def fit(self, X, Y):
import sklearn.svm
from sklearn.feature_selection import SelectFromModel
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)
estimator.fit(X, Y)
self.preprocessor = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
return self
def fit(self, X, Y):
import sklearn.svm
import sklearn.multiclass
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.svm
import sklearn.multiclass
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 iterative_fit(self, X, y, sample_weight=None, n_iter=1, refit=False):
from sklearn.ensemble import ExtraTreesClassifier as ETC
if refit:
self.estimator = None
if self.estimator is None:
max_features = int(X.shape[1]**float(self.max_features))
if self.criterion not in ("gini", "entropy"):
raise ValueError("'criterion' is not in ('gini', 'entropy'): "
"%s" % self.criterion)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_samples_split = int(self.min_samples_split)
self.max_features = float(self.max_features)
self.min_impurity_decrease = float(self.min_impurity_decrease)
self.min_weight_fraction_leaf = float(
self.min_weight_fraction_leaf)
self.oob_score = check_for_bool(self.oob_score)
self.bootstrap = check_for_bool(self.bootstrap)
self.n_jobs = int(self.n_jobs)
self.verbose = int(self.verbose)
self.estimator = ETC(
n_estimators=n_iter,
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_weight_fraction_leaf=self.min_weight_fraction_leaf,
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,
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 iterative_fit(self, X, y, n_iter=1, refit=False):
from sklearn.ensemble import ExtraTreesRegressor as ETR
if refit:
self.estimator = None
if self.estimator is None:
self.n_estimators = int(self.n_estimators)
if self.criterion not in ("mse", "friedman_mse", "mae"):
raise ValueError(
"'criterion' is not in ('mse', 'friedman_mse', "
"'mae): %s" % self.criterion)
if check_none(self.max_depth):
self.max_depth = None
else:
self.max_depth = int(self.max_depth)
if check_none(self.max_leaf_nodes):
self.max_leaf_nodes = None
else:
self.max_leaf_nodes = int(self.max_leaf_nodes)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_samples_split = int(self.min_samples_split)
self.max_features = float(self.max_features)
self.min_impurity_decrease = float(self.min_impurity_decrease)
self.min_weight_fraction_leaf = float(self.min_weight_fraction_leaf)
self.oob_score = check_for_bool(self.oob_score)
self.bootstrap = check_for_bool(self.bootstrap)
self.n_jobs = int(self.n_jobs)
self.verbose = int(self.verbose)
self.estimator = ETR(n_estimators=n_iter,
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=self.max_features,
max_leaf_nodes=self.max_leaf_nodes,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
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,
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,)
return self
def fit(self, X, Y):
import sklearn.preprocessing
self.degree = int(self.degree)
self.interaction_only = check_for_bool(self.interaction_only)
self.include_bias = check_for_bool(self.include_bias)
self.preprocessor = sklearn.preprocessing.PolynomialFeatures(
degree=self.degree, interaction_only=self.interaction_only,
include_bias=self.include_bias)
self.preprocessor.fit(X, Y)
return self
def fit(self, X, Y):
import sklearn.preprocessing
self.degree = int(self.degree)
self.interaction_only = check_for_bool(self.interaction_only)
self.include_bias = check_for_bool(self.include_bias)
self.preprocessor = sklearn.preprocessing.PolynomialFeatures(
degree=self.degree,
interaction_only=self.interaction_only,
include_bias=self.include_bias)
self.preprocessor.fit(X, Y)
return self
def _fit(self, X, Y=None):
import sklearn.decomposition
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)
self.preprocessor = sklearn.decomposition.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:
return self.preprocessor.fit_transform(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"
)
return self
def fit(self, X, Y):
import sklearn.linear_model
self.n_iter = int(self.n_iter)
self.tol = float(self.tol)
self.alpha_1 = float(self.alpha_1)
self.alpha_2 = float(self.alpha_2)
self.lambda_1 = float(self.lambda_1)
self.lambda_2 = float(self.lambda_2)
self.threshold_lambda = float(self.threshold_lambda)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.estimator = sklearn.linear_model.\
ARDRegression(n_iter=self.n_iter,
tol=self.tol,
alpha_1=self.alpha_1,
alpha_2=self.alpha_2,
lambda_1=self.lambda_1,
lambda_2=self.lambda_2,
compute_score=False,
threshold_lambda=self.threshold_lambda,
fit_intercept=True,
normalize=False,
copy_X=False,
verbose=False)
self.estimator.fit(X, Y)
return self
def fit(self, X, y):
import sklearn.naive_bayes
import scipy.sparse
self.fit_prior = check_for_bool(self.fit_prior)
self.alpha = float(self.alpha)
self.n_iter = 0
self.fully_fit_ = False
self.estimator = sklearn.naive_bayes.MultinomialNB(
alpha=self.alpha,
fit_prior=self.fit_prior,
)
self.classes_ = np.unique(y.astype(int))
# Because the pipeline guarantees that each feature is positive,
# clip all values below zero to zero
if scipy.sparse.issparse(X):
X.data[X.data < 0] = 0.0
else:
X[X < 0] = 0.0
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
return self
def _fit(self, X, Y=None):
import sklearn.ensemble
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)
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.preprocessor = sklearn.ensemble.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.preprocessor.fit(X, Y)
return self
def fit(self, X, Y):
import sklearn.linear_model
self.n_iter = int(self.n_iter)
self.tol = float(self.tol)
self.alpha_1 = float(self.alpha_1)
self.alpha_2 = float(self.alpha_2)
self.lambda_1 = float(self.lambda_1)
self.lambda_2 = float(self.lambda_2)
self.threshold_lambda = float(self.threshold_lambda)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.estimator = sklearn.linear_model.\
ARDRegression(n_iter=self.n_iter,
tol=self.tol,
alpha_1=self.alpha_1,
alpha_2=self.alpha_2,
lambda_1=self.lambda_1,
lambda_2=self.lambda_2,
compute_score=False,
threshold_lambda=self.threshold_lambda,
fit_intercept=True,
normalize=False,
copy_X=False,
verbose=False)
self.estimator.fit(X, Y)
return self
def _fit(self, X, Y=None):
import sklearn.ensemble
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)
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.preprocessor = sklearn.ensemble.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.preprocessor.fit(X, Y)
return self
def __init__(self, n_estimators, 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 = int(n_estimators)
self.estimator_increment = 10
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 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=10,
criterion='gini',
max_features='auto',
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
bootstrap=True,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
random_state=None,
n_jobs=1,
class_weight=None,
warm_start=False)
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 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 fit(self, X, Y):
import sklearn.svm
self.C = float(self.C)
self.tol = float(self.tol)
self.epsilon = float(self.epsilon)
self.dual = check_for_bool(self.dual)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.intercept_scaling = float(self.intercept_scaling)
self.estimator = sklearn.svm.LinearSVR(epsilon=self.epsilon,
loss=self.loss,
dual=self.dual,
tol=self.tol,
C=self.C,
fit_intercept=self.fit_intercept,
intercept_scaling=self.intercept_scaling,
random_state=self.random_state)
self.estimator.fit(X, Y)
return self
def fit(self, X, Y):
import sklearn.svm
self.C = float(self.C)
self.tol = float(self.tol)
self.epsilon = float(self.epsilon)
self.dual = check_for_bool(self.dual)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.intercept_scaling = float(self.intercept_scaling)
self.estimator = sklearn.svm.LinearSVR(
epsilon=self.epsilon,
loss=self.loss,
dual=self.dual,
tol=self.tol,
C=self.C,
fit_intercept=self.fit_intercept,
intercept_scaling=self.intercept_scaling,
random_state=self.random_state)
self.estimator.fit(X, Y)
return self
def fit(self, X, Y=None):
import sklearn.decomposition
n_components = float(self.keep_variance)
self.whiten = check_for_bool(self.whiten)
self.preprocessor = sklearn.decomposition.PCA(
n_components=n_components, whiten=self.whiten, copy=True)
self.preprocessor.fit(X)
if not np.isfinite(self.preprocessor.components_).all():
raise ValueError("PCA found non-finite components.")
return self
def fit(self, X, Y):
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.feature_selection import SelectFromModel
self.n_estimators = int(self.n_estimators)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_samples_split = int(self.min_samples_split)
self.max_features = float(self.max_features)
self.bootstrap = check_for_bool(self.bootstrap)
self.n_jobs = int(self.n_jobs)
self.verbose = int(self.verbose)
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.min_weight_fraction_leaf = float(self.min_weight_fraction_leaf)
num_features = X.shape[1]
max_features = int(
float(self.max_features) * (np.log(num_features) + 1))
# Use at most half of the features
max_features = max(1, min(int(X.shape[1] / 2), max_features))
estimator = ExtraTreesRegressor(
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,
oob_score=self.oob_score,
n_jobs=self.n_jobs,
verbose=self.verbose,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
random_state=self.random_state)
estimator.fit(X, Y)
self.preprocessor = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
return self
def fit(self, X, Y):
import sklearn.svm
try:
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
soft /= 1024 * 1024
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
cache_size = (soft - maxrss) / 1.5
else:
cache_size = 200
except Exception:
cache_size = 200
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,
cache_size=cache_size,
decision_function_shape='ovr')
self.estimator.fit(X, Y)
return self
def fit(self, X, Y):
import sklearn.linear_model
self.alpha = float(self.alpha)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.estimator = sklearn.linear_model.Ridge(alpha=self.alpha,
fit_intercept=self.fit_intercept,
tol=self.tol,
copy_X=True,
normalize=False,
random_state=self.random_state)
self.estimator.fit(X, Y)
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
import sklearn.naive_bayes
import scipy.sparse
if refit:
self.estimator = None
if self.estimator is None:
self.fit_prior = check_for_bool(self.fit_prior)
self.alpha = float(self.alpha)
self.n_iter = 0
self.fully_fit_ = False
self.estimator = sklearn.naive_bayes.MultinomialNB(
alpha=self.alpha, fit_prior=self.fit_prior)
self.classes_ = np.unique(y.astype(int))
# Because the pipeline guarantees that each feature is positive,
# clip all values below zero to zero
if scipy.sparse.issparse(X):
X.data[X.data < 0] = 0.0
else:
X[X < 0] = 0.0
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.n_iter = self.n_iter
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
for iter in range(n_iter):
start = min(self.n_iter * 1000, y.shape[0])
stop = min((self.n_iter + 1) * 1000, y.shape[0])
if X[start:stop].shape[0] == 0:
self.fully_fit_ = True
break
self.estimator.partial_fit(X[start:stop], y[start:stop],
self.classes_)
self.n_iter += 1
if stop >= len(y):
self.fully_fit_ = True
break
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
from sklearn.ensemble import RandomForestRegressor
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.max_features = float(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)
self.estimator = RandomForestRegressor(
n_estimators=n_iter,
criterion=self.criterion,
max_features=self.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,
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)
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
import sklearn.naive_bayes
import scipy.sparse
if refit:
self.estimator = None
if self.estimator is None:
self.fit_prior = check_for_bool(self.fit_prior)
self.alpha = float(self.alpha)
self.n_iter = 0
self.fully_fit_ = False
self.estimator = sklearn.naive_bayes.MultinomialNB(
alpha=self.alpha, fit_prior=self.fit_prior)
self.classes_ = np.unique(y.astype(int))
# Because the pipeline guarantees that each feature is positive,
# clip all values below zero to zero
if scipy.sparse.issparse(X):
X.data[X.data < 0] = 0.0
else:
X[X < 0] = 0.0
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.n_iter = self.n_iter
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
for iter in range(n_iter):
start = min(self.n_iter * 1000, y.shape[0])
stop = min((self.n_iter + 1) * 1000, y.shape[0])
if X[start:stop].shape[0] == 0:
self.fully_fit_ = True
break
self.estimator.partial_fit(X[start:stop], y[start:stop],
self.classes_)
self.n_iter += 1
if stop >= len(y):
self.fully_fit_ = True
break
return self
def fit(self, X, y):
import sklearn.naive_bayes
self.fit_prior = check_for_bool(self.fit_prior)
self.estimator = sklearn.naive_bayes.BernoulliNB(
alpha=self.alpha, fit_prior=self.fit_prior)
self.classes_ = np.unique(y.astype(int))
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
return self
def fit(self, X, Y):
import sklearn.svm
try:
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
soft /= 1024 * 1024
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
cache_size = (soft - maxrss) / 1.5
else:
cache_size = 200
except Exception:
cache_size = 200
self.C = float(self.C)
self.epsilon = float(self.epsilon)
self.tol = float(self.tol)
self.shrinking = check_for_bool(self.shrinking)
self.degree = int(self.degree)
self.gamma = float(self.gamma)
if check_none(self.coef0):
self.coef0 = 0.0
else:
self.coef0 = float(self.coef0)
self.verbose = int(self.verbose)
self.max_iter = int(self.max_iter)
self.estimator = sklearn.svm.SVR(
kernel=self.kernel,
C=self.C,
epsilon=self.epsilon,
tol=self.tol,
shrinking=self.shrinking,
degree=self.degree,
gamma=self.gamma,
coef0=self.coef0,
cache_size=cache_size,
verbose=self.verbose,
max_iter=self.max_iter
)
self.scaler = sklearn.preprocessing.StandardScaler(copy=True)
self.scaler.fit(Y.reshape((-1, 1)))
Y_scaled = self.scaler.transform(Y.reshape((-1, 1))).ravel()
self.estimator.fit(X, Y_scaled)
return self
def fit(self, X, Y, sample_weight=None):
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFromModel
self.n_estimators = int(self.n_estimators)
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.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, Y, sample_weight=sample_weight)
self.preprocessor = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
return self
def __init__(self,
n_estimators,
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 = int(n_estimators)
self.estimator_increment = 10
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 fit(self, X, Y, sample_weight=None):
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.feature_selection import SelectFromModel
self.n_estimators = int(self.n_estimators)
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.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, Y, sample_weight=sample_weight)
self.preprocessor = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
return self
def _fit(self, X, y=None):
self.use_minimum_fraction = check_for_bool(self.use_minimum_fraction)
if self.use_minimum_fraction is False:
self.minimum_fraction = None
else:
self.minimum_fraction = float(self.minimum_fraction)
if check_none(self.categorical_features):
categorical_features = []
else:
categorical_features = self.categorical_features
self.preprocessor = autosklearn.pipeline.implementations.OneHotEncoder\
.OneHotEncoder(minimum_fraction=self.minimum_fraction,
categorical_features=categorical_features,
sparse=True)
return self.preprocessor.fit_transform(X)
def fit(self, X, Y):
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.feature_selection import SelectFromModel
self.n_estimators = int(self.n_estimators)
self.min_samples_leaf = int(self.min_samples_leaf)
self.min_samples_split = int(self.min_samples_split)
self.max_features = float(self.max_features)
self.bootstrap = check_for_bool(self.bootstrap)
self.n_jobs = int(self.n_jobs)
self.verbose = int(self.verbose)
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.min_weight_fraction_leaf = float(self.min_weight_fraction_leaf)
num_features = X.shape[1]
max_features = int(
float(self.max_features) * (np.log(num_features) + 1))
# Use at most half of the features
max_features = max(1, min(int(X.shape[1] / 2), max_features))
estimator = ExtraTreesRegressor(
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,
oob_score=self.oob_score, n_jobs=self.n_jobs, verbose=self.verbose,
min_weight_fraction_leaf=self.min_weight_fraction_leaf,
random_state=self.random_state)
estimator.fit(X, Y)
self.preprocessor = SelectFromModel(estimator=estimator,
threshold='mean',
prefit=True)
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
from sklearn.ensemble import RandomForestRegressor
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.max_features = float(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)
self.estimator = RandomForestRegressor(
n_estimators=0,
criterion=self.criterion,
max_features=self.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,
warm_start=True)
self.estimator.n_estimators += n_iter
self.estimator.n_estimators = min(self.estimator.n_estimators,
self.n_estimators)
self.estimator.fit(X, y)
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
import sklearn.naive_bayes
if refit:
self.estimator = None
if self.estimator is None:
self.n_iter = 0
self.fully_fit_ = False
self.fit_prior = check_for_bool(self.fit_prior)
self.estimator = sklearn.naive_bayes.BernoulliNB(
alpha=self.alpha, fit_prior=self.fit_prior)
self.classes_ = np.unique(y.astype(int))
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.n_iter = self.n_iter
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
for iter in range(n_iter):
start = min(self.n_iter * 1000, y.shape[0])
stop = min((self.n_iter + 1) * 1000, y.shape[0])
# Upper limit, scipy.sparse doesn't seem to handle max > len(matrix)
stop = min(stop, y.shape[0])
if X[start:stop].shape[0] == 0:
self.fully_fit_ = True
break
self.estimator.partial_fit(X[start:stop], y[start:stop],
self.classes_)
self.n_iter += 1
if stop >= len(y):
self.fully_fit_ = True
break
return self
def iterative_fit(self, X, y, n_iter=1, refit=False):
import sklearn.naive_bayes
if refit:
self.estimator = None
if self.estimator is None:
self.n_iter = 0
self.fully_fit_ = False
self.fit_prior = check_for_bool(self.fit_prior)
self.estimator = sklearn.naive_bayes.BernoulliNB(
alpha=self.alpha, fit_prior=self.fit_prior)
self.classes_ = np.unique(y.astype(int))
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.n_iter = self.n_iter
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
for iter in range(n_iter):
start = min(self.n_iter * 1000, y.shape[0])
stop = min((self.n_iter + 1) * 1000, y.shape[0])
# Upper limit, scipy.sparse doesn't seem to handle max > len(matrix)
stop = min(stop, y.shape[0])
if X[start:stop].shape[0] == 0:
self.fully_fit_ = True
break
self.estimator.partial_fit(X[start:stop], y[start:stop], self.classes_)
self.n_iter += 1
if stop >= len(y):
self.fully_fit_ = True
break
return self
def _fit(self, X, Y=None):
import sklearn.decomposition
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)
self.preprocessor = sklearn.decomposition.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:
return self.preprocessor.fit_transform(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")
return self
def iterative_fit(self, X, y, n_iter=2, refit=False):
"""
Set n_iter=2 for the same reason as for SGD
"""
from sklearn.neural_network import MLPRegressor
import sklearn.preprocessing
n_iter = max(n_iter, 2)
if refit:
self.estimator = None
self.scaler = None
if self.estimator is None:
self._fully_fit = False
self.max_iter = int(self.max_iter)
self.hidden_layer_depth = int(self.hidden_layer_depth)
self.num_nodes_per_layer = int(self.num_nodes_per_layer)
self.hidden_layer_sizes = tuple(self.num_nodes_per_layer
for i in range(self.hidden_layer_depth))
self.activation = str(self.activation)
self.alpha = float(self.alpha)
self.learning_rate_init = float(self.learning_rate_init)
self.early_stopping = str(self.early_stopping)
if self.early_stopping == "train":
self.validation_fraction = 0.0
self.tol = float(self.tol)
self.n_iter_no_change = int(self.n_iter_no_change)
self.early_stopping_val = False
elif self.early_stopping == "valid":
self.validation_fraction = float(self.validation_fraction)
self.tol = float(self.tol)
self.n_iter_no_change = int(self.n_iter_no_change)
self.early_stopping_val = True
else:
raise ValueError("Set early stopping to unknown value %s" % self.early_stopping)
# elif self.early_stopping == "off":
# self.validation_fraction = 0
# self.tol = 10000
# self.n_iter_no_change = self.max_iter
# self.early_stopping_val = False
self.solver = self.solver
try:
self.batch_size = int(self.batch_size)
except ValueError:
self.batch_size = str(self.batch_size)
self.shuffle = check_for_bool(self.shuffle)
self.beta_1 = float(self.beta_1)
self.beta_2 = float(self.beta_2)
self.epsilon = float(self.epsilon)
self.beta_1 = float(self.beta_1)
self.verbose = int(self.verbose)
n_iter = int(np.ceil(n_iter))
# initial fit of only increment trees
self.estimator = MLPRegressor(
hidden_layer_sizes=self.hidden_layer_sizes,
activation=self.activation,
solver=self.solver,
alpha=self.alpha,
batch_size=self.batch_size,
learning_rate_init=self.learning_rate_init,
max_iter=n_iter,
shuffle=self.shuffle,
random_state=self.random_state,
verbose=self.verbose,
warm_start=True,
early_stopping=self.early_stopping_val,
validation_fraction=self.validation_fraction,
n_iter_no_change=self.n_iter_no_change,
tol=self.tol,
beta_1=self.beta_2,
beta_2=self.beta_1,
epsilon=self.epsilon,
# We do not use these, see comments below in search space
# momentum=self.momentum,
# nesterovs_momentum=self.nesterovs_momentum,
# power_t=self.power_t,
# learning_rate=self.learning_rate,
# max_fun=self.max_fun
)
self.scaler = sklearn.preprocessing.StandardScaler(copy=True)
self.scaler.fit(y.reshape((-1, 1)))
else:
new_max_iter = min(self.max_iter - self.estimator.n_iter_, n_iter)
self.estimator.max_iter = new_max_iter
Y_scaled = self.scaler.transform(y.reshape((-1, 1))).ravel()
self.estimator.fit(X, Y_scaled)
if self.estimator.n_iter_ >= self.max_iter or \
self.estimator._no_improvement_count > self.n_iter_no_change:
self._fully_fit = True
return self
def fit(self, X, Y):
import sklearn.svm
# Calculate the size of the kernel cache (in MB) for sklearn's LibSVM. The cache size is
# calculated as 2/3 of the available memory (which is calculated as the memory limit minus
# the used memory)
try:
# Retrieve memory limits imposed on the process
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
# Convert limit to units of megabytes
soft /= 1024 * 1024
# Retrieve memory used by this process
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
# In MacOS, the MaxRSS output of resource.getrusage in bytes; on other platforms,
# it's in kilobytes
if sys.platform == 'darwin':
maxrss = maxrss / 1024
cache_size = (soft - maxrss) / 1.5
if cache_size < 0:
cache_size = 200
else:
cache_size = 200
except Exception:
cache_size = 200
self.C = float(self.C)
self.epsilon = float(self.epsilon)
self.tol = float(self.tol)
self.shrinking = check_for_bool(self.shrinking)
self.degree = int(self.degree)
self.gamma = float(self.gamma)
if check_none(self.coef0):
self.coef0 = 0.0
else:
self.coef0 = float(self.coef0)
self.verbose = int(self.verbose)
self.max_iter = int(self.max_iter)
self.estimator = sklearn.svm.SVR(kernel=self.kernel,
C=self.C,
epsilon=self.epsilon,
tol=self.tol,
shrinking=self.shrinking,
degree=self.degree,
gamma=self.gamma,
coef0=self.coef0,
cache_size=cache_size,
verbose=self.verbose,
max_iter=self.max_iter)
self.scaler = sklearn.preprocessing.StandardScaler(copy=True)
self.scaler.fit(Y.reshape((-1, 1)))
Y_scaled = self.scaler.transform(Y.reshape((-1, 1))).ravel()
self.estimator.fit(X, Y_scaled)
return self
def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.passive_aggressive import \
PassiveAggressiveClassifier
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.C = float(self.C)
call_fit = True
self.estimator = PassiveAggressiveClassifier(
C=self.C,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
loss=self.loss,
shuffle=True,
random_state=self.random_state,
warm_start=True,
average=self.average,
)
self.classes_ = np.unique(y.astype(int))
else:
call_fit = False
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.max_iter = 50
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
if call_fit:
self.estimator.fit(X, y)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter,
1000)
self.estimator._validate_params()
lr = "pa1" if self.estimator.loss == "hinge" else "pa2"
self.estimator._partial_fit(
X, y,
alpha=1.0,
C=self.estimator.C,
loss="hinge",
learning_rate=lr,
max_iter=n_iter,
classes=None,
sample_weight=sample_weight,
coef_init=None,
intercept_init=None
)
if (
self.estimator._max_iter >= 1000
or n_iter > self.estimator.n_iter_
):
self.fully_fit_ = True
return self
def fit(self, X, Y):
import sklearn.svm
# Calculate the size of the kernel cache (in MB) for sklearn's LibSVM. The cache size is
# calculated as 2/3 of the available memory (which is calculated as the memory limit minus
# the used memory)
try:
# Retrieve memory limits imposed on the process
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
# Convert limit to units of megabytes
soft /= 1024 * 1024
# Retrieve memory used by this process
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
# In MacOS, the MaxRSS output of resource.getrusage in bytes; on other platforms,
# it's in kilobytes
if sys.platform == 'darwin':
maxrss = maxrss / 1024
cache_size = (soft - maxrss) / 1.5
if cache_size < 0:
cache_size = 200
else:
cache_size = 200
except Exception:
cache_size = 200
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,
cache_size=cache_size,
decision_function_shape='ovr')
self.estimator.fit(X, Y)
return self
def iterative_fit(self, X, y, n_iter=2, refit=False):
from sklearn.linear_model import SGDRegressor
import sklearn.preprocessing
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
n_iter = max(n_iter, 2)
if refit:
self.estimator = None
self.scaler = None
if self.estimator is None:
self.alpha = float(self.alpha)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.l1_ratio = float(
self.l1_ratio) if self.l1_ratio is not None else 0.15
self.epsilon = float(
self.epsilon) if self.epsilon is not None else 0.1
self.eta0 = float(self.eta0)
self.power_t = float(
self.power_t) if self.power_t is not None else 0.25
self.average = check_for_bool(self.average)
self.estimator = SGDRegressor(loss=self.loss,
penalty=self.penalty,
alpha=self.alpha,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
learning_rate=self.learning_rate,
l1_ratio=self.l1_ratio,
epsilon=self.epsilon,
eta0=self.eta0,
power_t=self.power_t,
shuffle=True,
average=self.average,
random_state=self.random_state,
warm_start=True)
self.scaler = sklearn.preprocessing.StandardScaler(copy=True)
self.scaler.fit(y.reshape((-1, 1)))
Y_scaled = self.scaler.transform(y.reshape((-1, 1))).ravel()
self.estimator.fit(X, Y_scaled)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter, self.max_iter)
Y_scaled = self.scaler.transform(y.reshape((-1, 1))).ravel()
self.estimator._validate_params()
self.estimator._partial_fit(
X, Y_scaled,
alpha=self.estimator.alpha,
C=1.0,
loss=self.estimator.loss,
learning_rate=self.estimator.learning_rate,
max_iter=n_iter,
sample_weight=None,
coef_init=None,
intercept_init=None
)
if self.estimator.max_iter >= self.max_iter or n_iter > self.estimator.n_iter_:
self.fully_fit_ = True
return self
def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.stochastic_gradient import SGDClassifier
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.alpha = float(self.alpha)
self.l1_ratio = float(self.l1_ratio) if self.l1_ratio is not None \
else 0.15
self.epsilon = float(self.epsilon) if self.epsilon is not None \
else 0.1
self.eta0 = float(self.eta0)
self.power_t = float(self.power_t) if self.power_t is not None \
else 0.5
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.estimator = SGDClassifier(loss=self.loss,
penalty=self.penalty,
alpha=self.alpha,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
learning_rate=self.learning_rate,
l1_ratio=self.l1_ratio,
epsilon=self.epsilon,
eta0=self.eta0,
power_t=self.power_t,
shuffle=True,
average=self.average,
random_state=self.random_state,
warm_start=True)
self.estimator.fit(X, y, sample_weight=sample_weight)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter, 512)
self.estimator._validate_params()
self.estimator._partial_fit(
X, y,
alpha=self.estimator.alpha,
C=1.0,
loss=self.estimator.loss,
learning_rate=self.estimator.learning_rate,
max_iter=n_iter,
sample_weight=sample_weight,
classes=None,
coef_init=None,
intercept_init=None
)
if self.estimator.max_iter >= 512 or n_iter > self.estimator.n_iter_:
self.fully_fit_ = True
return self
def fit(self, X, Y):
import sklearn.svm
# Calculate the size of the kernel cache (in MB) for sklearn's LibSVM. The cache size is
# calculated as 2/3 of the available memory (which is calculated as the memory limit minus
# the used memory)
try:
# Retrieve memory limits imposed on the process
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
# Convert limit to units of megabytes
soft /= 1024 * 1024
# Retrieve memory used by this process
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
# In MacOS, the MaxRSS output of resource.getrusage in bytes; on other platforms,
# it's in kilobytes
if sys.platform == 'darwin':
maxrss = maxrss / 1024
cache_size = (soft - maxrss) / 1.5
if cache_size < 0:
cache_size = 200
else:
cache_size = 200
except Exception:
cache_size = 200
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,
cache_size=cache_size,
decision_function_shape='ovr')
self.estimator.fit(X, Y)
return self
def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.stochastic_gradient import SGDClassifier
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.alpha = float(self.alpha)
self.l1_ratio = float(self.l1_ratio) if self.l1_ratio is not None \
else 0.15
self.epsilon = float(self.epsilon) if self.epsilon is not None \
else 0.1
self.eta0 = float(self.eta0)
self.power_t = float(self.power_t) if self.power_t is not None \
else 0.5
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.estimator = SGDClassifier(loss=self.loss,
penalty=self.penalty,
alpha=self.alpha,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
learning_rate=self.learning_rate,
l1_ratio=self.l1_ratio,
epsilon=self.epsilon,
eta0=self.eta0,
power_t=self.power_t,
shuffle=True,
average=self.average,
random_state=self.random_state,
warm_start=True)
self.estimator.fit(X, y, sample_weight=sample_weight)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter, 512)
self.estimator._validate_params()
self.estimator._partial_fit(
X, y,
alpha=self.estimator.alpha,
C=1.0,
loss=self.estimator.loss,
learning_rate=self.estimator.learning_rate,
max_iter=n_iter,
sample_weight=sample_weight,
classes=None,
coef_init=None,
intercept_init=None
)
if self.estimator._max_iter >= 512 or n_iter > self.estimator.n_iter_:
self.fully_fit_ = True
return self
def fit(self, X, Y):
import sklearn.svm
# Calculate the size of the kernel cache (in MB) for sklearn's LibSVM. The cache size is
# calculated as 2/3 of the available memory (which is calculated as the memory limit minus
# the used memory)
try:
# Retrieve memory limits imposed on the process
soft, hard = resource.getrlimit(resource.RLIMIT_AS)
if soft > 0:
# Convert limit to units of megabytes
soft /= 1024 * 1024
# Retrieve memory used by this process
maxrss = resource.getrusage(resource.RUSAGE_SELF)[2] / 1024
# In MacOS, the MaxRSS output of resource.getrusage in bytes; on other platforms,
# it's in kilobytes
if sys.platform == 'darwin':
maxrss = maxrss / 1024
cache_size = (soft - maxrss) / 1.5
if cache_size < 0:
cache_size = 200
else:
cache_size = 200
except Exception:
cache_size = 200
self.C = float(self.C)
self.epsilon = float(self.epsilon)
self.tol = float(self.tol)
self.shrinking = check_for_bool(self.shrinking)
self.degree = int(self.degree)
self.gamma = float(self.gamma)
if check_none(self.coef0):
self.coef0 = 0.0
else:
self.coef0 = float(self.coef0)
self.verbose = int(self.verbose)
self.max_iter = int(self.max_iter)
self.estimator = sklearn.svm.SVR(
kernel=self.kernel,
C=self.C,
epsilon=self.epsilon,
tol=self.tol,
shrinking=self.shrinking,
degree=self.degree,
gamma=self.gamma,
coef0=self.coef0,
cache_size=cache_size,
verbose=self.verbose,
max_iter=self.max_iter
)
self.scaler = sklearn.preprocessing.StandardScaler(copy=True)
self.scaler.fit(Y.reshape((-1, 1)))
Y_scaled = self.scaler.transform(Y.reshape((-1, 1))).ravel()
self.estimator.fit(X, Y_scaled)
return self
def iterative_fit(self, X, y, n_iter=2, refit=False, sample_weight=None):
from sklearn.linear_model.passive_aggressive import \
PassiveAggressiveClassifier
# Need to fit at least two iterations, otherwise early stopping will not
# work because we cannot determine whether the algorithm actually
# converged. The only way of finding this out is if the sgd spends less
# iterations than max_iter. If max_iter == 1, it has to spend at least
# one iteration and will always spend at least one iteration, so we
# cannot know about convergence.
if refit:
self.estimator = None
if self.estimator is None:
self.fully_fit_ = False
self.average = check_for_bool(self.average)
self.fit_intercept = check_for_bool(self.fit_intercept)
self.tol = float(self.tol)
self.C = float(self.C)
call_fit = True
self.estimator = PassiveAggressiveClassifier(
C=self.C,
fit_intercept=self.fit_intercept,
max_iter=n_iter,
tol=self.tol,
loss=self.loss,
shuffle=True,
random_state=self.random_state,
warm_start=True,
average=self.average,
)
self.classes_ = np.unique(y.astype(int))
else:
call_fit = False
# Fallback for multilabel classification
if len(y.shape) > 1 and y.shape[1] > 1:
import sklearn.multiclass
self.estimator.max_iter = 50
self.estimator = sklearn.multiclass.OneVsRestClassifier(
self.estimator, n_jobs=1)
self.estimator.fit(X, y)
self.fully_fit_ = True
else:
if call_fit:
self.estimator.fit(X, y)
else:
self.estimator.max_iter += n_iter
self.estimator.max_iter = min(self.estimator.max_iter, 1000)
self.estimator._validate_params()
lr = "pa1" if self.estimator.loss == "hinge" else "pa2"
self.estimator._partial_fit(X,
y,
alpha=1.0,
C=self.estimator.C,
loss="hinge",
learning_rate=lr,
max_iter=n_iter,
classes=None,
sample_weight=sample_weight,
coef_init=None,
intercept_init=None)
if (self.estimator.max_iter >= 1000
or n_iter > self.estimator.n_iter_):
self.fully_fit_ = True
return self