def get_automl_object(ml_algo):
"""
returns a ml model which can be trained
:param ml_algo: string which model schoulkd be returned
:return:
"""
cls = ""
if ml_algo == "SGDRegressor":
cls = sklearn.linear_model.SGDRegressor()
return cls
if ml_algo == "PassiveAggressiveRegressor":
cls = sklearn.linear_model.PassiveAggressiveRegressor()
return cls
if ml_algo == "KNeighborsRegressor":
cls = KNeighborsRegressor()
return cls
if ml_algo == "LinearRegression":
cls = sklearn.linear_model.LinearRegression()
return cls
if ml_algo == "RandomForestRegressor":
cls = RandomForestRegressor()
return cls
if ml_algo == "DecisionTreeRegressor":
cls = DecisionTreeRegressor()
return cls
if ml_algo == "ExtraTreeRegressor":
cls = ExtraTreeRegressor()
return cls
if ml_algo == "MLPRegressor":
cls = MLPRegressor(verbose=True)
return cls
if ml_algo == "SVR":
cls = SVR()
return cls
if ml_algo == "tpot":
cls = TPOTRegressor(generations = 1, population_size=1, verbosity=2, scoring="neg_mean_absolute_error",n_jobs=4)
return cls
if ml_algo == "sklearn":
runtime_seconds = 60
per_task = 60
mem_limit = 8000
#seconmds
#cls = regression.AutoSklearnRegressor(include_estimators=["random_forest" , "decision_tree" , "extra_trees" ], time_left_for_this_task=60)
cls = regression.AutoSklearnRegressor(#time_left_for_this_task=runtime_seconds,
#per_run_time_limit = per_task,
n_jobs=4,
ensemble_nbest=5,
ml_memory_limit=mem_limit
#include_estimators = ["sgd"]
)
# include_estimators = ["decision_tree"]
# )
return cls
def auto_sklearn(self, time=60, estimators=None, resampling_strategy='cv'):
if self.model is None:
self.model = asc.AutoSklearnRegressor(
time_left_for_this_task=time + 10,
per_run_time_limit=time,
initial_configurations_via_metalearning=0,
include_estimators=estimators,
resampling_strategy=resampling_strategy,
resampling_strategy_arguments={'folds': 5})
self.model.fit(self.df_train.copy(), self.label.copy())
if resampling_strategy == 'cv':
self.model.refit(self.df_train.copy(), self.label.copy())
#
elif alg.name == 'TPOT_Regressor':
from tpot import TPOTRegressor
model = TPOTRegressor(
generations=alg.generations,
cv=alg.cv,
scoring=alg.scoring,
verbosity=alg.verbosity
)
warn_not_gpu_support(alg)
elif alg.name == 'AutoSklearn_Regressor':
from autosklearn import regression
if alg.sampling:
model = regression.AutoSklearnRegressor(
time_left_for_this_task=alg.task_time,
per_run_time_limit=alg.run_time,
resampling_strategy=alg.sampling_strategy,
resampling_strategy_arguments={'folds': alg.folds}
)
else:
model = regression.AutoSklearnRegressor(
time_left_for_this_task=alg.task_time,
per_run_time_limit=alg.run_time
)
warn_not_gpu_support(alg)
elif alg.name == 'LinearRegression':
if NVIDIA_RAPIDS_ENABLED:
from cuml.linear_model import LinearRegression
model = LinearRegression(**alg.input_variables.__dict__)
else:
from sklearn.linear_model import LinearRegression
model = LinearRegression(**alg.input_variables.__dict__)
elif alg.name == 'TPOT_Regressor':
from tpot import TPOTRegressor
model = TPOTRegressor(
generations=alg.generations,
cv=alg.cv,
scoring=alg.scoring,
verbosity=alg.verbosity
)
elif alg.name == 'AutoSklearn_Regressor':
from autosklearn import regression
print("alg.sampling",alg.sampling_strategy)
if alg.sampling.lower()=='true':
model = regression.AutoSklearnRegressor(
time_left_for_this_task=alg.task_time,
per_run_time_limit=alg.run_time,
resampling_strategy= "".join(alg.sampling_strategy),
resampling_strategy_arguments={'folds':int(alg.folds)}
#feat_type = {Numerical,Numerical,Numerical,Numerical,Categorical}
)
else:
model = regression.AutoSklearnRegressor(
time_left_for_this_task=alg.task_time,
per_run_time_limit=alg.run_time
)
elif alg.name == 'LinearRegression':
from sklearn.linear_model import LinearRegression
model = LinearRegression(**vars)
elif alg.name == 'SupportVectorRegression':
from sklearn.svm import SVR
model = SVR(**vars)
elif alg.name == 'BayesianRidgeRegression':