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 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 user_features(self):
"""
The user features.
Underlying model parameters.
"""
return XArray.from_rdd(self.model.userFeatures(), list)
def item_features(self):
"""
The item features.
Underlying model parameters.
"""
return XArray.from_rdd(self.model.productFeatures(), list)
def _base_predict(self, data):
"""
Call the model's predict function.
Data can be a single item or a collection of items.
"""
features = self.make_features(data)
if isinstance(features, DenseVector):
return self.model.predict(features)
if isinstance(features, XArray) and issubclass(features.dtype(), DenseVector):
res = self.model.predict(features.to_spark_rdd())
return XArray.from_rdd(res, float)
raise TypeError('must pass a DenseVector or XArray of DenseVector')
def crossproduct(d):
"""
Create an SFrame containing the crossproduct of all provided options.
Parameters
----------
d : dict
Each key is the name of an option, and each value is a list
of the possible values for that option.
Returns
-------
out : SFrame
There will be a column for each key in the provided dictionary,
and a row for each unique combination of all values.
Example
-------
settings = {'argument_1':[0, 1],
'argument_2':['a', 'b', 'c']}
print crossproduct(settings)
+------------+------------+
| argument_2 | argument_1 |
+------------+------------+
| a | 0 |
| a | 1 |
| b | 0 |
| b | 1 |
| c | 0 |
| c | 1 |
+------------+------------+
[6 rows x 2 columns]
"""
from xframes import XArray
d = [zip(d.keys(), x) for x in itertools.product(*d.values())]
sa = [{k: v for (k, v) in x} for x in d]
return XArray(sa).unpack(column_name_prefix='')
def test_construct_local_file_dict(self):
t = XArray('{}/user/xpatterns/files/test-array-dict'.format(hdfs_prefix))
self.assertEqualLen(4, t)
self.assertIs(dict, t.dtype())
self.assertDictEqual({1: 'a', 2: 'b'}, t[0])
def test_construct_local_file_list(self):
t = XArray('{}/user/xpatterns/files/test-array-list'.format(hdfs_prefix))
self.assertEqualLen(4, t)
self.assertIs(list, t.dtype())
self.assertListEqual([1, 2], t[0])
def test_construct_local_file_str(self):
t = XArray('{}/user/xpatterns/files/test-array-str'.format(hdfs_prefix))
self.assertEqualLen(4, t)
self.assertIs(str, t.dtype())
self.assertEqual('a', t[0])
def test_construct_local_file_float(self):
t = XArray('{}/user/xpatterns/files/test-array-float'.format(hdfs_prefix))
self.assertEqualLen(4, t)
self.assertIs(float, t.dtype())
self.assertEqual(1.0, t[0])
def test_construct_file_int(self):
path = '{}/user/xpatterns/files/test-array-int'.format(hdfs_prefix)
t = XArray(path)
self.assertEqualLen(4, t)
self.assertIs(int, t.dtype())
self.assertEqual(1, t[0])
