project = 'PROJECT' # the project to launch the VM in
cloudsql_connection_name = f'{project}:REGION:INSTANCE'
mysql_db = 'DATABASE'
mysql_user = '******'
mysql_pw = 'PASSWORD'
training_job_dir = artifact_store_path + '/gcaiptrainer/'
training_pipeline = TrainingPipeline(name='GCP Orchestrated')
# Add a datasource. This will automatically track and version it.
ds = CSVDatasource(name='Pima Indians Diabetes',
path='gs://zenml_quickstart/diabetes.csv')
training_pipeline.add_datasource(ds)
# Add a split
training_pipeline.add_split(RandomSplit(
split_map={'train': 0.7, 'eval': 0.3}))
# Add a preprocessing unit
training_pipeline.add_preprocesser(
StandardPreprocesser(
features=['times_pregnant', 'pgc', 'dbp', 'tst', 'insulin', 'bmi',
'pedigree', 'age'],
labels=['has_diabetes'],
overwrite={'has_diabetes': {
'transform': [{'method': 'no_transform', 'parameters': {}}]}}
))
# Add a trainer
training_pipeline.add_trainer(FeedForwardTrainer(
loss='binary_crossentropy',
last_activation='sigmoid',
from examples.gan.preprocessing import GANPreprocessor
repo: Repository = Repository().get_instance()
gan_pipeline = TrainingPipeline(name="whynotletitfly", enable_cache=False)
try:
ds = ImageDatasource(
name="gan_images",
base_path="/Users/nicholasjunge/workspaces/maiot/ce_project/images_mini"
)
except:
ds = repo.get_datasource_by_name('gan_images')
gan_pipeline.add_datasource(ds)
gan_pipeline.add_split(
CategoricalDomainSplit(categorical_column="label",
split_map={
"train": [0],
"eval": [1]
}))
gan_pipeline.add_preprocesser(GANPreprocessor())
# gan_pipeline.add_preprocesser(transform_step)
gan_pipeline.add_trainer(CycleGANTrainer(epochs=5))
gan_pipeline.run()
for i in range(1, 6):
training_pipeline = TrainingPipeline(name='csvtest{0}'.format(i))
try:
# Add a datasource. This will automatically track and version it.
ds = CSVDatasource(name='my_csv_datasource',
path=os.path.join(csv_root, "my_dataframe.csv"))
except:
ds = repo.get_datasource_by_name("my_csv_datasource")
training_pipeline.add_datasource(ds)
# Add a split
training_pipeline.add_split(
CategoricalDomainSplit(categorical_column="name",
split_map={
'train': ["arnold", "nicholas"],
'eval': ["lülük"]
}))
# Add a preprocessing unit
training_pipeline.add_preprocesser(
StandardPreprocesser(features=["name", "age"],
labels=['gpa'],
overwrite={
'gpa': {
'transform': [{
'method': 'no_transform',
'parameters': {}
}]
}
}))
# Define the training pipeline
training_pipeline = TrainingPipeline()
# Add a datasource. This will automatically track and version it.
try:
ds = CSVDatasource(name='Pima Indians Diabetes',
path='gs://zenml_quickstart/diabetes.csv')
except AlreadyExistsException:
ds = Repository.get_instance().get_datasource_by_name(
'Pima Indians Diabetes')
training_pipeline.add_datasource(ds)
# Add a split
training_pipeline.add_split(
RandomSplit(split_map={'train': 0.7, 'eval': 0.3}).with_backend(
processing_backend)
)
# Add a preprocessing unit
training_pipeline.add_preprocesser(
StandardPreprocesser(
features=['times_pregnant', 'pgc', 'dbp', 'tst', 'insulin', 'bmi',
'pedigree', 'age'],
labels=['has_diabetes'],
overwrite={'has_diabetes': {
'transform': [{'method': 'no_transform', 'parameters': {}}]}}
).with_backend(processing_backend)
)
# Add a trainer
training_pipeline.add_trainer(FeedForwardTrainer(