def upload_artifact(self,
name,
artifact_object=None,
metadata=None,
preview=None,
delete_after_upload=False,
auto_pickle=True):
# type: (str, Optional[object], Optional[dict], Optional[str], bool, bool) -> bool
if not Session.check_min_api_version('2.3'):
LoggerRoot.get_base_logger().warning(
'Artifacts not supported by your TRAINS-server version, '
'please upgrade to the latest server version')
return False
if name in self._artifacts_container:
raise ValueError(
"Artifact by the name of {} is already registered, use register_artifact"
.format(name))
# cast preview to string
if preview:
preview = str(preview)
# convert string to object if try is a file/folder (dont try to serialize long texts
if isinstance(artifact_object,
six.string_types) and len(artifact_object) < 2048:
# noinspection PyBroadException
try:
artifact_path = Path(artifact_object)
if artifact_path.exists():
artifact_object = artifact_path
elif '*' in artifact_object or '?' in artifact_object:
# hackish, detect wildcard in tr files
folder = Path('').joinpath(*artifact_path.parts[:-1])
if folder.is_dir() and folder.parts:
wildcard = artifact_path.parts[-1]
if list(Path(folder).rglob(wildcard)):
artifact_object = artifact_path
except Exception:
pass
artifact_type_data = tasks.ArtifactTypeData()
artifact_type_data.preview = ''
override_filename_in_uri = None
override_filename_ext_in_uri = None
uri = None
if np and isinstance(artifact_object, np.ndarray):
artifact_type = 'numpy'
artifact_type_data.content_type = 'application/numpy'
artifact_type_data.preview = preview or str(
artifact_object.__repr__())
override_filename_ext_in_uri = '.npz'
override_filename_in_uri = name + override_filename_ext_in_uri
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.close(fd)
np.savez_compressed(local_filename, **{name: artifact_object})
delete_after_upload = True
elif pd and isinstance(artifact_object, pd.DataFrame):
artifact_type = 'pandas'
artifact_type_data.content_type = 'text/csv'
artifact_type_data.preview = preview or str(
artifact_object.__repr__())
override_filename_ext_in_uri = self._save_format
override_filename_in_uri = name
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.close(fd)
artifact_object.to_csv(local_filename,
compression=self._compression)
delete_after_upload = True
elif isinstance(artifact_object, Image.Image):
artifact_type = 'image'
artifact_type_data.content_type = 'image/png'
desc = str(artifact_object.__repr__())
artifact_type_data.preview = preview or desc[1:desc.find(' at ')]
override_filename_ext_in_uri = '.png'
override_filename_in_uri = name + override_filename_ext_in_uri
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.close(fd)
artifact_object.save(local_filename)
delete_after_upload = True
elif isinstance(artifact_object, dict):
artifact_type = 'JSON'
artifact_type_data.content_type = 'application/json'
preview = preview or json.dumps(
artifact_object, sort_keys=True, indent=4)
override_filename_ext_in_uri = '.json'
override_filename_in_uri = name + override_filename_ext_in_uri
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.write(fd, bytes(preview.encode()))
os.close(fd)
if len(preview) < self.max_preview_size_bytes:
artifact_type_data.preview = preview
else:
artifact_type_data.preview = '# full json too large to store, storing first {}kb\n{}'.format(
self.max_preview_size_bytes // 1024,
preview[:self.max_preview_size_bytes])
delete_after_upload = True
elif isinstance(artifact_object, (
Path,
pathlib_Path,
) if pathlib_Path is not None else (Path, )):
# check if single file
artifact_object = Path(artifact_object)
artifact_object.expanduser().absolute()
# noinspection PyBroadException
try:
create_zip_file = not artifact_object.is_file()
except Exception: # Hack for windows pathlib2 bug, is_file isn't valid.
create_zip_file = True
else: # We assume that this is not Windows os
if artifact_object.is_dir():
# change to wildcard
artifact_object /= '*'
if create_zip_file:
folder = Path('').joinpath(*artifact_object.parts[:-1])
if not folder.is_dir() or not folder.parts:
raise ValueError(
"Artifact file/folder '{}' could not be found".format(
artifact_object.as_posix()))
wildcard = artifact_object.parts[-1]
files = list(Path(folder).rglob(wildcard))
override_filename_ext_in_uri = '.zip'
override_filename_in_uri = folder.parts[
-1] + override_filename_ext_in_uri
fd, zip_file = mkstemp(
prefix=quote(folder.parts[-1], safe="") + '.',
suffix=override_filename_ext_in_uri)
try:
artifact_type_data.content_type = 'application/zip'
archive_preview = 'Archive content {}:\n'.format(
artifact_object.as_posix())
with ZipFile(zip_file,
'w',
allowZip64=True,
compression=ZIP_DEFLATED) as zf:
for filename in sorted(files):
if filename.is_file():
relative_file_name = filename.relative_to(
folder).as_posix()
archive_preview += '{} - {}\n'.format(
relative_file_name,
humanfriendly.format_size(
filename.stat().st_size))
zf.write(filename.as_posix(),
arcname=relative_file_name)
except Exception as e:
# failed uploading folder:
LoggerRoot.get_base_logger().warning(
'Exception {}\nFailed zipping artifact folder {}'.
format(folder, e))
return False
finally:
os.close(fd)
artifact_type_data.preview = preview or archive_preview
artifact_object = zip_file
artifact_type = 'archive'
artifact_type_data.content_type = mimetypes.guess_type(
artifact_object)[0]
local_filename = artifact_object
delete_after_upload = True
else:
if not artifact_object.is_file():
raise ValueError(
"Artifact file '{}' could not be found".format(
artifact_object.as_posix()))
override_filename_in_uri = artifact_object.parts[-1]
artifact_type_data.preview = preview or '{} - {}\n'.format(
artifact_object,
humanfriendly.format_size(artifact_object.stat().st_size))
artifact_object = artifact_object.as_posix()
artifact_type = 'custom'
artifact_type_data.content_type = mimetypes.guess_type(
artifact_object)[0]
local_filename = artifact_object
elif (isinstance(artifact_object, six.string_types)
and len(artifact_object) < 4096
and urlparse(artifact_object).scheme in remote_driver_schemes):
# we should not upload this, just register
local_filename = None
uri = artifact_object
artifact_type = 'custom'
artifact_type_data.content_type = mimetypes.guess_type(
artifact_object)[0]
elif isinstance(artifact_object, six.string_types):
# if we got here, we should store it as text file.
artifact_type = 'string'
artifact_type_data.content_type = 'text/plain'
if preview:
artifact_type_data.preview = preview
elif len(artifact_object) < self.max_preview_size_bytes:
artifact_type_data.preview = artifact_object
else:
artifact_type_data.preview = '# full text too large to store, storing first {}kb\n{}'.format(
self.max_preview_size_bytes // 1024,
artifact_object[:self.max_preview_size_bytes])
delete_after_upload = True
override_filename_ext_in_uri = '.txt'
override_filename_in_uri = name + override_filename_ext_in_uri
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.close(fd)
# noinspection PyBroadException
try:
with open(local_filename, 'wt') as f:
f.write(artifact_object)
except Exception:
# cleanup and raise exception
os.unlink(local_filename)
raise
elif auto_pickle:
# if we are here it means we do not know what to do with the object, so we serialize it with pickle.
artifact_type = 'pickle'
artifact_type_data.content_type = 'application/pickle'
# noinspection PyBroadException
try:
artifact_type_data.preview = preview or str(
artifact_object.__repr__())[:self.max_preview_size_bytes]
except Exception:
artifact_type_data.preview = preview or ''
delete_after_upload = True
override_filename_ext_in_uri = '.pkl'
override_filename_in_uri = name + override_filename_ext_in_uri
fd, local_filename = mkstemp(prefix=quote(name, safe="") + '.',
suffix=override_filename_ext_in_uri)
os.close(fd)
# noinspection PyBroadException
try:
with open(local_filename, 'wb') as f:
pickle.dump(artifact_object, f)
except Exception:
# cleanup and raise exception
os.unlink(local_filename)
raise
else:
raise ValueError("Artifact type {} not supported".format(
type(artifact_object)))
# remove from existing list, if exists
for artifact in self._task_artifact_list:
if artifact.key == name:
if artifact.type == self._pd_artifact_type:
raise ValueError(
"Artifact of name {} already registered, "
"use register_artifact instead".format(name))
self._task_artifact_list.remove(artifact)
break
if not local_filename:
file_size = None
file_hash = None
else:
# check that the file to upload exists
local_filename = Path(local_filename).absolute()
if not local_filename.exists() or not local_filename.is_file():
LoggerRoot.get_base_logger().warning(
'Artifact upload failed, cannot find file {}'.format(
local_filename.as_posix()))
return False
file_hash, _ = self.sha256sum(local_filename.as_posix())
file_size = local_filename.stat().st_size
uri = self._upload_local_file(
local_filename,
name,
delete_after_upload=delete_after_upload,
override_filename=override_filename_in_uri,
override_filename_ext=override_filename_ext_in_uri)
timestamp = int(time())
artifact = tasks.Artifact(
key=name,
type=artifact_type,
uri=uri,
content_size=file_size,
hash=file_hash,
timestamp=timestamp,
type_data=artifact_type_data,
display_data=[(str(k), str(v))
for k, v in metadata.items()] if metadata else None)
# update task artifacts
with self._task_edit_lock:
self._task_artifact_list.append(artifact)
self._task.set_artifacts(self._task_artifact_list)
return True
