def test_auto_dtype(self):
x = np.arange(80).reshape((40, 2))
y = tuple(range(40))
z = list(range(40))
x_rdd = self.sc.parallelize(x, 4)
y_rdd = self.sc.parallelize(y, 4)
z_rdd = self.sc.parallelize(z, 4)
expected = (np.arange(20).reshape(10, 2), tuple(range(10)),
list(range(10)))
rdd = DictRDD([x_rdd, y_rdd, z_rdd])
assert_tuple_equal(rdd.first(), expected)
assert_equal(rdd.dtype, (np.ndarray, tuple, tuple))
assert_true(check_rdd_dtype(rdd, {0: np.ndarray, 1: tuple, 2: tuple}))
rdd = DictRDD([x_rdd, y_rdd, z_rdd], columns=('x', 'y', 'z'))
assert_tuple_equal(rdd.first(), expected)
assert_equal(rdd.dtype, (np.ndarray, tuple, tuple))
assert_true(
check_rdd_dtype(rdd, {
'x': np.ndarray,
'y': tuple,
'z': tuple
}))
def test_creation_from_blocked_rdds(self):
x, y, z = np.arange(80).reshape((40, 2)), np.arange(40), range(40)
x_rdd = ArrayRDD(self.sc.parallelize(x, 4))
y_rdd = ArrayRDD(self.sc.parallelize(y, 4))
z_rdd = BlockRDD(self.sc.parallelize(z, 4), dtype=list)
expected = (np.arange(20).reshape(10, 2), np.arange(10), range(10))
rdd = DictRDD([x_rdd, y_rdd, z_rdd])
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd], columns=('x', 'y', 'z'))
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd], dtype=(None, None, list))
first = rdd.first()
assert_tuple_equal(first, expected)
assert_is_instance(first[2], list)
def test_creation_from_zipped_rdd(self):
x = np.arange(80).reshape((40, 2))
y = range(40)
x_rdd = self.sc.parallelize(x, 4)
y_rdd = self.sc.parallelize(y, 4)
zipped_rdd = x_rdd.zip(y_rdd)
expected = (np.arange(20).reshape(10, 2), tuple(range(10)))
rdd = DictRDD(zipped_rdd)
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD(zipped_rdd, columns=('x', 'y'))
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD(zipped_rdd, dtype=(np.ndarray, list))
first = rdd.first()
assert_tuple_equal(first, expected)
assert_is_instance(first[1], list)
def test_creation_from_zipped_rdd(self):
x = np.arange(80).reshape((40, 2))
y = range(40)
x_rdd = self.sc.parallelize(x, 4)
y_rdd = self.sc.parallelize(y, 4)
zipped_rdd = x_rdd.zip(y_rdd)
expected = (np.arange(20).reshape(10, 2), tuple(range(10)))
rdd = DictRDD(zipped_rdd)
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD(zipped_rdd, columns=('x', 'y'))
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD(zipped_rdd, dtype=(np.ndarray, list))
first = rdd.first()
assert_tuple_equal(first, expected)
assert_is_instance(first[1], list)
def test_creation_from_blocked_rdds(self):
x = np.arange(80).reshape((40, 2))
y = np.arange(40)
z = list(range(40))
x_rdd = ArrayRDD(self.sc.parallelize(x, 4))
y_rdd = ArrayRDD(self.sc.parallelize(y, 4))
z_rdd = BlockRDD(self.sc.parallelize(z, 4), dtype=list)
expected = (np.arange(20).reshape(10,
2), np.arange(10), list(range(10)))
rdd = DictRDD([x_rdd, y_rdd, z_rdd])
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd], columns=('x', 'y', 'z'))
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd], dtype=(None, None, list))
first = rdd.first()
assert_tuple_equal(first, expected)
assert_is_instance(first[2], list)
def test_creation_from_rdds(self):
x = np.arange(80).reshape((40, 2))
y = np.arange(40)
z = list(range(40))
x_rdd = self.sc.parallelize(x, 4)
y_rdd = self.sc.parallelize(y, 4)
z_rdd = self.sc.parallelize(z, 4)
expected = (
np.arange(20).reshape(10, 2),
np.arange(10), list(range(10))
)
rdd = DictRDD([x_rdd, y_rdd, z_rdd])
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd], columns=('x', 'y', 'z'))
assert_tuple_equal(rdd.first(), expected)
rdd = DictRDD([x_rdd, y_rdd, z_rdd],
dtype=(np.ndarray, np.ndarray, list))
first = rdd.first()
assert_tuple_equal(first, expected)
assert_is_instance(first[2], list)
def test_auto_dtype(self):
x = np.arange(80).reshape((40, 2))
y = tuple(range(40))
z = list(range(40))
x_rdd = self.sc.parallelize(x, 4)
y_rdd = self.sc.parallelize(y, 4)
z_rdd = self.sc.parallelize(z, 4)
expected = (np.arange(20).reshape(10, 2), tuple(range(10)),
list(range(10)))
rdd = DictRDD([x_rdd, y_rdd, z_rdd])
assert_tuple_equal(rdd.first(), expected)
assert_equal(rdd.dtype, (np.ndarray, tuple, tuple))
assert_true(check_rdd_dtype(rdd, {0: np.ndarray, 1: tuple, 2: tuple}))
rdd = DictRDD([x_rdd, y_rdd, z_rdd], columns=('x', 'y', 'z'))
assert_tuple_equal(rdd.first(), expected)
assert_equal(rdd.dtype, (np.ndarray, tuple, tuple))
assert_true(check_rdd_dtype(rdd, {'x': np.ndarray, 'y': tuple,
'z': tuple}))
def test_get_single_tuple(self):
x, y = np.arange(80).reshape((40, 2)), np.arange(40)
x_rdd = self.sc.parallelize(x, 2)
y_rdd = self.sc.parallelize(y, 2)
z_rdd = x_rdd.zip(y_rdd)
z = DictRDD(z_rdd, bsize=5)
expected = np.arange(0, 10).reshape((5, 2)), np.arange(5)
for tpl in [z.first(), z[0].first(), z[0].first()]:
assert_tuple_equal(tpl, expected)
expected = np.arange(30, 40).reshape((5, 2)), np.arange(15, 20)
for tpl in [z[3].first(), z[3].first(), z[-5].first()]:
assert_tuple_equal(tpl, expected)
expected = np.arange(70, 80).reshape((5, 2)), np.arange(35, 40)
for tpl in [z[7].first(), z[7].first(), z[-1].first()]:
assert_tuple_equal(tpl, expected)
def test_get_single_tuple(self):
x, y = np.arange(80).reshape((40, 2)), np.arange(40)
x_rdd = self.sc.parallelize(x, 2)
y_rdd = self.sc.parallelize(y, 2)
z_rdd = x_rdd.zip(y_rdd)
z = DictRDD(z_rdd, bsize=5)
expected = np.arange(0, 10).reshape((5, 2)), np.arange(5)
for tpl in [z.first(), z[0].first(), z[0].first()]:
assert_tuple_equal(tpl, expected)
expected = np.arange(30, 40).reshape((5, 2)), np.arange(15, 20)
for tpl in [z[3].first(), z[3].first(), z[-5].first()]:
assert_tuple_equal(tpl, expected)
expected = np.arange(70, 80).reshape((5, 2)), np.arange(35, 40)
for tpl in [z[7].first(), z[7].first(), z[-1].first()]:
assert_tuple_equal(tpl, expected)