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 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')
