def save(self, path, dependency_path, aws_credentials = {}):
""" Save predictive object to the given path
Parameters
----------
path : str
The location to save the predictive object to
"""
# only support saving to local or S3 for now
if (not fu.is_s3_path(path)) and (not fu.is_local_path(path)):
raise RuntimeError("Only save to local and S3 path is supported, cannot \
save predictive object to path %s. " % path)
if (fu.is_s3_path(path)):
self._save_s3(path, dependency_path, aws_credentials)
else:
if os.path.exists(path):
if os.path.isfile(path):
__logger__.warning("Overwriting existing file '%s' when saving predictive object" % path)
else:
raise RuntimeError("Path %s already exists, please remove that and save again" % path)
self._save_local(path, dependency_path, aws_credentials)
tracker = _mt._get_metric_tracker()
tracker.track('deploy.predictive_service.predictive_object',
value=1,
properties={
'type': self.__class__.__name__,
'dependencies': len(self.dependencies) if self.dependencies else 0}
)
def load(cls, path):
""" Load predictive object from given path
"""
new_po = None
if (fu.is_s3_path(path)):
new_po = cls._load_s3(path)
else:
new_po = cls._load_local(path)
# call derived class post_load
new_po.post_load()
return new_po
def _save_imp(self, po_path, dependency_path, aws_credentials):
'''Save the predictive object to a directory
The files for a predictive object are laid out the following way:
po_path/definition/meta -- serialized json file about the predictive
object, including: description, dependencies, etc.
po_path/definition/definition -- cloudpickle-serialized PredictiveObject
dependency_path -- all dependent GraphLab objects, each in its
own directory:
dependency_path/uri1/ -- serialized GraphLab object with uri1
dependency_path/uri2/ -- serialized GraphLab object with uri2
'''
fu.create_directory(po_path)
describe = {
'description': self.description,
'dependencies': {},
'schema_version' : self.schema_version
}
for (uri, gl_obj) in self.dependencies.iteritems():
# If it isn't already saved, save it.
temp_path = None
try:
if not fu.is_path(gl_obj):
obj_type = self._get_graphlab_object_type(gl_obj)
temp_path = tempfile.mkdtemp()
__logger__.info("Saving dependent GraphLab %s (%s) locally to '%s' " % (obj_type, uri, temp_path))
gl_obj.save(temp_path)
gl_obj = temp_path
else:
obj_type = get_graphlab_object_type(gl_obj)
# Copy the saved object without loading it.
save_path = os.path.join(dependency_path, uri)
__logger__.info("Copying dependent GraphLab %s(%s) from '%s' to '%s' " % (obj_type, uri, gl_obj, save_path))
if fu.is_s3_path(gl_obj) and fu.is_s3_path(save_path):
fu.intra_s3_copy_model(gl_obj, save_path, aws_credentials)
elif fu.is_local_path(gl_obj) and fu.is_s3_path(save_path):
fu.s3_copy_model(gl_obj, save_path, aws_credentials)
elif fu.is_local_path(gl_obj) and fu.is_local_path(save_path):
# Useful for unit tests
shutil.copytree(gl_obj, save_path)
else:
raise RuntimeError("Copy GraphLab object from S3 to local path is not supported. GraphLab object path: %s, save path: %s" % (gl_obj, save_path))
finally:
if temp_path:
shutil.rmtree(temp_path)
# add to the global describe dictionary
describe['dependencies'][uri] = {
'path': save_path,
'type': obj_type
}
# persist the global description
describe_path = self._get_describe_path(po_path)
self._save_object(describe_path, describe)
# persist the definition of myself
definition_path = self._get_definition_path(po_path)
try:
with open(definition_path, 'wb') as f:
_cloudpickle.dump(self, f)
except Exception as e:
__logger__.error('Unable to save object: %s' % (e.message))
raise e
