def test_experiment_sequence_combiner(csv_filename):
# Sequence combiner
input_features = [
sequence_feature(
name='english',
min_len=5,
max_len=5,
encoder='rnn',
cell_type='lstm',
reduce_output=None
),
sequence_feature(
name='spanish',
min_len=5,
max_len=5,
encoder='rnn',
cell_type='lstm',
reduce_output=None
),
categorical_feature(vocab_size=5)
]
output_features = [
categorical_feature(reduce_input='sum', vocab_size=5)
]
model_definition = {
'input_features': input_features,
'output_features': output_features,
'training': {
'epochs': 2
},
'combiner': {
'type': 'sequence_concat',
'encoder': 'rnn',
'main_sequence_feature': 'random_sequence'
}
}
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
for encoder in ENCODERS[:-2]:
logger.error('sequence combiner. encoders: {0}, {1}'.format(
encoder,
encoder
))
input_features[0]['encoder'] = encoder
input_features[1]['encoder'] = encoder
model_definition['input_features'] = input_features
exp_dir_name = experiment(
model_definition,
skip_save_processed_input=False,
skip_save_progress=True,
skip_save_unprocessed_output=True,
data_csv=rel_path
)
shutil.rmtree(exp_dir_name, ignore_errors=True)
def test_experiment_multi_input_intent_classification(csv_filename):
# Multiple inputs, Single category output
input_features = [
text_feature(vocab_size=10, min_len=1, representation='sparse'),
categorical_feature(vocab_size=10,
loss='sampled_softmax_cross_entropy')
]
output_features = [categorical_feature(vocab_size=2, reduce_input='sum')]
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
for encoder in ENCODERS:
input_features[0]['encoder'] = encoder
run_experiment(input_features, output_features, data_csv=rel_path)
def test_experiment_model_resume(csv_filename):
# Single sequence input, single category output
# Tests saving a model file, loading it to rerun training and predict
input_features = [sequence_feature(encoder='rnn', reduce_output='sum')]
output_features = [categorical_feature(vocab_size=2, reduce_input='sum')]
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
model_definition = {
'input_features': input_features,
'output_features': output_features,
'combiner': {
'type': 'concat',
'fc_size': 14
},
'training': {
'epochs': 2
}
}
exp_dir_name = experiment(model_definition, data_csv=rel_path)
logging.info('Experiment Directory: {0}'.format(exp_dir_name))
experiment(model_definition,
data_csv=rel_path,
model_resume_path=exp_dir_name)
full_predict(os.path.join(exp_dir_name, 'model'), data_csv=rel_path)
shutil.rmtree(exp_dir_name, ignore_errors=True)
def test_experiment_tied_weights(csv_filename):
# Single sequence input, single category output
input_features = [
text_feature(
name='text_feature1',
min_len=1,
encoder='cnnrnn',
reduce_output='sum'
),
text_feature(
name='text_feature2',
min_len=1,
encoder='cnnrnn',
reduce_output='sum',
tied_weights='text_feature1'
)
]
output_features = [categorical_feature(vocab_size=2, reduce_input='sum')]
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
for encoder in ENCODERS:
input_features[0]['encoder'] = encoder
input_features[1]['encoder'] = encoder
run_experiment(input_features, output_features, data_csv=rel_path)
def test_api_intent_classification(csv_filename):
# Single sequence input, single category output
input_features = [sequence_feature(reduce_output='sum')]
output_features = [categorical_feature(vocab_size=2, reduce_input='sum')]
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
for encoder in ENCODERS:
input_features[0]['encoder'] = encoder
run_api_experiment(input_features, output_features, data_csv=rel_path)
def test_experiment_datetime_feature(csv_filename):
input_features = [date_feature()]
output_features = [categorical_feature(vocab_size=2)]
# Generate test data
rel_path = generate_data(input_features, output_features, csv_filename)
encoders = ['wave', 'embed']
for encoder in encoders:
input_features[0]['encoder'] = encoder
run_experiment(input_features, output_features, data_csv=rel_path)
def test_experiment_multiple_seq_seq(csv_filename):
# Multiple inputs, Multiple outputs
input_features = [
text_feature(vocab_size=100, min_len=1, encoder='stacked_cnn'),
numerical_feature(),
categorical_feature(vocab_size=10, embedding_size=5),
set_feature(),
sequence_feature(vocab_size=10, max_len=10, encoder='embed')
]
output_features = [
categorical_feature(vocab_size=2, reduce_input='sum'),
sequence_feature(vocab_size=10, max_len=5),
numerical_feature()
]
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
# Use generator as decoder
output_features = [
categorical_feature(vocab_size=2, reduce_input='sum'),
sequence_feature(vocab_size=10, max_len=5, decoder='generator'),
numerical_feature()
]
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
# Generator decoder and reduce_input = None
output_features = [
categorical_feature(vocab_size=2, reduce_input='sum'),
sequence_feature(max_len=5, decoder='generator', reduce_input=None),
numerical_feature()
]
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
def test_experiment_image_inputs(csv_filename):
# Image Inputs
image_dest_folder = os.path.join(os.getcwd(), 'generated_images')
# Resnet encoder
input_features = [
image_feature(
folder=image_dest_folder,
encoder='resnet',
preprocessing={
'in_memory': True,
'height': 8,
'width': 8,
'num_channels': 3
},
fc_size=16,
num_filters=8
),
text_feature(encoder='embed', min_len=1),
numerical_feature(normalization='zscore')
]
output_features = [
categorical_feature(vocab_size=2, reduce_input='sum'),
numerical_feature()
]
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
# Stacked CNN encoder
input_features[0]['encoder'] = 'stacked_cnn'
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
# Stacked CNN encoder, in_memory = False
input_features[0]['preprocessing']['in_memory'] = False
rel_path = generate_data(input_features, output_features, csv_filename)
run_experiment(input_features, output_features, data_csv=rel_path)
# Delete the temporary data created
shutil.rmtree(image_dest_folder)
def test_server_integration(csv_filename):
# Image Inputs
image_dest_folder = os.path.join(os.getcwd(), 'generated_images')
# Resnet encoder
input_features = [
image_feature(folder=image_dest_folder,
encoder='resnet',
preprocessing={
'in_memory': True,
'height': 8,
'width': 8,
'num_channels': 3
},
fc_size=16,
num_filters=8),
text_feature(encoder='embed', min_len=1),
numerical_feature(normalization='zscore')
]
output_features = [
categorical_feature(vocab_size=2, reduce_input='sum'),
numerical_feature()
]
rel_path = generate_data(input_features, output_features, csv_filename)
model = train_model(input_features, output_features, data_csv=rel_path)
app = server(model)
client = TestClient(app)
response = client.post('/predict')
assert response.json() == ALL_FEATURES_PRESENT_ERROR
data_df = read_csv(rel_path)
data, files = convert_to_form(data_df.T.to_dict()[0])
response = client.post('/predict', data=data, files=files)
response_keys = sorted(list(response.json().keys()))
assert response_keys == sorted(output_keys_for(output_features))
shutil.rmtree(model.exp_dir_name, ignore_errors=True)
shutil.rmtree(image_dest_folder)
