveries_validation, cases_validation)
column_names = []
model_input = ak.Input()
model_output = ak.blocks.basic.DenseBlock()(model_input)
model_output = ak.blocks.basic.DenseBlock()(model_output)
model_output = ak.blocks.basic.DenseBlock()(model_output)
model_output = ak.RegressionHead()(model_output)
trainer = ak.AutoModel(inputs=model_input, outputs=model_output)
trainer.fit(X_train, y_train)
model = trainer.export_model()
y_fit = model.predict(X_test)
tf.keras.models.save_model(model, 'model.tf')
with open('data.json', 'wt') as f:
json.dump(data, f)
print(model.evaluate(X_test, y_test))
plt.scatter(y_test, y_fit)
plt.savefig('results.png')
def test_auto_model_max_trial_field_as_specified(tmp_path):
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path,
max_trials=10)
assert auto_model.max_trials == 10
def test_io_api(tmp_path):
num_instances = 100
(image_x, train_y), (test_x, test_y) = mnist.load_data()
(text_x, train_y), (test_x,
test_y) = utils.imdb_raw(num_instances=num_instances)
image_x = image_x[:num_instances]
text_x = text_x[:num_instances]
structured_data_x = utils.generate_structured_data(
num_instances=num_instances)
classification_y = utils.generate_one_hot_labels(
num_instances=num_instances, num_classes=3)
regression_y = utils.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_path,
max_trials=2,
seed=utils.SEED)
automodel.fit([image_x, text_x, structured_data_x],
[regression_y, classification_y],
epochs=1,
validation_split=0.2)
def applyAutoKeras(X_train, y_train, X_test, y_test, SavePath,
max_trials=100, epochs=300, useSavedModels = True):
if not useSavedModels or not os.path.isdir(SavePath+"/keras_auto_model/best_model/"):
input_node = ak.StructuredDataInput()
output_node = ak.DenseBlock()(input_node)
#output_node = ak.ConvBlock()(output_node)
output_node = ak.RegressionHead()(output_node)
AKRegressor = ak.AutoModel(
inputs=input_node,
outputs=output_node,
max_trials=max_trials,
overwrite=True,
tuner="bayesian",
project_name=SavePath+"/keras_auto_model"
)
print(" X_train shape: {0}\n y_train shape: {1}\n X_test shape: {2}\n y_test shape: {3}".format(X_train.shape, y_train.shape, X_test.shape, y_test.shape))
AKRegressor.fit(x=X_train, y=y_train[:,0],epochs=epochs,verbose=1, batch_size=int(X_train.shape[0]/10), shuffle=False, use_multiprocessing=True)
AKRegressor.export_model()
else:
AKRegressor = tf.keras.models.load_model(SavePath+"/keras_auto_model/best_model/")
y_hat = AKRegressor.predict(X_test)
print("AUTOKERAS - Score: ")
print("MAE: %.4f" % mean_absolute_error(y_test[:,0], y_hat))
return y_hat
def train():
(x_train, y_train), (x_test, y_test) = mnist.load_data()
# Initialize the image regressor.
input_node = ak.ImageInput()
output_node = ak.ImageBlock(
# Only search ResNet architectures.
block_type="resnet",
# Normalize the dataset.
normalize=False,
# Do not do data augmentation.
augment=False,
)(input_node)
output_node = ak.RegressionHead()(output_node)
reg = ak.AutoModel(inputs=input_node,
outputs=output_node,
overwrite=True,
max_trials=1)
# Feed the image regressor with training data.
reg.fit(
x_train,
y_train,
# Split the training data and use the last 15% as validation data.
validation_split=0.15,
epochs=2,
)
# Predict with the best model.
predicted_y = reg.predict(x_test)
print(predicted_y)
# Evaluate the best model with testing data.
print(reg.evaluate(x_test, y_test))
def test_image_blocks(tmp_path):
num_instances = 10
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train[:num_instances]
y_regression = utils.generate_data(num_instances=num_instances,
shape=(1, ))
input_node = ak.ImageInput()
output = ak.Normalization()(input_node)
output = ak.ImageAugmentation()(output)
outputs1 = ak.ResNetBlock(version="v2")(output)
outputs2 = ak.XceptionBlock()(output)
output_node = ak.Merge()((outputs1, outputs2))
output_node = ak.ClassificationHead()(output_node)
automodel = ak.AutoModel(
inputs=input_node,
outputs=output_node,
directory=tmp_path,
max_trials=1,
seed=utils.SEED,
)
automodel.fit(x_train,
y_regression,
validation_data=(x_train, y_regression),
epochs=1)
def build_model(self):
base_model_path = path_join(self.model_path, 'base_model.py')
exec(open(base_model_path).read())
model = ak.AutoModel(inputs=input_node,
outputs=output_node,
max_trials=1)
return model
def test_io_api(tmp_path):
num_instances = 20
image_x = utils.generate_data(num_instances=num_instances, shape=(28, 28))
text_x = utils.generate_text_data(num_instances=num_instances)
image_x = image_x[:num_instances]
structured_data_x = (pd.read_csv(utils.TRAIN_CSV_PATH).to_numpy().astype(
np.unicode)[:num_instances])
classification_y = utils.generate_one_hot_labels(
num_instances=num_instances, num_classes=3)
regression_y = utils.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_path,
max_trials=2,
tuner=ak.RandomSearch,
seed=utils.SEED,
)
automodel.fit(
[image_x, text_x, structured_data_x],
[regression_y, classification_y],
epochs=1,
validation_split=0.2,
batch_size=4,
)
def test_evaluate(tuner_fn, tmp_dir):
pg = mock.Mock()
pg.preprocess.return_value = (mock.Mock(), mock.Mock())
tuner_class = tuner_fn.return_value
tuner = tuner_class.return_value
tuner.get_best_model.return_value = (pg, mock.Mock())
x_train = np.random.rand(100, 32)
y_train = np.random.rand(100, 1)
input_node = ak.Input()
output_node = input_node
output_node = ak.DenseBlock()(output_node)
output_node = ak.RegressionHead()(output_node)
auto_model = ak.AutoModel(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.evaluate(x_train, y_train)
assert tuner_fn.called
assert tuner_class.called
assert tuner.get_best_model.called
def get_multi_io_auto_model(tmp_path):
return ak.AutoModel(
[ak.ImageInput(), ak.ImageInput()],
[ak.RegressionHead(), ak.RegressionHead()],
directory=tmp_path,
max_trials=2,
overwrite=False)
def test_image_blocks(tmp_path):
num_instances = 10
x_train = test_utils.generate_data(num_instances=num_instances,
shape=(28, 28))
y_train = np.random.randint(0, 10, num_instances)
input_node = ak.ImageInput()
output = ak.Normalization()(input_node)
output = ak.ImageAugmentation()(output)
outputs1 = ak.ResNetBlock(version="v2")(output)
outputs2 = ak.XceptionBlock()(output)
output_node = ak.Merge()((outputs1, outputs2))
output_node = ak.ClassificationHead()(output_node)
automodel = ak.AutoModel(
inputs=input_node,
outputs=output_node,
directory=tmp_path,
max_trials=1,
seed=test_utils.SEED,
)
automodel.fit(x_train,
y_train,
validation_data=(x_train, y_train),
epochs=1)
def io_api():
(x_train, y_train), (x_test, y_test) = mnist.load_data()
clf = ak.AutoModel(ak.ImageInput(),
ak.ClassificationHead(),
seed=5,
max_trials=3)
clf.fit(x_train, y_train, validation_split=0.2)
return clf.evaluate(x_test, y_test)
def test_predict_tuple_x_and_tuple_y_predict_doesnt_crash(tuner_fn, tmp_path):
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path)
dataset = tf.data.Dataset.from_tensor_slices(
((np.random.rand(100, 32, 32, 3), ), (np.random.rand(100, 1), )))
auto_model.fit(dataset)
auto_model.predict(dataset)
def test_auto_model_project_name_field_as_specified(tmp_path):
auto_model = ak.AutoModel(
ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path,
project_name="auto_model",
)
assert auto_model.project_name == "auto_model"
def test_auto_model_basic(_, tmp_dir):
x_train = np.random.rand(100, 32, 32, 3)
y_train = np.random.rand(100, 1)
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_dir,
max_trials=2)
auto_model.fit(x_train, y_train, epochs=2, validation_split=0.2)
def train_ak():
image_count = len(list(config.database_path.glob('**/*.jpg')))
print("# of images found:", image_count)
list_ds = tf.data.Dataset.list_files(str(config.database_path / '*/*.jpg'),
shuffle=False)
list_ds = list_ds.shuffle(image_count, reshuffle_each_iteration=False)
# Set `num_parallel_calls` so multiple images are loaded/processed in parallel.
AUTOTUNE = tf.data.experimental.AUTOTUNE
train_ds = list_ds.map(utils.process_path, num_parallel_calls=AUTOTUNE)
features = np.array([list(x[0].numpy()) for x in list(train_ds)])
labels = np.array([x[1].numpy() for x in list(train_ds)])
input_node = ak.ImageInput()
output_node = ak.Normalization()(input_node)
output_node = ak.ImageAugmentation(horizontal_flip=False,
vertical_flip=False,
rotation_factor=False,
zoom_factor=False)(output_node)
output_node = ak.ClassificationHead()(output_node)
clf = ak.AutoModel(inputs=input_node,
outputs=output_node,
overwrite=True,
max_trials=config.max_trials,
directory=config.outpath_mpii)
# Feed the tensorflow Dataset to the classifier.
split = config.split
x_val = features[split:]
y_val = labels[split:]
x_train = features[:split]
y_train = labels[:split]
clf.fit(x_train,
y_train,
validation_data=(x_val, y_val),
epochs=config.epochs)
# Predict with the best model.
#predicted_y = clf.predict(x_val)
#print(predicted_y)
# Evaluate the best model with testing data.
print(clf.evaluate(x_val, y_val))
# Export as a Keras Model.
model = clf.export_model()
print(
type(model)) # <class 'tensorflow.python.keras.engine.training.Model'>
model.save(config.output_path + "model_ak_imgClsf.h5")
return 0
def dataset_error(x, y, validation_data, message, tmp_path):
auto_model = ak.AutoModel(
[ak.ImageInput(), ak.ImageInput()],
[ak.RegressionHead(), ak.RegressionHead()],
directory=tmp_path,
max_trials=2,
overwrite=False)
with pytest.raises(ValueError) as info:
auto_model.fit(x, y, epochs=2, validation_data=validation_data)
assert message in str(info.value)
def test_auto_model_predict(tuner_fn, tmp_path):
x_train = np.random.rand(100, 32, 32, 3)
y_train = np.random.rand(100, 1)
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path,
max_trials=2)
auto_model.fit(x_train, y_train, epochs=2, validation_split=0.2)
auto_model.predict(x_train)
assert tuner_fn.called
def create_image_regressor(self):
input_node = ak.ImageInput()
output_node = ak.ConvBlock()(input_node)
output_node = ak.DenseBlock()(output_node)
output_node = ak.RegressionHead()(output_node)
reg = ak.AutoModel(inputs=input_node,
outputs=output_node,
max_trials=10)
return reg
def train():
house_dataset = fetch_california_housing()
df = pd.DataFrame(np.concatenate(
(house_dataset.data, house_dataset.target.reshape(-1, 1)), axis=1),
columns=house_dataset.feature_names + ['Price'])
train_size = int(df.shape[0] * 0.9)
df[:train_size].to_csv('train.csv', index=False)
df[train_size:].to_csv('eval.csv', index=False)
train_file_path = 'train.csv'
test_file_path = 'eval.csv'
# x_train as pandas.DataFrame, y_train as pandas.Series
x_train = pd.read_csv(train_file_path)
print(type(x_train)) # pandas.DataFrame
y_train = x_train.pop('Price')
print(type(y_train)) # pandas.Series
# You can also use pandas.DataFrame for y_train.
y_train = pd.DataFrame(y_train)
print(type(y_train)) # pandas.DataFrame
# You can also use numpy.ndarray for x_train and y_train.
x_train = x_train.to_numpy().astype(np.unicode)
y_train = y_train.to_numpy()
print(type(x_train)) # numpy.ndarray
print(type(y_train)) # numpy.ndarray
# Preparing testing data.
x_test = pd.read_csv(test_file_path)
y_test = x_test.pop('Price')
# Initialize the structured data regressor.
input_node = ak.StructuredDataInput()
output_node = ak.StructuredDataBlock(
categorical_encoding=True)(input_node)
output_node = ak.RegressionHead()(output_node)
reg = ak.AutoModel(inputs=input_node,
outputs=output_node,
overwrite=True,
max_trials=3)
# Feed the structured data regressor with training data.
reg.fit(
x_train,
y_train,
# Split the training data and use the last 15% as validation data.
validation_split=0.15,
epochs=10)
# Predict with the best model.
predicted_y = reg.predict(test_file_path)
# Evaluate the best model with testing data.
print(reg.evaluate(test_file_path, 'Price'))
def functional_api():
(x_train, y_train), (x_test, y_test) = mnist.load_data()
input_node = ak.ImageInput()
output_node = input_node
output_node = ak.Normalization()(output_node)
output_node = ak.ConvBlock()(output_node)
output_node = ak.SpatialReduction()(output_node)
output_node = ak.DenseBlock()(output_node)
output_node = ak.ClassificationHead()(output_node)
clf = ak.AutoModel(input_node, output_node, seed=5, max_trials=3)
clf.fit(x_train, y_train, validation_split=0.2)
return clf.evaluate(x_test, y_test)
def test_functional_api(tmp_path):
# Prepare the data.
num_instances = 80
(image_x, train_y), (test_x, test_y) = mnist.load_data()
(text_x, train_y), (test_x, test_y) = utils.imdb_raw()
(structured_data_x, train_y), (test_x, test_y) = utils.dataframe_numpy()
image_x = image_x[:num_instances]
text_x = text_x[:num_instances]
structured_data_x = structured_data_x[:num_instances]
classification_y = utils.generate_one_hot_labels(
num_instances=num_instances, num_classes=3)
regression_y = utils.generate_data(num_instances=num_instances,
shape=(1, ))
# Build model and train.
image_input = ak.ImageInput()
output = ak.Normalization()(image_input)
output = ak.ImageAugmentation()(output)
outputs1 = ak.ResNetBlock(version='next')(output)
outputs2 = ak.XceptionBlock()(output)
image_output = ak.Merge()((outputs1, outputs2))
structured_data_input = ak.StructuredDataInput()
structured_data_output = ak.CategoricalToNumerical()(structured_data_input)
structured_data_output = ak.DenseBlock()(structured_data_output)
text_input = ak.TextInput()
outputs1 = ak.TextToIntSequence()(text_input)
outputs1 = ak.Embedding()(outputs1)
outputs1 = ak.ConvBlock(separable=True)(outputs1)
outputs1 = ak.SpatialReduction()(outputs1)
outputs2 = ak.TextToNgramVector()(text_input)
outputs2 = ak.DenseBlock()(outputs2)
text_output = ak.Merge()((outputs1, outputs2))
merged_outputs = ak.Merge()(
(structured_data_output, image_output, text_output))
regression_outputs = ak.RegressionHead()(merged_outputs)
classification_outputs = ak.ClassificationHead()(merged_outputs)
automodel = ak.AutoModel(
inputs=[image_input, text_input, structured_data_input],
directory=tmp_path,
outputs=[regression_outputs, classification_outputs],
max_trials=2,
tuner=ak.Hyperband,
seed=utils.SEED)
automodel.fit((image_x, text_x, structured_data_x),
(regression_y, classification_y),
validation_split=0.2,
epochs=1)
def test_auto_model_basic(tmp_dir):
x_train = np.random.rand(100, 32, 32, 3)
y_train = np.random.rand(100)
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_dir,
max_trials=2)
auto_model.fit(x_train, y_train, epochs=2, validation_split=0.2)
result = auto_model.predict(x_train)
assert result.shape == (100, 1)
def test_no_validation_data_nor_split_error(tmp_path):
auto_model = ak.AutoModel(
ak.ImageInput(), ak.RegressionHead(), directory=tmp_path
)
with pytest.raises(ValueError) as info:
auto_model.fit(
x=np.random.rand(100, 32, 32, 3),
y=np.random.rand(100, 1),
validation_split=0,
)
assert "Either validation_data or a non-zero" in str(info.value)
def test_single_nested_dataset_doesnt_crash(tuner_fn, tmp_path):
auto_model = ak.AutoModel(
ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path,
max_trials=2,
overwrite=False,
)
x1 = utils.generate_data()
y1 = utils.generate_data(shape=(1,))
dataset = tf.data.Dataset.from_tensor_slices(((x1,), y1))
auto_model.fit(dataset, epochs=2)
def test_final_fit_concat(tuner_fn, tmp_dir):
tuner_class = tuner_fn.return_value
x_train = np.random.rand(100, 32, 32, 3)
y_train = np.random.rand(100, 1)
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_dir,
max_trials=2)
auto_model.fit(x_train, y_train, epochs=2, validation_split=0.2)
assert auto_model._split_dataset
assert tuner_class.call_args_list[0][1]['fit_on_val_data']
def test_single_nested_dataset(tuner_fn, tmp_path):
auto_model = ak.AutoModel(ak.ImageInput(),
ak.RegressionHead(),
directory=tmp_path,
max_trials=2,
overwrite=False)
x1 = utils.generate_data()
y1 = utils.generate_data(shape=(1, ))
dataset = tf.data.Dataset.from_tensor_slices(((x1, ), y1))
auto_model.fit(dataset, epochs=2)
for adapter in auto_model._input_adapters + auto_model._output_adapters:
assert adapter.shape is not None
def CreateSupergraph(output_dir, hp_tuner):
input_node = ak.Input()
conv2d_1 = ak.ConvBlock(num_blocks=1, num_layers=3,
max_pooling=True, dropout=0)(input_node)
dense_1 = ak.DenseBlock(dropout=0)(conv2d_1)
output_node = ak.ClassificationHead(num_classes=4,
metrics=['accuracy'])(dense_1)
automodel = ak.AutoModel(inputs=input_node, outputs=output_node,
max_trials=3, directory=output_dir, project_name="autoML",
tuner=hp_tuner, seed=123)
return automodel
def train():
TRAIN_DATA_URL = "https://storage.googleapis.com/tf-datasets/titanic/train.csv"
TEST_DATA_URL = "https://storage.googleapis.com/tf-datasets/titanic/eval.csv"
train_file_path = tf.keras.utils.get_file("train.csv", TRAIN_DATA_URL)
test_file_path = tf.keras.utils.get_file("eval.csv", TEST_DATA_URL)
# x_train as pandas.DataFrame, y_train as pandas.Series
x_train = pd.read_csv(train_file_path)
print(type(x_train)) # pandas.DataFrame
y_train = x_train.pop('survived')
print(type(y_train)) # pandas.Series
# You can also use pandas.DataFrame for y_train.
y_train = pd.DataFrame(y_train)
print(type(y_train)) # pandas.DataFrame
# You can also use numpy.ndarray for x_train and y_train.
x_train = x_train.to_numpy().astype(np.unicode)
y_train = y_train.to_numpy()
print(type(x_train)) # numpy.ndarray
print(type(y_train)) # numpy.ndarray
# Preparing testing data.
x_test = pd.read_csv(test_file_path)
y_test = x_test.pop('survived')
# Initialize the structured data classifier.
input_node = ak.StructuredDataInput()
output_node = ak.StructuredDataBlock(
categorical_encoding=True)(input_node)
output_node = ak.ClassificationHead()(output_node)
clf = ak.AutoModel(inputs=input_node,
outputs=output_node,
overwrite=True,
max_trials=3)
# Feed the structured data classifier with training data.
clf.fit(
x_train,
y_train,
# Split the training data and use the last 15% as validation data.
validation_split=0.15,
epochs=10)
# Predict with the best model.
predicted_y = clf.predict(test_file_path)
# Evaluate the best model with testing data.
print(clf.evaluate(test_file_path, 'survived'))
