def test_save(self):
t = XArray([1, 2, 3])
path = '{}/tmp/array-csv'.format(hdfs_prefix)
t.save(path)
success_path = os.path.join(path, '_SUCCESS')
self.assertTrue(fileio.is_file(success_path))
fileio.delete(path)
def save_as_csv(self, path, **params):
"""
Saves the RDD to file as text.
"""
self._entry(path=path)
# noinspection PyShadowingNames
def to_csv(row, **params):
sio = StringIO.StringIO()
writer = csv.writer(sio, **params)
try:
writer.writerow([row], **params)
ret = sio.getvalue()
return ret
except IOError:
return ''
fileio.delete(path)
with fileio.open_file(path, 'w') as f:
self.begin_iterator()
elems_at_a_time = 10000
ret = self.iterator_get_next(elems_at_a_time)
while True:
for row in ret:
line = to_csv(row, **params)
f.write(line)
if len(ret) == elems_at_a_time:
ret = self.iterator_get_next(elems_at_a_time)
else:
break
def save_as_csv(self, path, **params):
"""
Saves the RDD to file as text.
"""
self._entry(path=path)
# noinspection PyShadowingNames
def to_csv(row, **params):
sio = StringIO.StringIO()
writer = csv.writer(sio, **params)
try:
writer.writerow([row], **params)
ret = sio.getvalue()
return ret
except IOError:
return ''
fileio.delete(path)
with fileio.open_file(path, 'w') as f:
self.begin_iterator()
elems_at_a_time = 10000
ret = self.iterator_get_next(elems_at_a_time)
while True:
for row in ret:
line = to_csv(row, **params)
f.write(line)
if len(ret) == elems_at_a_time:
ret = self.iterator_get_next(elems_at_a_time)
else:
break
def test_save_format(self):
t = XArray([1, 2, 3])
path = '{}/tmp/array-csv'.format(hdfs_prefix)
t.save(path, format='csv')
with fileio.open_file(path) as f:
self.assertEqual('1', f.readline().strip())
self.assertEqual('2', f.readline().strip())
self.assertEqual('3', f.readline().strip())
fileio.delete(path)
def test_save(self):
t = XFrame({'id': [30, 20, 10], 'val': ['a', 'b', 'c']})
path = '{}/tmp/frame'.format(hdfs_prefix)
t.save(path, format='binary')
with fileio.open_file(os.path.join(path, '_metadata')) as f:
metadata = pickle.load(f)
self.assertListEqual([['id', 'val'], [int, str]], metadata)
# TODO find some way to check the data
fileio.delete(path)
def test_save(self):
t = XFrame({'id': [30, 20, 10], 'val': ['a', 'b', 'c']})
path = '{}/tmp/frame-csv'.format(hdfs_prefix)
t.save(path, format='csv')
with fileio.open_file(path + '.csv') as f:
heading = f.readline().rstrip()
self.assertEqual('id,val', heading)
self.assertEqual('30,a', f.readline().rstrip())
self.assertEqual('20,b', f.readline().rstrip())
self.assertEqual('10,c', f.readline().rstrip())
fileio.delete(path + '.csv')
def test_read_parquet_str(self):
t = XFrame({'id': [1, 2, 3], 'val': ['a', 'b', 'c']})
path = '{}/tmp/frame-parquet'.format(hdfs_prefix)
t.save(path, format='parquet')
res = XFrame('{}/tmp/frame-parquet.parquet'.format(hdfs_prefix))
# results may not come back in the same order
res = res.sort('id')
self.assertEqualLen(3, res)
self.assertListEqual(['id', 'val'], res.column_names())
self.assertListEqual([int, str], res.column_types())
self.assertDictEqual({'id': 1, 'val': 'a'}, res[0])
self.assertDictEqual({'id': 2, 'val': 'b'}, res[1])
self.assertDictEqual({'id': 3, 'val': 'c'}, res[2])
fileio.delete(path)
def save_as_text(self, path):
"""
Saves the RDD to file as text.
"""
self._entry(path=path)
fileio.delete(path)
try:
self._rdd.saveAsTextFile(path)
except:
# TODO distinguish between filesystem errors and pickle errors
raise TypeError('The XArray save failed.')
metadata = self.elem_type
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
lineage_path = os.path.join(path, '_lineage')
self.lineage.save(lineage_path)
def save_as_text(self, path):
"""
Saves the RDD to file as text.
"""
self._entry(path=path)
fileio.delete(path)
try:
self._rdd.saveAsTextFile(path)
except:
# TODO distinguish between filesystem errors and pickle errors
raise TypeError('The XArray save failed.')
metadata = self.elem_type
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
lineage_path = os.path.join(path, '_lineage')
self.lineage.save(lineage_path)
def save(self, path):
"""
Saves the RDD to file in pickled form.
"""
self._entry(path=path)
# this only works for local files
fileio.delete(path)
try:
self._rdd.saveAsPickleFile(path) # action ?
except:
# TODO distinguish between filesystem errors and pickle errors
raise TypeError('The XArray save failed.')
metadata = self.elem_type
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
lineage_path = os.path.join(path, '_lineage')
self.lineage.save(lineage_path)
def save(self, path):
"""
Saves the RDD to file in pickled form.
"""
self._entry(path=path)
# this only works for local files
fileio.delete(path)
try:
self._rdd.saveAsPickleFile(path) # action ?
except:
# TODO distinguish between filesystem errors and pickle errors
raise TypeError('The XArray save failed.')
metadata = self.elem_type
metadata_path = os.path.join(path, '_metadata')
with fileio.open_file(metadata_path, 'w') as f:
# TODO detect filesystem errors
pickle.dump(metadata, f)
lineage_path = os.path.join(path, '_lineage')
self.lineage.save(lineage_path)
def test_save(self):
t = XFrame({'id': [30, 20, 10], 'val': ['a', 'b', 'c']})
path = '{}/tmp/frame-parquet'.format(hdfs_prefix)
t.save(path, format='parquet')
# TODO verify
fileio.delete(path + '.parquet')
