# 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',
output_units=1,
metrics=['accuracy'],
epochs=20))
# Add an evaluator
training_pipeline.add_evaluator(
TFMAEvaluator(slices=[['has_diabetes']],
# 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': {}
}]
}
}))
# Add a trainer
training_pipeline.add_trainer(
FeedForwardTrainer(batch_size=1,
loss='binary_crossentropy',
last_activation='sigmoid',
output_units=1,
metrics=['accuracy'],
epochs=i))
# Run the pipeline locally
