def __init__(self, **kwargs):
r"""Initialize SelectPercentile feature selection algorithm.
"""
self._params = dict(score_func=ParameterDefinition(
[chi2, f_classif, mutual_info_classif]),
percentile=ParameterDefinition(
MinMax(10, 100), np.uint))
self.__select_percentile = SelectPerc()
def __init__(self, **kwargs):
r"""Initialize PSO feature selection algorithm.
"""
self._params = dict(
C1 = ParameterDefinition(MinMax(1.5, 2.5), param_type=float),
C2 = ParameterDefinition(MinMax(1.5, 2.5), param_type=float)
)
self.__pso = PSO(NP=10)
def __init__(self, **kwargs):
r"""Initialize BA feature selection algorithm.
"""
self._params = dict(A=ParameterDefinition(MinMax(0.5, 1.0),
param_type=float),
r=ParameterDefinition(MinMax(0.0, 0.5),
param_type=float),
Qmin=ParameterDefinition(MinMax(0.0, 1.0),
param_type=float),
Qmax=ParameterDefinition(MinMax(1.0, 2.0),
param_type=float))
self.__ba = BA(NP=10)
def __init__(self, **kwargs):
r"""Initialize DecisionTree instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(criterion=ParameterDefinition(['gini', 'entropy']),
splitter=ParameterDefinition(['best', 'random']))
self.__decision_tree_classifier = DTC()
def __init__(self, **kwargs):
r"""Initialize LinearSVCClassifier instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(penalty=ParameterDefinition(['l1', 'l2']),
max_iter=ParameterDefinition(
MinMax(min=300, max=2000), np.uint))
self.__linear_SVC = LSVC()
def __init__(self, **kwargs):
r"""Initialize SelectKBest feature selection algorithm.
Notes:
_params['k'] is initialized to None as it is included in the optimization process later since we cannot determine a proper value range until length of the feature vector becomes known.
"""
self._params = dict(score_func=ParameterDefinition(
[chi2, f_classif, mutual_info_classif]),
k=None)
self.__k = None
self.__select_k_best = SelectKB()
def __init__(self, **kwargs):
r"""Initialize KNeighbors instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(weights=ParameterDefinition(
['uniform', 'distance']),
algorithm=ParameterDefinition(
['auto', 'ball_tree', 'kd_tree', 'brute']))
self.__kn_classifier = KNC()
def __init__(self, **kwargs):
r"""Initialize Bagging instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(
n_estimators=ParameterDefinition(MinMax(min=10, max=111), np.uint),
bootstrap=ParameterDefinition([True, False]),
bootstrap_features=ParameterDefinition([True, False]))
self.__bagging_classifier = BaggingClassifier()
def __init__(self, **kwargs):
r"""Initialize AdaBoost instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(n_estimators=ParameterDefinition(
MinMax(min=10, max=111), np.uint),
algorithm=ParameterDefinition(['SAMME',
'SAMME.R']))
self.__ada_boost = AdaBoostClassifier()
def __init__(self, **kwargs):
r"""Initialize GaussianProcess instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(
max_iter_predict=ParameterDefinition(MinMax(50, 200), np.uint),
warm_start=ParameterDefinition([True, False]),
multi_class=ParameterDefinition(['one_vs_rest', 'one_vs_one']))
self.__gaussian_process = GPC()
def __init__(self, **kwargs):
r"""Initialize MultiLayerPerceptron instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(activation=ParameterDefinition(
['identity', 'logistic', 'tanh', 'relu']),
solver=ParameterDefinition(
['lbfgs', 'sgd', 'adam']),
learning_rate=ParameterDefinition(
['constant', 'invscaling', 'adaptive']))
self.__multi_layer_perceptron = MLPClassifier()
def __init__(self, **kwargs):
r"""Initialize RandomForestClassifier instance.
"""
warnings.filterwarnings(action='ignore',
category=ChangedBehaviorWarning)
warnings.filterwarnings(action='ignore', category=ConvergenceWarning)
warnings.filterwarnings(action='ignore',
category=DataConversionWarning)
warnings.filterwarnings(action='ignore',
category=DataDimensionalityWarning)
warnings.filterwarnings(action='ignore', category=EfficiencyWarning)
warnings.filterwarnings(action='ignore', category=FitFailedWarning)
warnings.filterwarnings(action='ignore', category=NonBLASDotWarning)
warnings.filterwarnings(action='ignore',
category=UndefinedMetricWarning)
self._params = dict(
n_estimators=ParameterDefinition(MinMax(min=10, max=111), np.uint))
self.__random_forest_classifier = RF()
def select_features(self, x, y, **kwargs):
r"""Perform the feature selection process.
Arguments:
x (pandas.core.frame.DataFrame): Array of original features.
y (pandas.core.series.Series) Expected classifier results.
Returns:
numpy.ndarray[bool]: Mask of selected features.
"""
if self.__k is None:
self.__k = x.shape[1]
self._params['k'] = ParameterDefinition(MinMax(1, self.__k),
np.int)
val = np.int(np.around(np.random.uniform(1, self.__k)))
self.__select_k_best.set_params(k=val)
self.__select_k_best.fit(x, y)
return self.__select_k_best.get_support()
def __init__(self, **kwargs):
r"""Initialize QuantileTransformer.
"""
self._params = dict(
output_distribution=ParameterDefinition(['uniform', 'normal']))
self.__quantile_transformer = QT()
def __init__(self, **kwargs):
r"""Initialize VarianceThreshold feature selection algorithm.
"""
self._params = dict(
threshold=ParameterDefinition(MinMax(0, 0.1), np.float))
self.__variance_threshold = VarThr()
def __init__(self, **kwargs):
r"""Initialize Normalizer.
"""
self._params = dict(norm=ParameterDefinition(['l1', 'l2', 'max']))
self.__params = None
self.__normalizer = Nrm()
def __init__(self, **kwargs):
r"""Initialize RobustScaler.
"""
self._params = dict(with_centering=ParameterDefinition([True, False]),
with_scaling=ParameterDefinition([True, False]))
self.__robust_scaler = RS()
