def testDoubleRDDToH2OFrame(spark, hc):
rdd = spark.sparkContext.parallelize([0.5, 1.3333333333, 178])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == 0.5
assert pytest.approx(h2o_frame[1, 0]) == 1.3333333333
assert h2o_frame[2, 0] == 178
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testNumericRDDtoH2OFrameWithValueTooBig(spark, hc):
min = _jvm().Long.MIN_VALUE - 1
max = _jvm().Long.MAX_VALUE + 1
rdd = spark.sparkContext.parallelize([1, min, max])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == str(1)
assert h2o_frame[1, 0] == str(min)
assert h2o_frame[2, 0] == str(max)
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testLongRDDToH2OFrame(spark, hc):
min = _jvm().Integer.MIN_VALUE - 1
max = _jvm().Integer.MAX_VALUE + 1
rdd = spark.sparkContext.parallelize([1, min, max])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == 1
assert h2o_frame[1, 0] == min
assert h2o_frame[2, 0] == max
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testStringRDDToH2OFrame(spark, hc):
rdd = spark.sparkContext.parallelize(["a", "b", "c"])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == "a"
assert h2o_frame[2, 0] == "c"
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testBooleanRDDToH2OFrame(spark, hc):
rdd = spark.sparkContext.parallelize([True, False, True, True, False])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == 1
assert h2o_frame[1, 0] == 0
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testIntegerRDDToH2OFrame(spark, hc):
rdd = spark.sparkContext.parallelize([num for num in range(0, 100)])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == 0
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
def testFloatRDDToH2OFrame(spark, hc):
rdd = spark.sparkContext.parallelize([0.5, 1.3333333333, 178])
h2o_frame = hc.asH2OFrame(rdd)
assert h2o_frame[0, 0] == 0.5
assert h2o_frame[1, 0] == 1.3333333333
unit_test_utils.asert_h2o_frame(h2o_frame, rdd)
