def sklearn_main(config,
ClassifierClass,
clf_name,
train_mode,
normalize=False):
model_params = getattr(config, clf_name)
random_search_config = getattr(config.random_search, clf_name)
full_config = (config, model_params, random_search_config)
if train_mode:
features, features_valid = feature_extraction(
config,
train_mode,
persist_output=True,
cache_output=True,
load_persisted_output=True)
sklearn_preproc = preprocessing_fillna((features, features_valid),
config, train_mode)
else:
features = feature_extraction(config, train_mode, cache_output=True)
sklearn_preproc = preprocessing_fillna(features, config, train_mode)
sklearn_clf = classifier_sklearn(sklearn_preproc, ClassifierClass,
full_config, clf_name, train_mode,
normalize)
clipper = Step(name='clipper',
transformer=Clipper(**config.clipper),
input_steps=[sklearn_clf],
adapter=Adapter(
{'prediction': E(sklearn_clf.name, 'predicted')}),
experiment_directory=config.pipeline.experiment_directory)
return clipper
def solution_1(config, train_mode):
if train_mode:
features, features_valid = feature_extraction(config,
train_mode,
save_output=True,
cache_output=True,
load_saved_output=True)
light_gbm = classifier_lgbm((features, features_valid), config,
train_mode)
else:
features = feature_extraction(config, train_mode, cache_output=True)
light_gbm = classifier_lgbm(features, config, train_mode)
clipper = Step(name='clipper',
transformer=Clipper(**config.clipper),
input_steps=[light_gbm],
adapter={
'prediction': ([(light_gbm.name, 'prediction')]),
},
cache_dirpath=config.env.cache_dirpath)
output = Step(name='output',
transformer=Dummy(),
input_steps=[clipper],
adapter={
'y_pred': ([(clipper.name, 'clipped_prediction')]),
},
cache_dirpath=config.env.cache_dirpath)
return output
def main(config, train_mode):
if train_mode:
features, features_valid = feature_extraction(config, train_mode,
save_output=True, cache_output=True, load_saved_output=True)
light_gbm = classifier_lgbm((features, features_valid), config, train_mode)
else:
features = feature_extraction(config, train_mode, cache_output=True)
light_gbm = classifier_lgbm(features, config, train_mode)
clipper = Step(name='clipper',
transformer=Clipper(**config.clipper),
input_steps=[light_gbm],
adapter=Adapter({'prediction': E(light_gbm.name, 'prediction')}),
cache_dirpath=config.env.cache_dirpath)
return clipper
def xgboost(config, train_mode):
if train_mode:
features, features_valid = feature_extraction(
config,
train_mode,
persist_output=True,
cache_output=True,
load_persisted_output=True)
xgb = classifier_xgb((features, features_valid), config, train_mode)
else:
features = feature_extraction(config, train_mode, cache_output=True)
xgb = classifier_xgb(features, config, train_mode)
clipper = Step(name='clipper',
transformer=Clipper(**config.clipper),
input_steps=[xgb],
adapter=Adapter({'prediction': E(xgb.name, 'prediction')}),
experiment_directory=config.pipeline.experiment_directory)
return clipper