def run(dataset: Dataset, config: TaskConfig):
#TODO: use rpy2 instead? not necessary here though as the call is very simple
log.info("\n**** Random Forest (R) ****\n")
is_classification = config.type == 'classification'
if not is_classification:
raise ValueError('Regression is not supported.')
here = dir_of(__file__)
run_cmd(
r"""Rscript --vanilla -e "source('{script}'); run('{train}', '{test}', '{output}', {cores})" """
.format(script=os.path.join(here, 'exec.R'),
train=dataset.train.path,
test=dataset.test.path,
output=config.output_predictions_file,
cores=config.cores))
log.info("Predictions saved to %s", config.output_predictions_file)
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(dataset: Dataset, config: TaskConfig):
log.info("\n**** AutoWEKA ****\n")
is_classification = config.type == 'classification'
if not is_classification:
raise ValueError('Regression is not supported.')
# Mapping of benchmark metrics to Weka metrics
metrics_mapping = dict(acc='errorRate',
auc='areaUnderROC',
logloss='kBInformation')
metric = metrics_mapping[
config.metric] if config.metric in metrics_mapping else None
if metric is None:
raise ValueError("Performance metric {} not supported.".format(
config.metric))
train_file = dataset.train.path
test_file = dataset.test.path
# Weka to requires target as the last attribute
if dataset.target.index != len(dataset.predictors):
train_file = reorder_dataset(dataset.train.path,
target_src=dataset.target.index)
test_file = reorder_dataset(dataset.test.path,
target_src=dataset.target.index)
training_params = {
k: v
for k, v in config.framework_params.items() if not k.startswith('_')
}
parallelRuns = config.framework_params.get('_parallelRuns', config.cores)
memLimit = config.framework_params.get('_memLimit', 'auto')
if memLimit == 'auto':
memLimit = max(
min(config.max_mem_size_mb,
math.ceil(config.max_mem_size_mb / parallelRuns)),
1024) # AutoWEKA default memLimit
log.info("Using %sMB memory per run on %s parallel runs.", memLimit,
parallelRuns)
f = split_path(config.output_predictions_file)
f.extension = '.weka_pred.csv'
weka_file = path_from_split(f)
cmd_root = "java -cp {here}/lib/autoweka/autoweka.jar weka.classifiers.meta.AutoWEKAClassifier ".format(
here=dir_of(__file__))
cmd_params = dict(
t='"{}"'.format(train_file),
T='"{}"'.format(test_file),
memLimit=memLimit,
classifications=
'"weka.classifiers.evaluation.output.prediction.CSV -distribution -file \\\"{}\\\""'
.format(weka_file),
timeLimit=int(config.max_runtime_seconds / 60),
parallelRuns=parallelRuns,
metric=metric,
seed=config.seed % (1 << 16), # weka accepts only int16 as seeds
**training_params)
cmd = cmd_root + ' '.join(
["-{} {}".format(k, v) for k, v in cmd_params.items()])
with Timer() as training:
run_cmd(cmd)
# if target values are not sorted alphabetically in the ARFF file, then class probabilities are returned in the original order
# interestingly, other frameworks seem to always sort the target values first
# that's why we need to specify the probabilities labels here: sorting+formatting is done in saving function
probabilities_labels = dataset.target.values
if not os.path.exists(weka_file):
raise NoResultError("AutoWEKA failed producing any prediction.")
with open(weka_file, 'r') as weka_file:
probabilities = []
predictions = []
truth = []
for line in weka_file.readlines()[1:-1]:
inst, actual, predicted, error, *distribution = line.split(',')
pred_probabilities = [
pred_probability.replace('*', '').replace('\n', '')
for pred_probability in distribution
]
_, pred = predicted.split(':')
_, tru = actual.split(':')
probabilities.append(pred_probabilities)
predictions.append(pred)
truth.append(tru)
save_predictions_to_file(dataset=dataset,
output_file=config.output_predictions_file,
probabilities=probabilities,
predictions=predictions,
truth=truth,
probabilities_labels=probabilities_labels)
return dict(training_duration=training.duration)
