def test_preview():
t1 = Task1()
t2 = Task2()
t3 = Task3()
d6tflow.invalidate_upstream(t3, confirm=False)
import io
from contextlib import redirect_stdout
with io.StringIO() as buf, redirect_stdout(buf):
d6tflow.preview(t3)
output = buf.getvalue()
assert output.count('PENDING') == 3
assert output.count('COMPLETE') == 0
with io.StringIO() as buf, redirect_stdout(buf):
d6tflow.run(t3)
d6tflow.preview(t3)
output = buf.getvalue()
assert output.count('PENDING') == 0
assert output.count('COMPLETE') == 3
with io.StringIO() as buf, redirect_stdout(buf):
d6tflow.preview(Task3(do_preprocess=False))
output = buf.getvalue()
assert output.count('PENDING') == 1
assert output.count('COMPLETE') == 2
def test_execute(cleanup):
# execute
t1=Task1(); t2=Task2();t3=Task3();
[t.invalidate() for t in [t1,t2,t3]]
d6tflow.run(t3)
assert all(t.complete() for t in [t1,t2,t3])
t1.invalidate(); t2.invalidate();
assert not t3.complete() # cascade upstream
d6tflow.settings.check_dependencies=False
assert t3.complete() # no cascade upstream
d6tflow.run([t3])
assert t3.complete() and not t1.complete()
d6tflow.settings.check_dependencies=True
d6tflow.run([t3])
assert all(t.complete() for t in [t1,t2,t3])
# forced single
class TaskTest(d6tflow.tasks.TaskCachePandas):
def run(self):
self.save(df)
d6tflow.run(TaskTest())
assert TaskTest().output().load().equals(df)
class TaskTest(d6tflow.tasks.TaskCachePandas):
def run(self):
self.save(df*2)
d6tflow.run(TaskTest())
assert TaskTest().output().load().equals(df)
d6tflow.run(TaskTest(),forced=TaskTest(),confirm=False)
assert TaskTest().output().load().equals(df*2)
d6tflow.run([TaskTest()],forced=[TaskTest()],confirm=False)
# forced flow
mtimes = [t1.output().path.stat().st_mtime,t2.output()['df2'].path.stat().st_mtime]
d6tflow.run(t3,forced=t1,confirm=False)
assert t1.output().path.stat().st_mtime>mtimes[0]
assert t2.output()['df2'].path.stat().st_mtime>mtimes[1]
# downstream
assert d6tflow.run(t3)
d6tflow.invalidate_downstream(t2, t3, confirm=False)
assert not (t2.complete() and t3.complete()) and t1.complete()
# upstream
assert d6tflow.run(t3)
d6tflow.invalidate_upstream(t3, confirm=False)
assert not all(t.complete() for t in [t1,t2,t3])
def run(self):
self.save({'df':df})
class Task3(d6tflow.tasks.TaskCache):
persist=['df']
def requires(self):
return {'2':Task2(),'1a':Task1a()}
def run(self):
self.save({'df':df})
Task3().input()
importlib.reload(d6tflow)
d6tflow.show_flow(Task3())
d6tflow.invalidate_downstream(Task3())
d6tflow.invalidate_upstream(Task1(), Task3())
importlib.reload(d6tflow)
d6tflow.run_local([Task3()],forced=[Task1()])
d6tflow.run_local([Task3()])
import luigi.tools.deps
import luigi.tools.deps_tree
import yaml
cfg = yaml.load(open('tests/.creds.yml'))
print(cfg)
print(cfg['d6tpipe_profile'])
from pathlib import Path
persist = ['df', 'df2']
idx3 = luigi.Parameter(default='test3')
export = False
def run(self):
self.save({'df': df, 'df2': df})
@d6tflow.requires(Task1A, Task1B, Task1C)
class Task1All(d6tflow.tasks.TaskCache):
def run(self):
self.save(df)
d6tflow.run(Task1All())
d6tflow.invalidate_upstream(Task1All(), confirm=False)
d6tflow.preview(Task1All())
task = Task1All()
#**************************************************
# tests
#**************************************************
import pytest
import d6tflow.pipes
def readfile(file_dir):
with open(file_dir, 'r') as f:
import d6tflow
# Import workflow tasks and output visualizations
import flow_tasks, flow_viz
# Instantiate terminal task with parameters
params = {'data_size': 6, 'mini_batch_size': 2}
task = flow_tasks.TaskModelTrain(**params)
# optional: reset everything every time workflow is run
d6tflow.invalidate_upstream(task, confirm=False)
# Preview terminal task
d6tflow.preview(task, clip_params=True)
# Run terminal task
d6tflow.run(task)
# Show output
if task.complete():
flow_viz.show_test_prints(params)
