def test_workflow():
builder = FugueWorkflow()
a = builder.create_data([[0], [0], [1]], "a:int")
raises(InvalidOperationError, lambda: a._task.copy())
raises(InvalidOperationError, lambda: copy.copy(a._task))
raises(InvalidOperationError, lambda: copy.deepcopy(a._task))
a.show()
a.show()
raises(FugueWorkflowCompileError, lambda: builder.df(123))
b = a.transform(mock_tf1, "*,b:int", pre_partition=dict(by=["a"]))
b.show()
builder.create_data([[0], [1]], "b:int").show()
c = ArrayDataFrame([[100]], "a:int")
builder.show(a, b, c)
b = a.partition(by=["a"]).transform(mock_tf2).persist().broadcast()
b.show()
builder.run()
df_eq(a.result, [[0], [0], [1]], "a:int")
raises(TypeError, lambda: builder.run("abc"))
builder.run(FugueWorkflowContext())
df_eq(a.result, [[0], [0], [1]], "a:int")
builder.run("NativeExecutionEngine")
df_eq(b.result, [[0, 2], [0, 2], [1, 1]], "a:int,b:int")
df_eq(b.compute(), [[0, 2], [0, 2], [1, 1]], "a:int,b:int")
df_eq(b.compute(NativeExecutionEngine), [[0, 2], [0, 2], [1, 1]],
"a:int,b:int")
def test_print():
dag = FugueWorkflow()
a = dag.create(mock_create1, params=dict(n=1))
a.show()
b = dag.create(mock_create1, params=dict(n=2))
dag.show(a, b, rows=5, show_count=True, title='"b B')
assert_eq(
"""
a=create using mock_create1(n=1)
print
print 5 rows from a, (create using mock_create1(n=2)) rowcount title "\\"b B"
""",
dag,
)
def test_yield():
dag = FugueWorkflow()
dag.df([[0]], "a:int32").show()
id0 = dag.spec_uuid()
x = FugueWorkflow().df([[0]], "a:int32")
x.yield_file_as("x")
x.show()
id1 = x.workflow.spec_uuid()
x = FugueWorkflow().df([[0]], "a:int32")
x.deterministic_checkpoint().yield_file_as("y")
x.show()
id2 = x.workflow.spec_uuid()
x = FugueWorkflow().df([[0]], "a:int32")
x.deterministic_checkpoint().yield_dataframe_as("z")
x.show()
id3 = x.workflow.spec_uuid()
# yield doesn't change determinism
assert id0 == id1
assert id0 == id2
assert id0 == id3
