def save(self, path):
"""
Save a model.
The model can be saved, then reloaded later to provide recommendations.
Parameters
----------
path : str
The path where the model will be saved.
This should refer to a file, not to a directory.
Three items will be stored here: the underlying model parameters, the original ratings,
and the column names. These are stored with suffix '.model', '.ratings', and
'.metadata'.
"""
sc = CommonSparkContext.Instance().sc
delete_file_or_dir(path)
os.makedirs(path)
model_path, metadata_path = self._file_paths(path)
# save model
self.model.save(sc, model_path)
# save metadata
model_type = self.__class__.__name__
metadata = [model_type, self.feature_cols]
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
def save(self, path):
"""
Save a model.
The model can be saved, then reloaded later to provide recommendations.
Parameters
----------
path : str
The path where the model will be saved.
This should refer to a file, not to a directory.
Three items will be stored here: the underlying model parameters, the original ratings,
and the column names. These are stored with suffix '.model', '.ratings', and
'.metadata'.
"""
sc = CommonSparkContext.Instance().sc()
delete_file_or_dir(path)
os.makedirs(path)
model_path, ratings_path, metadata_path = self._file_paths(path)
# save model
self.model.save(sc, model_path)
# save ratings
self.ratings.save(ratings_path)
# save metadata
metadata = [self.user_col, self.item_col, self.rating_col]
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
def delete(uri):
""" Delete a file or directory. """
parsed_uri = _parse_uri(uri)
if parsed_uri.scheme == 'file':
from xframes.util import delete_file_or_dir
delete_file_or_dir(parsed_uri.path)
elif parsed_uri.scheme == 'hdfs':
hdfs_connection = _make_hdfs_connection(parsed_uri)
hdfs_connection.delete(parsed_uri.path, recursive=True)
elif parsed_uri.scheme == 'hive':
pass
else:
raise UriError('Invalid URI scheme: {}'.format(parsed_uri.scheme))
def delete(uri):
""" Delete a file or directory. """
parsed_uri = _parse_uri(uri)
if parsed_uri.scheme == 'file':
from xframes.util import delete_file_or_dir
delete_file_or_dir(parsed_uri.path)
elif parsed_uri.scheme == 'hdfs':
hdfs_connection = _make_hdfs_connection(parsed_uri)
hdfs_connection.delete(parsed_uri.path, recursive=True)
elif parsed_uri.scheme == 'hive':
pass
else:
raise UriError('Invalid URI scheme: {}'.format(parsed_uri.scheme))