def notebook_to_graph(self):
"""Convert an annotated Notebook to a Graph."""
# convert notebook to nx graph
(pipeline_graph, pipeline_parameters_source, pipeline_metrics_source,
imports_and_functions) = parser.parse_notebook(
self.notebook, self.pipeline_metadata)
# 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)
# run static analysis over the source code
dependencies.dependencies_detection(
pipeline_graph,
pipeline_parameters=pipeline_parameters_dict,
imports_and_functions=imports_and_functions)
dependencies.assign_metrics(pipeline_graph, pipeline_metrics)
# if there are multiple DAG leaves, add an empty step at the end of the
# pipeline for final snapshot
leaf_steps = graphutils.get_leaf_nodes(pipeline_graph)
if self.pipeline_metadata.get("autosnapshot") and len(leaf_steps) > 1:
auto_snapshot_name = 'final_auto_snapshot'
# add a link from all the last steps of the pipeline to
# the final auto snapshot one.
for node in leaf_steps:
pipeline_graph.add_edge(node, auto_snapshot_name)
step_defaults = parser.parse_steps_defaults(
self.pipeline_metadata.get("steps_defaults", []))
data = {
auto_snapshot_name: {
"source": "",
"ins": [],
"outs": [],
"annotations": step_defaults.get("annotations"),
"labels": step_defaults.get("labels"),
"limits": step_defaults.get("limits")
}
}
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 get_pipeline_metrics(request, source_notebook_path):
"""Get the pipeline metrics tagged in the notebook."""
# read notebook
log = request.log if hasattr(request, "log") else logger
try:
notebook = nbformat.read(source_notebook_path,
as_version=nbformat.NO_CONVERT)
metrics_source = parser.get_pipeline_metrics_source(notebook)
if metrics_source == '':
raise ValueError("No pipeline metrics found. Please tag a cell"
" of the notebook with the `pipeline-metrics`"
" tag.")
# get a dict from the 'pipeline parameters' cell source code
metrics = ast.parse_metrics_print_statements(metrics_source)
except ValueError as e:
log.exception("Failed to parse pipeline metrics")
raise RPCInternalError(details=str(e), trans_id=request.trans_id)
log.info("Pipeline metrics: {}".format(metrics))
return metrics
def get_pipeline_metrics(request, source_notebook_path):
"""Get the pipeline metrics tagged in the notebook."""
# read notebook
log = request.log if hasattr(request, "log") else logger
try:
processor = NotebookProcessor(os.path.expanduser(source_notebook_path),
skip_validation=True)
metrics_source = processor.get_pipeline_metrics_source()
if metrics_source == '':
raise ValueError("No pipeline metrics found. Please tag a cell"
" of the notebook with the `pipeline-metrics`"
" tag.")
# get a dict from the 'pipeline parameters' cell source code
metrics = ast.parse_metrics_print_statements(metrics_source)
except ValueError as e:
log.exception("Failed to parse pipeline metrics")
raise RPCInternalError(details=str(e), trans_id=request.trans_id)
log.info("Pipeline metrics: {}".format(metrics))
return metrics
def to_pipeline(self):
"""Convert an annotated Notebook to a Pipeline object."""
(pipeline_parameters_source, pipeline_metrics_source,
imports_and_functions) = self.parse_notebook()
self.parse_pipeline_parameters(pipeline_parameters_source)
self.pipeline.set_volume_pipeline_parameters()
# get a list of variables that need to be logged as pipeline metrics
pipeline_metrics = ast.parse_metrics_print_statements(
pipeline_metrics_source)
# run static analysis over the source code
dependencies.dependencies_detection(
self.pipeline, imports_and_functions=imports_and_functions)
dependencies.assign_metrics(self.pipeline, pipeline_metrics)
# if there are multiple DAG leaves, add an empty step at the end of the
# pipeline for final snapshot
leaf_steps = self.pipeline.get_leaf_steps()
if self.config.autosnapshot and len(leaf_steps) > 1:
_name = "final_auto_snapshot"
self.pipeline.add_step(Step(name=_name, source=[]))
# add a link from all the last steps of the pipeline to
# the final auto snapshot one.
for step in leaf_steps:
self.pipeline.add_edge(step.name, _name)
# FIXME: Move this to a base class Processor, to be executed by default
# after `to_pipeline`, so that it is agnostic to the type of
# processor.
for step in self.pipeline.steps:
step.config.update(self.pipeline.config.steps_defaults)
# TODO: Additional action required:
# Run a static analysis over every step to check that pipeline
# parameters are not assigned with new values.
return self.pipeline
def notebook_to_graph(self):
"""Convert an annotated Notebook to a Graph."""
# convert notebook to nx graph
(pipeline_graph, pipeline_parameters_source, pipeline_metrics_source,
imports_and_functions) = 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)
# run static analysis over the source code
dependencies.dependencies_detection(
pipeline_graph,
pipeline_parameters=pipeline_parameters_dict,
imports_and_functions=imports_and_functions)
dependencies.assign_metrics(pipeline_graph, pipeline_metrics)
# 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 = graph_utils.get_leaf_nodes(pipeline_graph)
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 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 test_parse_metrics_print_statements_exc(code):
"""Tests a exception cases for parse_metrics_print_statements function."""
with pytest.raises(ValueError):
kale_ast.parse_metrics_print_statements(code)
def test_parse_metrics_print_statements(code, target):
"""Tests parse_metrics_print_statements function."""
res = kale_ast.parse_metrics_print_statements(code)
assert res == target