def test_drf_classifier_backupsklearn(backend='auto'):
df = pd.read_csv("./open_data/creditcard.csv")
X = np.array(df.iloc[:, :df.shape[1] - 1], dtype='float32', order='C')
y = np.array(df.iloc[:, df.shape[1] - 1], dtype='float32', order='C')
import h2o4gpu
Solver = h2o4gpu.RandomForestClassifier
#Run h2o4gpu version of RandomForest Regression
drf = Solver(backend=backend, random_state=1234, oob_score=True, n_estimators=10, n_gpus=n_gpus())
print("h2o4gpu fit()")
drf.fit(X, y)
#Run Sklearn version of RandomForest Regression
from h2o4gpu.ensemble import RandomForestClassifierSklearn
drf_sk = RandomForestClassifierSklearn(random_state=1234, oob_score=True, max_depth=3, n_estimators=10)
print("Scikit fit()")
drf_sk.fit(X, y)
if backend == "sklearn":
assert (drf.predict(X) == drf_sk.predict(X)).all() == True
assert (drf.predict_log_proba(X) == drf_sk.predict_log_proba(X)).all() == True
assert (drf.predict_proba(X) == drf_sk.predict_proba(X)).all() == True
assert (drf.score(X, y) == drf_sk.score(X, y)).all() == True
assert (drf.decision_path(X)[1] == drf_sk.decision_path(X)[1]).all() == True
assert (drf.apply(X) == drf_sk.apply(X)).all() == True
print("Estimators")
print(drf.estimators_)
print(drf_sk.estimators_)
print("n_features")
print(drf.n_features_)
print(drf_sk.n_features_)
assert drf.n_features_ == drf_sk.n_features_
print("n_classes_")
print(drf.n_classes_)
print(drf_sk.n_classes_)
assert drf.n_classes_ == drf_sk.n_classes_
print("n_features")
print(drf.classes_)
print(drf_sk.classes_)
assert (drf.classes_ == drf_sk.classes_).all() == True
print("n_outputs")
print(drf.n_outputs_)
print(drf_sk.n_outputs_)
assert drf.n_outputs_ == drf_sk.n_outputs_
print("Feature importance")
print(drf.feature_importances_)
print(drf_sk.feature_importances_)
assert (drf.feature_importances_ == drf_sk.feature_importances_).all() == True
print("oob_score")
print(drf.oob_score_)
print(drf_sk.oob_score_)
assert drf.oob_score_ == drf_sk.oob_score_
class RandomForestClassifier(object):
"""H2O RandomForestClassifier Solver
Selects between h2o4gpu.solvers.xgboost.RandomForestClassifier
and h2o4gpu.ensemble.forest.RandomForestClassifierSklearn
Documentation:
import h2o4gpu.solvers ; help(h2o4gpu.xgboost.RandomForestClassifierO)
help(h2o4gpu.ensemble.forest.RandomForestClassifierSklearn)
:param: backend : Which backend to use. Options are 'auto', 'sklearn',
'h2o4gpu'. Default is 'auto'.
Saves as attribute for actual backend used.
"""
def __init__(
self,
n_estimators=10, # h2o4gpu
criterion='gini',
max_depth=3, # h2o4gpu
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
bootstrap=True,
oob_score=False,
n_jobs=1, # h2o4gpu
random_state=None, # h2o4gpu
verbose=0, # h2o4gpu
warm_start=False,
class_weight=None,
# XGBoost specific params
subsample=1.0, # h2o4gpu
colsample_bytree=1.0, # h2o4gpu
num_parallel_tree=100, # h2o4gpu
tree_method='gpu_hist', # h2o4gpu
n_gpus=-1, # h2o4gpu
predictor='gpu_predictor', # h2o4gpu
backend='auto'): # h2o4gpu
import os
_backend = os.environ.get('H2O4GPU_BACKEND', None)
if _backend is not None:
backend = _backend
from ..typecheck.typechecks import assert_is_type
assert_is_type(backend, str)
# Fall back to Sklearn
# Can remove if fully implement sklearn functionality
self.do_sklearn = False
if backend == 'auto':
params_string = [
'criterion', 'min_samples_split', 'min_samples_leaf',
'min_weight_fraction_leaf', 'max_features', 'max_leaf_nodes',
'min_impurity_decrease', 'min_impurity_split', 'bootstrap',
'oob_score', 'class_weight'
]
params = [
criterion, min_samples_split, min_samples_leaf,
min_weight_fraction_leaf, max_features, max_leaf_nodes,
min_impurity_decrease, min_impurity_split, bootstrap,
oob_score, class_weight
]
params_default = [
'gini', 2, 1, 0.0, 'auto', None, 0.0, None, True, False, None
]
i = 0
for param in params:
if param != params_default[i]:
self.do_sklearn = True
if verbose > 0:
print("WARNING: The sklearn parameter " +
params_string[i] +
" has been changed from default to " +
str(param) +
". Will run Sklearn RandomForestsClassifier.")
self.do_sklearn = True
i = i + 1
elif backend == 'sklearn':
self.do_sklearn = True
elif backend == 'h2o4gpu':
self.do_sklearn = False
self.backend = backend
from h2o4gpu.ensemble import RandomForestClassifierSklearn
self.model_sklearn = RandomForestClassifierSklearn(
n_estimators=n_estimators,
criterion=criterion,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
min_impurity_decrease=min_impurity_decrease,
min_impurity_split=min_impurity_split,
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight)
# Parameters for random forest
silent = False
if verbose != 0:
silent = True
if random_state is None:
random_state = 0
import xgboost as xgb
self.model_h2o4gpu = xgb.XGBClassifier(
n_estimators=n_estimators, # h2o4gpu
max_depth=max_depth, # h2o4gpu
n_jobs=n_jobs, # h2o4gpu
random_state=random_state, # h2o4gpu
num_parallel_tree=num_parallel_tree,
tree_method=tree_method,
n_gpus=n_gpus,
predictor=predictor,
silent=silent,
num_round=1,
subsample=subsample,
colsample_bytree=colsample_bytree)
if self.do_sklearn:
print("Running sklearn RandomForestClassifier")
self.model = self.model_sklearn
else:
print("Running h2o4gpu RandomForestClassifier")
self.model = self.model_h2o4gpu
def apply(self, X):
print("WARNING: apply() is using sklearn")
return self.model_sklearn.apply(X)
def decision_path(self, X):
print("WARNING: decision_path() is using sklearn")
return self.model_sklearn.decision_path(X)
def fit(self, X, y=None, sample_weight=None):
res = self.model.fit(X, y, sample_weight)
self.set_attributes()
return res
def get_params(self):
return self.model.get_params()
def predict(self, X):
if self.do_sklearn:
res = self.model.predict(X)
self.set_attributes()
return res
res = self.model.predict(X)
res[res < 0.5] = 0
res[res > 0.5] = 1
self.set_attributes()
return res.squeeze()
def predict_log_proba(self, X):
res = self.predict_proba(X)
self.set_attributes()
import numpy as np
return np.log(res)
def predict_proba(self, X):
if self.do_sklearn:
res = self.model.predict_proba(X)
self.set_attributes()
return res
res = self.model.predict(X)
self.set_attributes()
return res
def score(self, X, y, sample_weight=None):
# TODO add for h2o4gpu
print("WARNING: score() is using sklearn")
if not self.do_sklearn:
self.model_sklearn.fit(X, y) # Need to re-fit
res = self.model_sklearn.score(X, y, sample_weight)
return res
def set_params(self, **params):
return self.model.set_params(**params)
def set_attributes(self):
""" Set attributes for class"""
from ..solvers.utils import _setter
s = _setter(oself=self, e1=NameError, e2=AttributeError)
s('oself.estimators_ = oself.model.estimators_')
s('oself.classes_ = oself.model.classes_')
s('oself.n_classes_ = oself.model.n_classes_')
s('oself.n_features_ = oself.model.n_features_')
s('oself.n_outputs_ = oself.model.n_outputs_')
s('oself.feature_importances_ = oself.model.feature_importances_')
s('oself.oob_score_ = oself.model.oob_score_')
s('oself.oob_decision_function_ = oself.model.oob_decision_function_')
class RandomForestClassifier(object):
"""H2O RandomForestClassifier Solver
Selects between h2o4gpu.solvers.xgboost.RandomForestClassifier
and h2o4gpu.ensemble.forest.RandomForestClassifierSklearn
Documentation:
import h2o4gpu.solvers ; help(h2o4gpu.xgboost.RandomForestClassifierO)
help(h2o4gpu.ensemble.forest.RandomForestClassifierSklearn)
:param: backend : Which backend to use. Options are 'auto', 'sklearn',
'h2o4gpu'. Default is 'auto'.
Saves as attribute for actual backend used.
"""
def __init__(
self,
n_estimators=10, # h2o4gpu
criterion='gini',
max_depth=3, # h2o4gpu
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features='auto',
max_leaf_nodes=None,
min_impurity_decrease=0.0,
min_impurity_split=None,
bootstrap=True,
oob_score=False,
n_jobs=1, # h2o4gpu
random_state=None, # h2o4gpu
verbose=0, # h2o4gpu
warm_start=False,
class_weight=None,
# XGBoost specific params
subsample=1.0, # h2o4gpu
colsample_bytree=1.0, # h2o4gpu
num_parallel_tree=100, # h2o4gpu
tree_method='gpu_hist', # h2o4gpu
n_gpus=-1, # h2o4gpu
predictor='gpu_predictor', # h2o4gpu
backend='auto'): # h2o4gpu
import os
_backend = os.environ.get('H2O4GPU_BACKEND', None)
if _backend is not None:
backend = _backend
from ..typecheck.typechecks import assert_is_type
assert_is_type(backend, str)
# Fall back to Sklearn
# Can remove if fully implement sklearn functionality
self.do_sklearn = False
if backend == 'auto':
params_string = [
'criterion', 'min_samples_split', 'min_samples_leaf',
'min_weight_fraction_leaf', 'max_features', 'max_leaf_nodes',
'min_impurity_decrease', 'min_impurity_split', 'bootstrap',
'oob_score', 'class_weight'
]
params = [
criterion, min_samples_split, min_samples_leaf,
min_weight_fraction_leaf, max_features, max_leaf_nodes,
min_impurity_decrease, min_impurity_split, bootstrap, oob_score,
class_weight
]
params_default = [
'gini', 2, 1, 0.0, 'auto', None, 0.0, None, True, False, None
]
i = 0
for param in params:
if param != params_default[i]:
self.do_sklearn = True
if verbose > 0:
print("WARNING: The sklearn parameter " +
params_string[i] +
" has been changed from default to " + str(param)
+ ". Will run Sklearn RandomForestsClassifier.")
self.do_sklearn = True
i = i + 1
elif backend == 'sklearn':
self.do_sklearn = True
elif backend == 'h2o4gpu':
self.do_sklearn = False
self.backend = backend
from h2o4gpu.ensemble import RandomForestClassifierSklearn
self.model_sklearn = RandomForestClassifierSklearn(
n_estimators=n_estimators,
criterion=criterion,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
min_impurity_decrease=min_impurity_decrease,
min_impurity_split=min_impurity_split,
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight)
# Parameters for random forest
silent = False
if verbose != 0:
silent = True
if random_state is None:
random_state = 0
import xgboost as xgb
self.model_h2o4gpu = xgb.XGBClassifier(
n_estimators=n_estimators, # h2o4gpu
max_depth=max_depth, # h2o4gpu
n_jobs=n_jobs, # h2o4gpu
random_state=random_state, # h2o4gpu
num_parallel_tree=num_parallel_tree,
tree_method=tree_method,
n_gpus=n_gpus,
predictor=predictor,
silent=silent,
num_round=1,
subsample=subsample,
colsample_bytree=colsample_bytree)
if self.do_sklearn:
print("Running sklearn RandomForestClassifier")
self.model = self.model_sklearn
else:
print("Running h2o4gpu RandomForestClassifier")
self.model = self.model_h2o4gpu
def apply(self, X):
print("WARNING: apply() is using sklearn")
return self.model_sklearn.apply(X)
def decision_path(self, X):
print("WARNING: decision_path() is using sklearn")
return self.model_sklearn.decision_path(X)
def fit(self, X, y=None, sample_weight=None):
res = self.model.fit(X, y, sample_weight)
self.set_attributes()
return res
def get_params(self):
return self.model.get_params()
def predict(self, X):
if self.do_sklearn:
res = self.model.predict(X)
self.set_attributes()
return res
res = self.model.predict(X)
res[res < 0.5] = 0
res[res > 0.5] = 1
self.set_attributes()
return res.squeeze()
def predict_log_proba(self, X):
res = self.predict_proba(X)
self.set_attributes()
import numpy as np
return np.log(res)
def predict_proba(self, X):
if self.do_sklearn:
res = self.model.predict_proba(X)
self.set_attributes()
return res
res = self.model.predict(X)
self.set_attributes()
return res
def score(self, X, y, sample_weight=None):
# TODO add for h2o4gpu
print("WARNING: score() is using sklearn")
if not self.do_sklearn:
self.model_sklearn.fit(X, y) # Need to re-fit
res = self.model_sklearn.score(X, y, sample_weight)
return res
def set_params(self, **params):
return self.model.set_params(**params)
def set_attributes(self):
""" Set attributes for class"""
from ..solvers.utils import _setter
s = _setter(oself=self, e1=NameError, e2=AttributeError)
s('oself.estimators_ = oself.model.estimators_')
s('oself.classes_ = oself.model.classes_')
s('oself.n_classes_ = oself.model.n_classes_')
s('oself.n_features_ = oself.model.n_features_')
s('oself.n_outputs_ = oself.model.n_outputs_')
s('oself.feature_importances_ = oself.model.feature_importances_')
s('oself.oob_score_ = oself.model.oob_score_')
s('oself.oob_decision_function_ = oself.model.oob_decision_function_')