Exemplo n.º 1
0
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])
Exemplo n.º 2
0
import d6tflow
import cfg, tasks, visualize

# Check task dependencies and their execution status
d6tflow.preview(tasks.TaskTrain())

# Execute the model training task including dependencies. See https://d6tflow.readthedocs.io/en/latest/run.html
d6tflow.run(tasks.TaskTrain())

# use output
visualize.accuracy()
visualize.plot_importances()

# change parameter and rerun, see https://d6tflow.readthedocs.io/en/latest/advparam.html
d6tflow.run(tasks.TaskTrain(do_preprocess=False))
visualize.accuracy(do_preprocess=False)  # task output is parameter specific

# rerun flow after code changes
import importlib
importlib.reload(cfg)
importlib.reload(tasks)

# say you changed TaskGetData, reset all tasks depending on TaskGetData
d6tflow.invalidate_downstream(tasks.TaskGetData(), tasks.TaskTrain())

d6tflow.preview(tasks.TaskTrain())
d6tflow.run(tasks.TaskTrain())
Exemplo n.º 3
0
    persist=['df']
    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