def set_default_params(self,
accuracy=10, time_tolerance=10, interpretability=1,
**kwargs):
# https://catboost.ai/docs/concepts/python-reference_parameters-list.html
# https://catboost.ai/docs/concepts/python-reference_catboostclassifier.html
# optimize for final model as transcribed from best lightgbm model
n_estimators = self.params_base.get('n_estimators', 100)
learning_rate = self.params_base.get('learning_rate', config.min_learning_rate)
early_stopping_rounds_default = min(500, max(1, int(n_estimators / 4)))
early_stopping_rounds = self.params_base.get('early_stopping_rounds', early_stopping_rounds_default)
self.params = {'bootstrap_type': 'Bayesian',
'n_estimators': n_estimators,
'learning_rate': learning_rate,
'early_stopping_rounds': early_stopping_rounds,
'max_depth': 8
}
dummy = kwargs.get('dummy', False)
ensemble_level = kwargs.get('ensemble_level', 0)
train_shape = kwargs.get('train_shape', (1, 1))
valid_shape = kwargs.get('valid_shape', (1, 1))
self.get_gbm_main_params_evolution(self.params, dummy, accuracy,
self.num_classes,
ensemble_level, train_shape,
valid_shape)
# self.params['has_time'] # should use this if TS problem
if self._can_handle_categorical:
# less than 2 is risky, can get stuck in learning
max_cat_to_onehot_list = [4, 10, 20, 40, config.max_int_as_cat_uniques]
self.params['one_hot_max_size'] = MainModel.get_one(max_cat_to_onehot_list, get_best=True)
uses_gpus, n_gpus = self.get_uses_gpus(self.params)
if uses_gpus:
self.params['one_hot_max_size'] = min(self.params['one_hot_max_size'], 255)
def mutate_params(self, **kwargs):
fake_lgbm_model = LightGBMModel(**self.input_dict)
fake_lgbm_model.params = self.params.copy()
fake_lgbm_model.params_base = self.params_base.copy()
fake_lgbm_model.params.update(fake_lgbm_model.params_base)
kwargs['train_shape'] = kwargs.get('train_shape', (10000, 500))
fake_lgbm_model.mutate_params(**kwargs)
self.params.update(fake_lgbm_model.params)
fake_lgbm_model.transcribe_params(params=self.params)
self.params.update(fake_lgbm_model.lightgbm_params)
# see what else can mutate, need to know things don't want to preserve
uses_gpus, n_gpus = self.get_uses_gpus(self.params)
if not uses_gpus:
self.params['colsample_bylevel'] = MainModel.get_one(
[0.3, 0.5, 0.9, 1.0])
if not (uses_gpus and self.num_classes > 2):
self.params['boosting_type'] = MainModel.get_one(
['Plain', 'Ordered'])
if self._can_handle_categorical:
max_cat_to_onehot_list = [
4, 10, 20, 40, config.max_int_as_cat_uniques
]
self.params['one_hot_max_size'] = MainModel.get_one(
max_cat_to_onehot_list)
if uses_gpus:
self.params['one_hot_max_size'] = min(
self.params['one_hot_max_size'], 255)
else:
self.params['one_hot_max_size'] = min(
self.params['one_hot_max_size'], 65535)
if not uses_gpus:
self.params['sampling_frequency'] = MainModel.get_one(
['PerTree', 'PerTreeLevel', 'PerTreeLevel', 'PerTreeLevel'])
bootstrap_type_list = [
'Bayesian', 'Bayesian', 'Bayesian', 'Bayesian', 'Bernoulli', 'MVS',
'Poisson', 'No'
]
if not uses_gpus:
bootstrap_type_list.remove('Poisson')
if uses_gpus:
bootstrap_type_list.remove('MVS') # undocumented CPU only
self.params['bootstrap_type'] = MainModel.get_one(bootstrap_type_list)
if self.params['bootstrap_type'] in ['Poisson', 'Bernoulli']:
self.params['subsample'] = MainModel.get_one(
[0.5, 0.66, 0.66,
0.9]) # will get pop'ed if not Poisson/Bernoulli
if self.params['bootstrap_type'] in ['Bayesian']:
self.params['bagging_temperature'] = MainModel.get_one(
[0, 0.1, 0.5, 0.9, 1.0])
def set_default_params(self,
accuracy=10,
time_tolerance=10,
interpretability=1,
**kwargs):
# https://catboost.ai/docs/concepts/python-reference_parameters-list.html
# https://catboost.ai/docs/concepts/python-reference_catboostclassifier.html
# optimize for final model as transcribed from best lightgbm model
n_estimators = self.params_base.get('n_estimators', 100)
learning_rate = self.params_base.get('learning_rate',
config.min_learning_rate)
early_stopping_rounds_default = min(500, max(1, int(n_estimators / 4)))
early_stopping_rounds = self.params_base.get(
'early_stopping_rounds', early_stopping_rounds_default)
self.params = {
'bootstrap_type': 'Bayesian',
'n_estimators': n_estimators,
'learning_rate': learning_rate,
'early_stopping_rounds': early_stopping_rounds,
'max_depth': 8,
'grow_policy': 'depthwise',
}
dummy = kwargs.get('dummy', False)
ensemble_level = kwargs.get('ensemble_level', 0)
train_shape = kwargs.get('train_shape', (1, 1))
valid_shape = kwargs.get('valid_shape', (1, 1))
self.get_gbm_main_params_evolution(params=self.params,
dummy=dummy,
accuracy=accuracy,
num_classes=self.num_classes,
ensemble_level=ensemble_level,
train_shape=train_shape,
valid_shape=valid_shape)
for k in kwargs:
if k in self.params:
self.params[k] = copy.deepcopy(kwargs[k])
# self.params['has_time'] # should use this if TS problem
if self._can_handle_categorical:
# less than 2 is risky, can get stuck in learning
max_cat_to_onehot_list = [
4, 10, 20, 40, config.max_int_as_cat_uniques
]
self.params['one_hot_max_size'] = MainModel.get_one(
max_cat_to_onehot_list, get_best=True)
uses_gpus, n_gpus = self.get_uses_gpus(self.params)
if uses_gpus:
self.params['one_hot_max_size'] = min(
self.params['one_hot_max_size'], 255)
else:
self.params['one_hot_max_size'] = min(
self.params['one_hot_max_size'], 65535)
self.params['learning_rate'] = max(self._min_learning_rate_catboost,
self.params['learning_rate'])
# fill mutatable params with best for left over if default didn't fill
params = copy.deepcopy(self.params)
self.mutate_params(accuracy=accuracy,
time_tolerance=time_tolerance,
interpretability=interpretability,
get_best=True,
**kwargs)
params_from_mutate = copy.deepcopy(self.params)
for k in params_from_mutate:
if k not in params:
params[k] = params_from_mutate[k]
self.params = copy.deepcopy(params)
def mutate_params(self, **kwargs):
fake_lgbm_model = LightGBMModel(**self.input_dict)
fake_lgbm_model.params = self.params.copy()
fake_lgbm_model.params_base = self.params_base.copy()
for k, v in fake_lgbm_model.params_base.items():
if k in fake_lgbm_model.params:
fake_lgbm_model.params[k] = fake_lgbm_model.params_base[k]
kwargs['train_shape'] = kwargs.get('train_shape', (10000, 500))
kwargs['from_catboost'] = True
fake_lgbm_model.mutate_params(**kwargs)
self.params.update(fake_lgbm_model.params)
fake_lgbm_model.transcribe_params(params=self.params, **kwargs)
self.params.update(fake_lgbm_model.lightgbm_params)
get_best = kwargs.get('get_best', True)
if get_best is None:
get_best = True
trial = kwargs.get('trial', False)
if trial is None:
trial = False
# see what else can mutate, need to know things don't want to preserve
uses_gpus, n_gpus = self.get_uses_gpus(self.params)
if not uses_gpus:
colsample_bylevel_list = [0.3, 0.5, 0.9, 1.0]
self.params['colsample_bylevel'] = MainModel.get_one(
colsample_bylevel_list,
get_best=get_best,
best_type="first",
name="colsample_bylevel",
trial=trial)
if not (uses_gpus and self.num_classes > 2):
boosting_type_list = ['Plain', 'Ordered']
self.params['boosting_type'] = MainModel.get_one(
boosting_type_list,
get_best=get_best,
best_type="first",
name="boosting_type",
trial=trial)
if self._can_handle_categorical:
max_cat_to_onehot_list = [
4, 10, 20, 40, config.max_int_as_cat_uniques
]
if uses_gpus:
max_one_hot_max_size = 255
else:
max_one_hot_max_size = 65535
max_cat_to_onehot_list = sorted(
set([
min(x, max_one_hot_max_size)
for x in max_cat_to_onehot_list
]))
log = True if max(max_cat_to_onehot_list) > 1000 else False
self.params['one_hot_max_size'] = MainModel.get_one(
max_cat_to_onehot_list,
get_best=get_best,
best_type="max",
name="one_hot_max_size",
trial=trial,
log=log)
if not uses_gpus:
sampling_frequency_list = [
'PerTree', 'PerTreeLevel', 'PerTreeLevel', 'PerTreeLevel'
]
self.params['sampling_frequency'] = MainModel.get_one(
sampling_frequency_list,
get_best=get_best,
best_type="first",
name="sampling_frequency",
trial=trial)
bootstrap_type_list = [
'Bayesian', 'Bayesian', 'Bayesian', 'Bayesian', 'Bernoulli', 'MVS',
'Poisson', 'No'
]
if not uses_gpus:
bootstrap_type_list.remove('Poisson')
if uses_gpus:
bootstrap_type_list.remove('MVS') # undocumented CPU only
self.params['bootstrap_type'] = MainModel.get_one(
bootstrap_type_list,
get_best=get_best,
best_type="first",
name="bootstrap_type",
trial=trial)
# lgbm usage already sets subsample
#if self.params['bootstrap_type'] in ['Poisson', 'Bernoulli']:
# subsample_list = [0.5, 0.66, 0.66, 0.9]
# # will get pop'ed if not Poisson/Bernoulli
# self.params['subsample'] = MainModel.get_one(subsample_list, get_best=get_best, best_type="first", name="subsample", trial=trial)
if self.params['bootstrap_type'] in ['Bayesian']:
bagging_temperature_list = [0.0, 0.1, 0.5, 0.9, 1.0]
self.params['bagging_temperature'] = MainModel.get_one(
bagging_temperature_list,
get_best=get_best,
best_type="first",
name="bagging_temperature",
trial=trial)
# overfit protection different sometimes compared to early_stopping_rounds
# self.params['od_type']
# self.params['od_pval']
# self.params['od_wait']
self.params['learning_rate'] = max(
config.min_learning_rate,
max(self._min_learning_rate_catboost,
self.params['learning_rate']))