def test_split_on_multi_column_values_and_sample_using_random(test_sparkdf):
returned_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
splitter_method="_split_on_multi_column_values",
splitter_kwargs={
"column_names": ["y", "m", "d"],
"partition_definition": {
"y": 2020,
"m": 1,
"d": 5,
},
},
sampling_method="_sample_using_random",
sampling_kwargs={
"p": 0.5,
},
)
)
# The test dataframe contains 10 columns and 120 rows.
assert len(returned_df.columns) == 10
# The number of returned rows corresponding to the value of "partition_definition" above is 4.
assert 0 <= returned_df.count() <= 4
# The sampling probability "p" used in "SparkDFExecutionEngine._sample_using_random()" is 0.5 (the equivalent of a
# fair coin with the 50% chance of coming up as "heads"). Hence, on average we should get 50% of the rows, which is
# 2; however, for such a small sample (of 4 rows), the number of rows returned by an individual run can deviate from
# this average. Still, in the majority of trials, the number of rows should not be fewer than 2 or greater than 3.
# The assertion in the next line, supporting this reasoning, is commented out to insure zero failures. Developers
# are encouraged to uncomment it, whenever the "_sample_using_random" feature is the main focus of a given effort.
# assert 2 <= returned_df.count() <= 3
for val in returned_df.collect():
assert val.date == datetime.date(2020, 1, 5)
def test_get_batch_with_split_on_column_value(test_sparkdf):
split_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
splitter_method="_split_on_column_value",
splitter_kwargs={
"column_name": "batch_id",
"partition_definition": {"batch_id": 2},
},
)
)
assert test_sparkdf.count() == 120
assert len(test_sparkdf.columns) == 10
collected = split_df.collect()
for val in collected:
assert val.batch_id == 2
split_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
splitter_method="_split_on_column_value",
splitter_kwargs={
"column_name": "date",
"partition_definition": {"date": datetime.date(2020, 1, 30)},
},
)
)
assert split_df.count() == 3
assert len(split_df.columns) == 10
def test_get_batch_with_split_on_multi_column_values(test_sparkdf):
split_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
splitter_method="_split_on_multi_column_values",
splitter_kwargs={
"column_names": ["y", "m", "d"],
"partition_definition": {
"y": 2020,
"m": 1,
"d": 5,
},
},
))
assert split_df.count() == 4
assert len(split_df.columns) == 10
collected = split_df.collect()
for val in collected:
assert val.date == datetime.date(2020, 1, 5)
with pytest.raises(ValueError):
split_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
splitter_method="_split_on_multi_column_values",
splitter_kwargs={
"column_names": ["I", "dont", "exist"],
"partition_definition": {
"y": 2020,
"m": 1,
"d": 5,
},
},
))
def test_sample_using_md5(test_sparkdf):
sampled_df = SparkDFExecutionEngine().get_batch_data(
RuntimeDataBatchSpec(
batch_data=test_sparkdf,
sampling_method="_sample_using_hash",
sampling_kwargs={
"column_name": "date",
"hash_function_name": "md5",
},
)
)
assert sampled_df.count() == 10
assert len(sampled_df.columns) == 10
collected = sampled_df.collect()
for val in collected:
assert val.date in [datetime.date(2020, 1, 15), datetime.date(2020, 1, 29)]
