def __init__(self, model, description = ''):
if not isinstance(model, graphlab.Model) and not is_path(model):
raise TypeError('Model must be a GraphLab model or a path to a model.')
super(ModelPredictiveObject, self).__init__(description)
self._set_model(model)
def _set_model(self, model):
self.dependencies = {'model':model}
if is_path(model):
# This is a path, can't do anything till we load it.
self._model_methods = {}
return
self._model_methods = model._get_queryable_methods()
if type(self._model_methods) != dict:
raise RuntimeError("_get_queryable_methods for model %s should return a \
dictionary" % model.__class__)
for (method, description) in self._model_methods.iteritems():
if type(description) != dict:
raise RuntimeError("model %s _get_queryable_methods should use dict as method\
description."% mode.__class__)
for (param_name, param_type) in description.iteritems():
if (param_type not in ['sframe', 'sarray']):
raise RuntimeError("model %s _get_queryable_methods should only use \
'sframe' or 'sarray' type. %s is not supported" % (model.__class__, param_type))
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