def fit(self, X, y, sample_weight=None):
from sklearn.tree import DecisionTreeClassifier
self.max_features = float(self.max_features)
# Heuristic to set the tree depth
if check_none(self.max_depth_factor):
max_depth_factor = self.max_depth_factor = None
else:
num_features = X.shape[1]
self.max_depth_factor = int(self.max_depth_factor)
max_depth_factor = max(
1,
int(np.round(self.max_depth_factor * num_features, 0)))
self.min_samples_split = int(self.min_samples_split)
self.min_samples_leaf = int(self.min_samples_leaf)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_weight_fraction_leaf = float(self.min_weight_fraction_leaf)
self.min_impurity_decrease = float(self.min_impurity_decrease)
self.estimator = DecisionTreeClassifier(
criterion=self.criterion,
max_depth=max_depth_factor,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
max_leaf_nodes=self.max_leaf_nodes,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
min_impurity_decrease=self.min_impurity_decrease,
class_weight=self.class_weight,
random_state=self.random_state)
self.estimator.fit(X, y, sample_weight=sample_weight)
return self
def iterative_fit(self, X, y, sample_weight=None, n_iter=1, refit=False):
from sklearn.ensemble.gradient_boosting import GradientBoostingRegressor as GBR
# Special fix for gradient boosting!
if isinstance(X, np.ndarray):
X = np.ascontiguousarray(X, dtype=X.dtype)
if refit:
self.estimator = None
if self.estimator is None:
self.learning_rate = float(self.learning_rate)
self.n_estimators = int(self.n_estimators)
self.subsample = float(self.subsample)
self.min_samples_split = int(self.min_samples_split)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_weight_fraction_leaf = float(
self.min_weight_fraction_leaf)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
self.max_features = float(self.max_features)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_impurity_decrease = float(self.min_impurity_decrease)
self.verbose = int(self.verbose)
self.estimator = GBR(
loss=self.loss,
learning_rate=self.learning_rate,
n_estimators=n_iter,
subsample=self.subsample,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
max_depth=self.max_depth,
criterion=self.criterion,
max_features=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
random_state=self.random_state,
verbose=self.verbose,
warm_start=True,
)
else:
self.estimator.n_estimators += n_iter
self.estimator.n_estimators = min(self.estimator.n_estimators,
self.n_estimators)
self.estimator.fit(X, y, sample_weight=sample_weight)
# Apparently this if is necessary
if self.estimator.n_estimators >= self.n_estimators:
self.fully_fit_ = True
return self
def iterative_fit(self, X, y, sample_weight=None, n_iter=1, refit=False):
from sklearn.ensemble import RandomForestClassifier
if refit:
self.estimator = None
if self.estimator is None:
self.n_estimators = int(self.n_estimators)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
self.min_samples_split = int(self.min_samples_split)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_weight_fraction_leaf = float(
self.min_weight_fraction_leaf)
if self.max_features not in ("sqrt", "log2", "auto"):
max_features = int(X.shape[1]**float(self.max_features))
else:
max_features = self.max_features
self.bootstrap = check_for_bool(self.bootstrap)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_impurity_decrease = float(self.min_impurity_decrease)
# initial fit of only increment trees
self.estimator = RandomForestClassifier(
n_estimators=n_iter,
criterion=self.criterion,
max_features=max_features,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
bootstrap=self.bootstrap,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
random_state=self.random_state,
n_jobs=self.n_jobs,
class_weight=self.class_weight,
warm_start=True)
else:
self.estimator.n_estimators += n_iter
self.estimator.n_estimators = min(self.estimator.n_estimators,
self.n_estimators)
self.estimator.fit(X, y, sample_weight=sample_weight)
return self
def operate(self, input_datanode: DataNode, target_fields=None):
from sklearn.ensemble import RandomTreesEmbedding
X, y = input_datanode.data
if target_fields is None:
target_fields = collect_fields(input_datanode.feature_types,
self.input_type)
X_new = X[:, target_fields]
if not self.model:
self.n_estimators = int(self.n_estimators)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
# Skip heavy computation. max depth is set to 6.
if X.shape[0] > 5000:
self.max_depth = min(6, self.max_depth)
self.min_samples_split = int(self.min_samples_split)
self.min_samples_leaf = int(self.min_samples_leaf)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_weight_fraction_leaf = float(
self.min_weight_fraction_leaf)
self.bootstrap = check_for_bool(self.bootstrap)
self.model = RandomTreesEmbedding(
n_estimators=self.n_estimators,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
max_leaf_nodes=self.max_leaf_nodes,
sparse_output=self.sparse_output,
n_jobs=self.n_jobs,
random_state=self.random_state)
self.model.fit(X_new)
_X = self.model.transform(X_new).toarray()
return _X
def __init__(self,
criterion,
min_samples_leaf,
min_samples_split,
max_features,
bootstrap,
max_leaf_nodes,
max_depth,
min_weight_fraction_leaf,
min_impurity_decrease,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0,
class_weight=None):
self.n_estimators = self.get_max_iter()
if criterion not in ("gini", "entropy"):
raise ValueError("'criterion' is not in ('gini', 'entropy'): "
"%s" % criterion)
self.criterion = criterion
if check_none(max_depth):
self.max_depth = None
else:
self.max_depth = int(max_depth)
if check_none(max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(max_leaf_nodes)
self.min_samples_leaf = int(min_samples_leaf)
self.min_samples_split = int(min_samples_split)
self.max_features = float(max_features)
self.bootstrap = check_for_bool(bootstrap)
self.min_weight_fraction_leaf = float(min_weight_fraction_leaf)
self.min_impurity_decrease = float(min_impurity_decrease)
self.oob_score = oob_score
self.n_jobs = int(n_jobs)
self.random_state = random_state
self.verbose = int(verbose)
self.class_weight = class_weight
self.estimator = None
def __init__(self,
criterion,
min_samples_leaf,
min_samples_split,
max_features,
bootstrap,
max_leaf_nodes,
max_depth,
min_weight_fraction_leaf,
min_impurity_decrease,
oob_score=False,
n_jobs=1,
random_state=None,
verbose=0):
self.n_estimators = self.get_max_iter()
self.criterion = criterion
if check_none(max_depth):
self.max_depth = None
else:
self.max_depth = int(max_depth)
if check_none(max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(max_leaf_nodes)
self.min_samples_leaf = int(min_samples_leaf)
self.min_samples_split = int(min_samples_split)
self.max_features = float(max_features)
self.bootstrap = check_for_bool(bootstrap)
self.min_weight_fraction_leaf = float(min_weight_fraction_leaf)
self.min_impurity_decrease = float(min_impurity_decrease)
self.oob_score = oob_score
self.n_jobs = int(n_jobs)
self.random_state = random_state
self.verbose = int(verbose)
self.estimator = None
def fit(self, X, Y):
import sklearn.svm
# Nested kernel
if isinstance(self.kernel, tuple):
nested_kernel = self.kernel
self.kernel = nested_kernel[0]
if self.kernel == 'poly':
self.degree = nested_kernel[1]['degree']
self.coef0 = nested_kernel[1]['coef0']
elif self.kernel == 'sigmoid':
self.coef0 = nested_kernel[1]['coef0']
self.C = float(self.C)
if self.degree is None:
self.degree = 3
else:
self.degree = int(self.degree)
if self.gamma is None:
self.gamma = 0.0
else:
self.gamma = float(self.gamma)
if self.coef0 is None:
self.coef0 = 0.0
else:
self.coef0 = float(self.coef0)
self.tol = float(self.tol)
self.max_iter = float(self.max_iter)
self.shrinking = check_for_bool(self.shrinking)
if check_none(self.class_weight):
self.class_weight = None
self.estimator = sklearn.svm.SVC(C=self.C,
kernel=self.kernel,
degree=self.degree,
gamma=self.gamma,
coef0=self.coef0,
shrinking=self.shrinking,
tol=self.tol,
class_weight=self.class_weight,
max_iter=self.max_iter,
random_state=self.random_state,
decision_function_shape='ovr')
self.estimator.fit(X, Y)
return self
def operate(self, input_datanode, target_fields=None):
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
X, y = input_datanode.data
if self.model is None:
if check_none(self.shrinkage):
self.shrinkage = None
self.model = LinearDiscriminantAnalysis(
n_components=self.n_components,
shrinkage=self.shrinkage
)
self.model.fit(X, y)
X_new = self.model.transform(X)
return X_new
def operate(self, input_datanode, target_fields=None):
X, y = input_datanode.data
# Skip heavy computation in fast ica.
if X.shape[0] > 10000 or X.shape[1] > 200:
if not self.pre_trained:
pass
# self.skip_flag = True
self.pre_trained = True
if self.skip_flag:
return X.copy()
if self.model is None:
from sklearn.decomposition import FastICA
self.whiten = check_for_bool(self.whiten)
if check_none(self.n_components):
self.n_components = None
else:
self.n_components = int(self.n_components)
if self.n_components is not None:
self.n_components = min(self.n_components, X.shape[0])
self.model = FastICA(n_components=self.n_components,
algorithm=self.algorithm,
fun=self.fun,
whiten=self.whiten,
random_state=self.random_state)
# Make the RuntimeWarning an Exception!
with warnings.catch_warnings():
warnings.filterwarnings(
"error", message='array must not contain infs or NaNs')
try:
self.model.fit(X)
except ValueError as e:
if 'array must not contain infs or NaNs' in e.args[0]:
raise ValueError(
"Bug in scikit-learn: https://github.com/scikit-learn/scikit-learn/pull/2738"
)
raise e
X_new = self.model.transform(X)
return X_new
def fit(self, X, Y):
import sklearn.svm
import sklearn.multiclass
# In case of nested penalty
if isinstance(self.penalty, dict):
combination = self.penalty
self.penalty = combination['penalty']
self.loss = combination['loss']
self.dual = combination['dual']
self.C = float(self.C)
self.tol = float(self.tol)
self.dual = check_for_bool(self.dual)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.intercept_scaling = float(self.intercept_scaling)
if check_none(self.class_weight):
self.class_weight = None
estimator = sklearn.svm.LinearSVC(
penalty=self.penalty,
loss=self.loss,
dual=self.dual,
tol=self.tol,
C=self.C,
class_weight=self.class_weight,
fit_intercept=self.fit_intercept,
intercept_scaling=self.intercept_scaling,
multi_class=self.multi_class,
random_state=self.random_state)
if len(Y.shape) == 2 and Y.shape[1] > 1:
self.estimator = sklearn.multiclass.OneVsRestClassifier(estimator,
n_jobs=1)
else:
self.estimator = estimator
self.estimator.fit(X, Y)
return self
def fit(self, X, Y):
import sklearn.multiclass
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
# In case of nested shrinkage
if isinstance(self.shrinkage, tuple):
self.shrinkage_factor = self.shrinkage[1]['shrinkage_factor']
self.shrinkage = self.shrinkage[0]
if check_none(self.shrinkage):
self.shrinkage_ = None
solver = 'svd'
elif self.shrinkage == "auto":
self.shrinkage_ = 'auto'
solver = 'lsqr'
elif self.shrinkage == "manual":
self.shrinkage_ = float(self.shrinkage_factor)
solver = 'lsqr'
else:
raise ValueError(self.shrinkage)
self.n_components = int(self.n_components)
self.tol = float(self.tol)
estimator = LinearDiscriminantAnalysis(n_components=self.n_components,
shrinkage=self.shrinkage_,
tol=self.tol,
solver=solver)
if len(Y.shape) == 2 and Y.shape[1] > 1:
self.estimator = sklearn.multiclass.OneVsRestClassifier(estimator,
n_jobs=1)
else:
self.estimator = estimator
self.estimator.fit(X, Y)
return self
def operate(self, input_datanode, target_fields=None, sample_weight=None):
from sklearn.feature_selection import SelectFromModel
feature_types = input_datanode.feature_types
X, y = input_datanode.data
if target_fields is None:
target_fields = collect_fields(feature_types, self.input_type)
X_new = X[:, target_fields]
n_fields = len(feature_types)
irrevalent_fields = list(range(n_fields))
for field_id in target_fields:
irrevalent_fields.remove(field_id)
if self.model is None:
from sklearn.ensemble import ExtraTreesClassifier
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
self.bootstrap = check_for_bool(self.bootstrap)
self.n_jobs = int(self.n_jobs)
self.min_impurity_decrease = float(self.min_impurity_decrease)
self.max_features = self.max_features
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_samples_split = int(self.min_samples_split)
self.verbose = int(self.verbose)
max_features = int(X_new.shape[1]**float(self.max_features))
estimator = ExtraTreesClassifier(
n_estimators=self.n_estimators,
criterion=self.criterion,
max_depth=self.max_depth,
min_samples_split=self.min_samples_split,
min_samples_leaf=self.min_samples_leaf,
bootstrap=self.bootstrap,
max_features=max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_impurity_decrease=self.min_impurity_decrease,
oob_score=self.oob_score,
n_jobs=self.n_jobs,
verbose=self.verbose,
random_state=self.random_state,
class_weight=self.class_weight)
estimator.fit(X_new, y, sample_weight=sample_weight)
self.model = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
_X = self.model.transform(X_new)
is_selected = self.model.get_support()
irrevalent_types = [feature_types[idx] for idx in irrevalent_fields]
selected_types = [
feature_types[idx] for idx in target_fields if is_selected[idx]
]
selected_types.extend(irrevalent_types)
new_X = np.hstack((_X, X[:, irrevalent_fields]))
new_feature_types = selected_types
output_datanode = DataNode((new_X, y), new_feature_types,
input_datanode.task_type)
output_datanode.trans_hist = input_datanode.trans_hist.copy()
output_datanode.trans_hist.append(self.type)
output_datanode.enable_balance = input_datanode.enable_balance
output_datanode.data_balance = input_datanode.data_balance
self.target_fields = target_fields.copy()
return output_datanode