Some ML Workflow Frameworks

from metaflow import FlowSpec, step

class BranchFlow(FlowSpec):

    @step
    def start(self):
        self.next(self.a, self.b)

    @step
    def a(self):
        self.x = 1
        self.next(self.join)

    @step
    def b(self):
        self.x = 2
        self.next(self.join)

    @step
    def join(self, inputs):
        print('a is %s' % inputs.a.x)
        print('b is %s' % inputs.b.x)
        print('total is %d' % sum(input.x for input in inputs))
        self.next(self.end)

    @step
    def end(self):
        pass

if __name__ == '__main__':
    BranchFlow()

from sklearn import svm
from sklearn import datasets

clf = svm.SVC(gamma='scale')
iris = datasets.load_iris()
X, y = iris.data, iris.target
clf.fit(X, y)

# Create a iris classifier service with the newly trained model
iris_classifier_service = IrisClassifier()
iris_classifier_service.pack("model", clf)

# Test invoking BentoService instance
iris_classifier_service.predict([[5.1, 3.5, 1.4, 0.2]])

# Save the entire prediction service to file bundle
saved_path = iris_classifier_service.save()

from zenml.core.datasources.csv_datasource import CSVDatasource
from zenml.core.pipelines.training_pipeline import TrainingPipeline
from zenml.core.steps.evaluator.tfma_evaluator import TFMAEvaluator
from zenml.core.steps.preprocesser.standard_preprocesser.standard_preprocesser import StandardPreprocesser
from zenml.core.steps.split.random_split import RandomSplit
from zenml.core.steps.trainer.feedforward_trainer import FeedForwardTrainer

training_pipeline = TrainingPipeline(name='Quickstart')

# Add a datasource. This will automatically track and version it.
ds = CSVDatasource(name='Pima Indians Diabetes Dataset',
                   path='gs://zenml_quickstart/diabetes.csv')
training_pipeline.add_datasource(ds)

# Add a random 70/30 train-eval split
training_pipeline.add_split(RandomSplit(split_map={'train': 0.7, 'eval': 0.3}))

# StandardPreprocesser() has sane defaults for normal preprocessing methods
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']],
                  metrics={'has_diabetes': ['binary_crossentropy',
                                            'binary_accuracy']}))

# Run the pipeline locally
training_pipeline.run()