def __init__(self,
n_estimators=10,
criterion='mse',
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
max_features='auto',
max_leaf_nodes=None,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
min_density=None,
compute_importances=None):
RandomForestRegressor.__init__(self,
n_estimators=n_estimators,
criterion=criterion,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
bootstrap=bootstrap,
compute_importances=compute_importances,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose)
def __init__(self,
n_estimators=10,
criterion="mse",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features="auto",
max_leaf_nodes=None,
min_impurity_decrease=0.,
min_impurity_split=None,
bootstrap=True,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
warm_start=False):
n_jobs = 4
n_estimators = int(n_estimators)
_RandomForestRegressor.__init__(
self, n_estimators, criterion, max_depth, min_samples_split,
min_samples_leaf, min_weight_fraction_leaf, max_features,
max_leaf_nodes, min_impurity_decrease, min_impurity_split,
bootstrap, oob_score, n_jobs, random_state, verbose, warm_start)
BaseWrapperReg.__init__(self)
def __init__(self,
n_estimators=10,
random_state=1,
X_train=None,
Y_train=None,
data=None):
"""[summary]
Args:
n_estimators (int, optional): Nombre d'arbres de décision. 10 par défaut.
random_state (int, optional): Seed de l'aléatoire. 1 par défaut.
X_train (df, optional): Données applaties en entrée.
Y_train (df, optional): Données de sortie.
data (df, optional): Données non applaties en entrée.
"""
RandomForestRegressor.__init__(self,
n_estimators=n_estimators,
random_state=random_state)
self.X_train = X_train
self.Y_train = Y_train
self.data = data
if not os.path.exists("./model"):
os.makedirs("./model")
def __init__(self, n_estimators=10, criterion='mse', max_depth=None, min_samples_split=2, min_samples_leaf=1, max_features='auto', max_leaf_nodes=None, bootstrap=True, oob_score=False, n_jobs=1, random_state=None, verbose=0, min_density=None, compute_importances=None): RandomForestRegressor.__init__(self, n_estimators=n_estimators, criterion=criterion, max_depth=max_depth, min_samples_split=min_samples_split, min_samples_leaf=min_samples_leaf, max_features=max_features, max_leaf_nodes= max_leaf_nodes, bootstrap= bootstrap, compute_importances=compute_importances, oob_score=oob_score, n_jobs=n_jobs, random_state=random_state, verbose=verbose)
def __init__(self, k=1000, var_threshold=0, **kwargs):
self.k = k
RandomForestRegressor.__init__(self, **kwargs)
self.filter = SelectKBest(score_func=f_regression, k=k)
self.var_threshold = var_threshold
def __init__(self, reserved_columns=[], **kwargs):
self.reserved_columns = reserved_columns
RandomForestRegressor.__init__(self, **kwargs)
self.feature_names = []
def __init__(self, pmml, n_jobs=None):
PMMLBaseRegressor.__init__(self, pmml)
mining_model = self.root.find('MiningModel')
if mining_model is None:
raise Exception('PMML model does not contain MiningModel.')
segmentation = mining_model.find('Segmentation')
if segmentation is None:
raise Exception('PMML model does not contain Segmentation.')
if segmentation.get('multipleModelMethod') not in [
'majorityVote', 'average'
]:
raise Exception(
'PMML model ensemble should use majority vote or average.')
# Parse segments
segments = segmentation.findall('Segment')
valid_segments = [
segment for segment in segments if segment.find('True') is not None
]
if len(valid_segments) < len(segments):
warnings.warn(
'Warning: {} segment(s) ignored because of unsupported predicate.'
.format(len(segments) - len(valid_segments)))
n_estimators = len(valid_segments)
self.n_outputs_ = 1
RandomForestRegressor.__init__(self,
n_estimators=n_estimators,
n_jobs=n_jobs)
self._validate_estimator()
clf = self._make_estimator(append=False, random_state=123)
try:
clf.n_features_in_ = self.n_features_in_
except AttributeError:
clf.n_features_ = self.n_features_
clf.n_outputs_ = self.n_outputs_
self.template_estimator = clf
self.estimators_ = [
get_tree(self, s, rescale_factor=0.1) for s in valid_segments
]
# Required after constructing trees, because categories may be inferred in
# the parsing process
target = self.target_field.get('name')
fields = [
field for name, field in self.fields.items() if name != target
]
for clf in self.estimators_:
n_categories = np.asarray([
len(self.field_mapping[field.get('name')][1].categories)
if field.get('optype') == 'categorical' else -1
for field in fields if field.tag == 'DataField'
],
dtype=np.int32,
order='C')
clf.n_categories = n_categories
clf.tree_.set_n_categories(n_categories)
self.categorical = [x != -1 for x in self.estimators_[0].n_categories]
def __init__(self, **kwargs):
RandomForestRegressor.__init__(self, **kwargs)
self.tree_means_per_leaf = []
self.tree_vars_per_leaf = []
def __init__(self):
RandomForestRegressor.__init__(self,
n_estimators=RandomForest.n_est,
warm_start=True)
OnlineScorer.__init__(self, batch_size=RandomForest.batch)
def __init__(self, *args, **kargs):
RandomForestRegressor.__init__(self, *args, **kargs)
self.weight = np.array([1]).astype(np.float32)
self.weight_gpu = cuda.mem_alloc(self.weight.nbytes)
train_data = munge_rest(train_df)
test_data = munge_rest(test_df)
#Delete revenue column from train data
x = np.delete(train_data, 37, 1)
#Define revenue as target variable
revenue = train_data[:, 37]
'''TRAINING'''
# Create the random forest object which will include all the parameters
# for the fit
forest = RandomForestRegressor(n_estimators=100,
max_depth=None,
max_features='sqrt',
min_samples_split=3)
forest.__init__(oob_score=True)
# Fit the training data to the revenue and create the decision trees
forest = forest.fit(x, train_data[0::, 37])
# Try the Ridge Regression model
clf = linear_model.Ridge(alpha=0.75,
fit_intercept=True,
normalize=True,
copy_X=True,
max_iter=1000,
tol=0.015)
#Fit the training data to the revenue and create the Ridge regression model
Ridge = clf.fit(x, train_data[0::, 37])
#prints the oob score -- I think
#print forest.score(train_data[0::,1::],train_data[0::,37])
