def run(dataset: Dataset, config: TaskConfig):
with TmpDir() as tmpdir:
ds = ns(
train=ns(
X_enc=os.path.join(tmpdir, 'train.X_enc'),
y=os.path.join(tmpdir, 'train.y')
),
test=ns(
X_enc=os.path.join(tmpdir, 'test.X_enc'),
y=os.path.join(tmpdir, 'test.y')
)
)
write_csv(dataset.train.X_enc, ds.train.X_enc),
write_csv(dataset.train.y.reshape(-1, 1), ds.train.y),
write_csv(dataset.test.X_enc, ds.test.X_enc),
write_csv(dataset.test.y.reshape(-1, 1), ds.test.y),
dataset.release()
config.result_token = str(uuid.uuid1())
config.result_dir = tmpdir
params = json_dumps(dict(dataset=ds, config=config), style='compact')
output, err = run_cmd('{python} {here}/exec_proc.py'.format(python=PYTHON, here=dir_of(__file__)), _input_str_=params)
out = io.StringIO(output)
res = ns()
for line in out:
li = line.rstrip()
if li == config.result_token:
res = json_loads(out.readline(), as_namespace=True)
break
def load_data(path):
return read_csv(path, as_data_frame=False, header=False)
log.debug("Result from subprocess:\n%s", res)
save_predictions_to_file(dataset=dataset,
output_file=res.output_file,
probabilities=load_data(res.probabilities) if res.probabilities is not None else None,
predictions=load_data(res.predictions).squeeze(),
truth=load_data(res.truth).squeeze(),
target_is_encoded=res.target_is_encoded)
def run_in_venv(caller_file,
script_file: str,
*args,
input_data: Union[dict, ns],
dataset: Dataset,
config: TaskConfig,
process_results=None,
python_exec=None):
here = dir_of(caller_file)
venv_bin_path = os.path.join(here, 'venv', 'bin')
if python_exec is None: # use local virtual env by default
python_exec = os.path.join(venv_bin_path, 'python -W ignore')
script_path = os.path.join(here, script_file)
cmd = f"{python_exec} {script_path}"
input_data = ns.from_dict(input_data)
with TemporaryDirectory() as tmpdir:
def make_path(k, v, parents=None):
if isinstance(v, np.ndarray):
path = os.path.join(tmpdir, '.'.join(parents + [k, 'npy']))
if vector_keys.match(k):
v = v.reshape(-1, 1)
np.save(path, v, allow_pickle=True)
return k, path
return k, v
ds = ns.walk(input_data, make_path)
dataset.release()
config.result_dir = tmpdir
config.result_file = mktemp(dir=tmpdir)
params = json_dumps(dict(dataset=ds, config=config), style='compact')
with Timer() as proc_timer:
output, err = run_cmd(
cmd,
*args,
_input_str_=params,
_live_output_=True,
_error_level_=logging.DEBUG,
_env_=dict(PATH=os.pathsep.join(
[venv_bin_path, os.environ['PATH']]),
PYTHONPATH=os.pathsep.join([
rconfig().root_dir,
]),
AMLB_PATH=os.path.join(rconfig().root_dir, "amlb")),
)
res = ns(lambda: None)
if os.path.exists(config.result_file):
res = json_load(config.result_file, as_namespace=True)
log.debug("Result from subprocess:\n%s", res)
if not res:
raise NoResultError(f"Process crashed:\n{err}")
if res.error_message is not None:
raise NoResultError(res.error_message)
for name in ['predictions', 'truth', 'probabilities']:
res[name] = np.load(
res[name],
allow_pickle=True) if res[name] is not None else None
if callable(process_results):
res = process_results(res)
if res.output_file:
save_predictions(
dataset=dataset,
output_file=res.output_file,
predictions=res.predictions.reshape(-1)
if res.predictions is not None else None,
truth=res.truth.reshape(-1) if res.truth is not None else None,
probabilities=res.probabilities,
probabilities_labels=res.probabilities_labels,
target_is_encoded=res.target_is_encoded)
return dict(models_count=res.models_count
if res.models_count is not None else 1,
training_duration=res.training_duration if
res.training_duration is not None else proc_timer.duration,
predict_duration=res.predict_duration,
**res.others.__dict__)
def run_in_venv(caller_file,
script_file: str,
*args,
input_data: Union[dict, ns],
dataset: Dataset,
config: TaskConfig,
process_results=None,
python_exec=None):
here = dir_of(caller_file)
if python_exec is None: # use local virtual env by default
python_exec = os.path.join(here, 'venv/bin/python -W ignore')
script_path = os.path.join(here, script_file)
cmd = f"{python_exec} {script_path}"
input_data = ns.from_dict(input_data)
with TmpDir() as tmpdir:
def make_path(k, v, parents=None):
if isinstance(v, np.ndarray):
path = os.path.join(tmpdir, '.'.join(parents + [k, 'npy']))
if vector_keys.match(k):
v = v.reshape(-1, 1)
np.save(path, v, allow_pickle=True)
return k, path
return k, v
ds = ns.walk(input_data, make_path)
dataset.release()
config.result_token = str(uuid.uuid1())
config.result_dir = tmpdir
params = json_dumps(dict(dataset=ds, config=config), style='compact')
with Timer() as proc_timer:
output, err = run_cmd(cmd,
*args,
_input_str_=params,
_live_output_=True,
_env_=dict(PYTHONPATH=os.pathsep.join([
rconfig().root_dir,
os.path.join(rconfig().root_dir, "amlb"),
])))
out = io.StringIO(output)
res = ns()
for line in out:
li = line.rstrip()
if li == config.result_token:
res = json_loads(out.readline(), as_namespace=True)
break
if res.error_message is not None:
raise NoResultError(res.error_message)
for name in ['predictions', 'truth', 'probabilities']:
res[name] = np.load(
res[name],
allow_pickle=True) if res[name] is not None else None
log.debug("Result from subprocess:\n%s", res)
if callable(process_results):
res = process_results(res)
save_predictions_to_file(
dataset=dataset,
output_file=res.output_file,
predictions=res.predictions.reshape(-1)
if res.predictions is not None else None,
truth=res.truth.reshape(-1) if res.truth is not None else None,
probabilities=res.probabilities,
target_is_encoded=res.target_is_encoded)
return dict(models_count=res.models_count
if res.models_count is not None else 1,
training_duration=res.training_duration if
res.training_duration is not None else proc_timer.duration)
def run_in_venv(caller_file,
script_file: str,
*args,
input_data: Union[dict, ns],
dataset: Dataset,
config: TaskConfig,
options: Union[None, dict, ns] = None,
process_results=None,
python_exec=None):
here = dir_of(caller_file)
if python_exec is None: # use local virtual env by default
python_exec = venv_python_exec(here)
script_path = os.path.join(here, script_file)
cmd = f"{python_exec} {script_path}"
options = ns.from_dict(options) if options else ns()
ser_config = options['serialization']
env = options['env'] or ns()
with TemporaryDirectory() as tmpdir:
ds = _make_input_dataset(input_data,
dataset,
tmpdir,
serialization=ser_config)
config.result_dir = tmpdir
config.result_file = mktemp(dir=tmpdir)
params = json_dumps(dict(dataset=ds, config=config, options=options),
style='compact')
log.debug("Params passed to subprocess:\n%s", params)
cmon = rconfig().monitoring
monitor = (dict(interval_seconds=cmon.interval_seconds,
verbosity=cmon.verbosity)
if 'sub_proc_memory' in cmon.statistics else None)
env = dict(PATH=os.pathsep.join([venv_bin(here), os.environ['PATH']]),
PYTHONPATH=os.pathsep.join([
rconfig().root_dir,
]),
AMLB_PATH=os.path.join(rconfig().root_dir, "amlb"),
AMLB_LOG_TRACE=str(
logging.TRACE if hasattr(logging, 'TRACE') else ''),
**{k: str(v)
for k, v in env})
with Timer() as proc_timer:
output, err = run_cmd(cmd,
*args,
_input_str_=params,
_live_output_=True,
_error_level_=logging.DEBUG,
_env_=env,
_monitor_=monitor)
res = ns(lambda: None)
if os.path.exists(config.result_file):
res = json_load(config.result_file, as_namespace=True)
log.debug("Result from subprocess:\n%s", res)
if not res:
raise NoResultError(f"Process crashed:\n{err}")
if res.error_message is not None:
raise NoResultError(res.error_message)
for name in ['predictions', 'truth', 'probabilities']:
res[name] = deserialize_data(
res[name],
config=ser_config) if res[name] is not None else None
if callable(process_results):
res = process_results(res)
if res.output_file:
save_predictions(dataset=dataset,
output_file=res.output_file,
predictions=as_vec(res.predictions),
truth=(as_vec(res.truth) if res.truth is not None
else dataset.test.y_enc if
res.target_is_encoded else dataset.test.y),
probabilities=res.probabilities,
probabilities_labels=res.probabilities_labels,
target_is_encoded=res.target_is_encoded)
return dict(models_count=res.models_count
if res.models_count is not None else 1,
training_duration=res.training_duration if
res.training_duration is not None else proc_timer.duration,
predict_duration=res.predict_duration,
**res.others.__dict__)