def test_head(test_backend):
dataset = get_dataset(test_backend,
data,
schemas=schemas.get(test_backend),
caching=True)
dataset.expect_column_mean_to_be_between("b", 5, 5)
head = dataset.head(1)
assert isinstance(head, PandasDataset)
assert len(head) == 1
assert list(head.columns) == ["a", "b", "c", "d"]
assert head["a"][0] == 2.0
suite = head.get_expectation_suite()
assert len(suite.expectations) == 5
# Interestingly, the original implementation failed to work for a single
# column (it would always name the column "*").
# This should also work if we only get a single column
dataset = get_dataset(test_backend, {"a": data["a"]},
schemas=schemas.get(test_backend),
caching=True)
head = dataset.head(1)
assert isinstance(head, PandasDataset)
assert len(head) == 1
assert list(head.columns) == ["a"]
# We also needed special handling for empty tables in SqlalchemyDataset
dataset = get_dataset(test_backend, {"a": []},
schemas=schemas.get(test_backend),
caching=True)
head = dataset.head(1)
assert isinstance(head, PandasDataset)
assert len(head) == 0
assert list(head.columns) == ["a"]
def test_caching(test_backend):
dataset = get_dataset(test_backend, data, schemas=schemas.get(test_backend), caching=True)
dataset.get_column_max('a')
dataset.get_column_max('a')
dataset.get_column_max('b')
assert dataset.get_column_max.cache_info().hits == 1
assert dataset.get_column_max.cache_info().misses == 2
assert dataset.get_column_max.cache_info().misses == 2
dataset = get_dataset(test_backend, data, schemas=schemas.get(test_backend), caching=False)
with pytest.raises(AttributeError):
dataset.get_column_max.cache_info()
def pytest_generate_tests(metafunc):
#Load all the JSON files in the directory
dir_path = os.path.dirname(os.path.realpath(__file__))
test_configuration_files = glob.glob(dir_path+'/*.json')
parametrized_tests = []
ids = []
for c in contexts:
for filename in test_configuration_files:
file = open(filename)
test_configuration = json.load(file)
if candidate_test_is_on_temporary_notimplemented_list(c, test_configuration["expectation_type"]):
warnings.warn("Skipping generation of tests for expectation " + test_configuration["expectation_type"] +
" and context " + c)
else:
for d in test_configuration['datasets']:
my_dataset = get_dataset(c, d["data"])
for test in d["tests"]:
parametrized_tests.append({
"expectation_type": test_configuration["expectation_type"],
"dataset": my_dataset,
"test": test,
})
ids.append(c+":"+test_configuration["expectation_type"]+":"+test["title"])
metafunc.parametrize(
"test_case",
parametrized_tests,
ids=ids
)
def unexpected_count_df(sa):
return get_dataset("sqlite", {"a": [1, 2, 1, 2, 1, 2, 1, 2, 1, 2]})