async def random_search_worker(get_model, model_type, features, label,
configuration, output, parallel, fast):
log("Random search starting", level=1)
# noinspection PyBroadException
try:
timer = Timer()
X, y, classifier = make_model(get_model, features, label,
configuration['pipeline'],
configuration['reduce_classes'])
results: ModelCVResult = cross_validate_model_cached(X,
y,
classifier,
parallel=parallel,
fast=fast,
n_jobs=5)
result_for_comparison, y_for_comparison = get_result_for_comparison(
configuration['reduce_classes'], results, y, label)
tab_data_output, records_output = output_all(result_for_comparison,
y_for_comparison)
event_data = optimization_configuration_ready(
results=tab_data_output,
records=records_output,
parameters=configuration,
features=features,
model_type=model_type,
label=label,
elapsed=timer.elapsed_cpu())
identifier = (
hash_features(features),
label,
model_type,
)
append_data(identifier, event_data['payload'])
await output(event_data)
log("Optimization iteration finished`")
except Exception as e:
warning(e)
raise e
def cross_validate_model_fold(chunk_input: WorkerInput) -> ModelResult:
log("Execution fold", level=2)
timer = Timer()
classifier = chunk_input['classifier']
X_train = chunk_input['X_train']
y_train = chunk_input['y_train']
X_test = chunk_input['X_test']
return_model = chunk_input['return_model']
if get_log_level() == 1:
print(".")
feature_names = \
chunk_input['feature_names'] if \
('feature_names' in chunk_input and chunk_input['feature_names'] is not None) \
else list(X_train.columns)
classifier.fit(X_train, y_train, **chunk_input['fit_kwargs'])
y_predict = Series(classifier.predict(X_test), index=X_test.index)
y_train_predict = Series(classifier.predict(X_train), index=X_train.index)
try:
y_predict_probabilities_raw = classifier.predict_proba(X_test)
y_train_predict_probabilities_raw = classifier.predict_proba(X_train)
except AttributeError:
y_predict_probabilities = y_predict
y_train_predict_probabilities = y_train_predict
else:
probability_columns = [
f'y_predict_probabilities_{i}'
for i in range(y_predict_probabilities_raw.shape[1])
]
y_predict_probabilities = DataFrame(y_predict_probabilities_raw,
index=X_test.index,
columns=probability_columns)
y_train_predict_probabilities = DataFrame(
y_train_predict_probabilities_raw,
index=X_train.index,
columns=probability_columns)
if y_predict.dtype == np.float:
y_predict = y_predict \
.map(lambda v: 0 if v < 0 else v) \
.map(lambda v: 1 if v > 1 else v) \
.map(lambda v: round(v))
try:
feature_importance = Series(
classifier[-1].feature_importances_,
index=feature_names,
)
except (TypeError, AttributeError):
try:
classifier[-1].coef_
except AttributeError:
feature_importance = None
logging.debug("No feature importance in the result")
else:
feature_importance = None
# feature_importance = Series(classifier[-1].coef_[0], index=feature_names)
if not return_model:
try:
classifier[-1].get_booster().__del__()
except AttributeError:
pass
return ModelResult(y_test_score=y_predict_probabilities,
y_test_predict=y_predict,
y_train_predict=y_train_predict,
y_train_score=y_train_predict_probabilities,
feature_importance=feature_importance,
model=classifier[-1] if return_model else None,
elapsed=timer.elapsed_cpu())
