def to_csv(self,
path,
sep=',',
encoding='utf-8',
engine='python',
compression=None,
profile_name=None):
'''Write entityset to disk in the csv format, location specified by `path`.
Path could be a local path or a S3 path.
If writing to S3 a tar archive of files will be written.
Args:
path (str) : Location on disk to write to (will be created as a directory)
sep (str) : String of length 1. Field delimiter for the output file.
encoding (str) : A string representing the encoding to use in the output file, defaults to 'utf-8'.
engine (str) : Name of the engine to use. Possible values are: {'c', 'python'}.
compression (str) : Name of the compression to use. Possible values are: {'gzip', 'bz2', 'zip', 'xz', None}.
profile_name (str) : Name of AWS profile to use, False to use an anonymous profile, or None.
'''
serialize.write_data_description(self,
path,
format='csv',
index=False,
sep=sep,
encoding=encoding,
engine=engine,
compression=compression,
profile_name=profile_name)
return self
def to_pickle(self, path, compression=None):
'''Write entityset to disk in the pickle format, location specified by `path`.
Args:
path (str): location on disk to write to (will be created as a directory)
compression (str) : Name of the compression to use. Possible values are: {'gzip', 'bz2', 'zip', 'xz', None}.
'''
serialize.write_data_description(self, path, format='pickle', compression=compression)
return self
def test_serialize_subdirs_not_removed(es, tmpdir):
write_path = tmpdir.mkdir("test")
test_dir = write_path.mkdir("test_dir")
with open(str(write_path.join('data_description.json')), 'w') as f:
json.dump('__SAMPLE_TEXT__', f)
serialize.write_data_description(es, path=str(write_path), index='1', sep='\t', encoding='utf-8', compression=None)
assert os.path.exists(str(test_dir))
with open(str(write_path.join('data_description.json')), 'r') as f:
assert '__SAMPLE_TEXT__' not in json.load(f)
def to_parquet(self, path, engine='auto', compression=None):
'''Write entityset to disk in the parquet format, location specified by `path`.
Args:
path (str): location on disk to write to (will be created as a directory)
engine (str) : Name of the engine to use. Possible values are: {'auto', 'pyarrow', 'fastparquet'}.
compression (str) : Name of the compression to use. Possible values are: {'snappy', 'gzip', 'brotli', None}.
'''
serialize.write_data_description(self, path, format='parquet', engine=engine, compression=compression)
return self
def to_pickle(self, path, compression=None, profile_name=None):
'''Write entityset in the pickle format, location specified by `path`.
Path could be a local path or a S3 path.
If writing to S3 a tar archive of files will be written.
Args:
path (str): location on disk to write to (will be created as a directory)
compression (str) : Name of the compression to use. Possible values are: {'gzip', 'bz2', 'zip', 'xz', None}.
profile_name (str) : Name of AWS profile to use, False to use an anonymous profile, or None.
'''
serialize.write_data_description(self, path, format='pickle', compression=compression, profile_name=profile_name)
return self
def to_csv(self, path, sep=',', encoding='utf-8', engine='python', compression=None):
'''Write entityset to disk in the csv format, location specified by `path`.
Args:
path (str) : Location on disk to write to (will be created as a directory)
sep (str) : String of length 1. Field delimiter for the output file.
encoding (str) : A string representing the encoding to use in the output file, defaults to 'utf-8'.
engine (str) : Name of the engine to use. Possible values are: {'c', 'python'}.
compression (str) : Name of the compression to use. Possible values are: {'gzip', 'bz2', 'zip', 'xz', None}.
'''
serialize.write_data_description(self, path, format='csv', index=False, sep=sep, encoding=encoding, engine=engine, compression=compression)
return self
def to_parquet(self, path, engine='auto', compression=None, profile_name=None):
'''Write entityset to disk in the parquet format, location specified by `path`.
Path could be a local path or a S3 path.
If writing to S3 a tar archive of files will be written.
Args:
path (str): location on disk to write to (will be created as a directory)
engine (str) : Name of the engine to use. Possible values are: {'auto', 'pyarrow', 'fastparquet'}.
compression (str) : Name of the compression to use. Possible values are: {'snappy', 'gzip', 'brotli', None}.
profile_name (str) : Name of AWS profile to use, False to use an anonymous profile, or None.
'''
serialize.write_data_description(self, path, format='parquet', engine=engine, compression=compression, profile_name=profile_name)
return self
def test_serialize_subdirs_not_removed(es, tmpdir):
write_path = tmpdir.mkdir("test")
test_dir = write_path.mkdir("test_dir")
with open(str(write_path.join('data_description.json')), 'w') as f:
json.dump('__SAMPLE_TEXT__', f)
if ks and any(isinstance(e.df, ks.DataFrame) for e in es.entities):
compression = 'none'
else:
compression = None
serialize.write_data_description(es,
path=str(write_path),
index='1',
sep='\t',
encoding='utf-8',
compression=compression)
assert os.path.exists(str(test_dir))
with open(str(write_path.join('data_description.json')), 'r') as f:
assert '__SAMPLE_TEXT__' not in json.load(f)
def test_serialize_invalid_formats(es, tmpdir):
error_text = 'must be one of the following formats: {}'
error_text = error_text.format(', '.join(serialize.FORMATS))
with pytest.raises(ValueError, match=error_text):
serialize.write_data_description(es, path=str(tmpdir), format='')
