def notebook_to_graph(self):
# convert notebook to nx graph
(pipeline_graph, pipeline_parameters_source,
pipeline_metrics_source) = parser.parse_notebook(self.notebook)
# get a dict from the 'pipeline parameters' cell source code
pipeline_parameters_dict = ast.parse_assignments_expressions(
pipeline_parameters_source)
# get a list of variables that need to be logged as pipeline metrics
pipeline_metrics = ast.parse_metrics_print_statements(
pipeline_metrics_source)
# if there are some pipeline metrics, create an additional step at the
# end of the pipeline to log them.
# By adding this step before dependencies detection, we make sure that
# the necessary variables are marshalled at the beginning of the step.
if len(pipeline_metrics):
pipeline_metrics_name = "pipeline_metrics"
# add a link from all the last steps of the pipeline to
# the final auto snapshot one.
leaf_steps = [
x for x in pipeline_graph.nodes()
if pipeline_graph.out_degree(x) == 0
]
for node in leaf_steps:
pipeline_graph.add_edge(node, pipeline_metrics_name)
# generate the code that dumps the pipeline metrics to file
template_env = _initialize_templating_env()
metrics_template = template_env.get_template(
'pipeline_metrics_template.jinja2')
# need to be a list since it will be treated as a code cell and
# passed to the ipykernel
metrics_source = [
metrics_template.render(pipeline_metrics=pipeline_metrics)
]
data = {
pipeline_metrics_name: {
'source': metrics_source,
'ins': [],
'outs': []
}
}
nx.set_node_attributes(pipeline_graph, data)
# run static analysis over the source code
dependencies.dependencies_detection(
pipeline_graph, pipeline_parameters=pipeline_parameters_dict)
# add an empty step at the end of the pipeline for final snapshot
if self.auto_snapshot:
auto_snapshot_name = 'final_auto_snapshot'
# add a link from all the last steps of the pipeline to
# the final auto snapshot one.
leaf_steps = [
x for x in pipeline_graph.nodes()
if pipeline_graph.out_degree(x) == 0
]
for node in leaf_steps:
pipeline_graph.add_edge(node, auto_snapshot_name)
data = {auto_snapshot_name: {'source': '', 'ins': [], 'outs': []}}
nx.set_node_attributes(pipeline_graph, data)
# TODO: Additional Step required:
# Run a static analysis over every step to check that pipeline
# parameters are not assigned with new values.
return pipeline_graph, pipeline_parameters_dict
def template():
"""Reusable function template."""
tmpl_dir = os.path.join(THIS_DIR, '../../templates')
env = generate_code._initialize_templating_env(tmpl_dir)
return env.get_template('function_template.jinja2')