List of all Nodes

pySPACE comes along with a big choice of 295 processing nodes. This includes numerous wrappers around optional external libraries. They can be accessed via the NodeChainOperation. In the following you can get an overview on their functionality, the mapping from node names in specification files to the node class and vice versa.

For details on the usage of the nodes and for getting usage examples, have a look at their documentation.

Mapping of Class Names to Functionality

classification


classification Classification of the incoming signal

adaptive_threshold_classifier.AdaptiveThresholdClassifierNode Adaptive threshold onset detection classifier
adaptive_threshold_classifier.AdaptiveThresholdPreprocessingNode Setting adaptive threshold as described by Semmaoui, H., etal.
discriminant_analysis_classifier.LinearDiscriminantAnalysisClassifierNode Classify by linear discriminant analysis
discriminant_analysis_classifier.QuadraticDiscriminantAnalysisClassifierNode Classify by quadratic discriminant analysis
ensemble.ChampionGatingNode Gating function to classify with the classifier that performs best on training data
ensemble.KNNGatingNode Gating function based on k-Nearest-Neighbors
ensemble.LabelVotingGatingNode Gating function to classify based on the majority vote
ensemble.PrecisionWeightedGatingNode Gating function to classify based on weighted majority vote
ensemble.ProbVotingGatingNode Add up prediction values for labels to find out most probable label
ensemble.RidgeRegressionGatingNode Gating function using ridge regression to learn weighting
linear_classifier.BayesianLinearDiscriminantAnalysisClassifierNode Classify with the bayesian linear discriminant analysis
linear_classifier.FDAClassifierNode Classify with Fisher’s linear discriminant analysis
one_class.LibsvmOneClassNode Interface to one-class SVM in Libsvm package
random_classifier.RandomClassifierNode Assign data randomly with probability 0.5 to the classes
svm_variants.ORMM.L2OcRmmPerceptronNode Squared loss variant of the one-class RMM Perceptron
svm_variants.ORMM.OcRmmNode Take zero as opposite class
svm_variants.ORMM.OcRmmPerceptronNode Take zero as opposite class for online learning update formula
svm_variants.ORMM.SvddPassiveAggressiveNode Support Vector Data Description like Perceptron’s suggested by Crammer
svm_variants.ORMM.UnaryPA0Node PA0 Node for unary classification
svm_variants.ORMM.UnaryPA1Node PA1 Node for unary classification
svm_variants.ORMM.UnaryPA2Node PA2 Node for unary classification
svm_variants.SOR.SorSvmNode Classify with 2-norm SVM relaxation using the SOR algorithm
svm_variants.brmm.RMM1ClassifierNode Classify with 1-Norm SVM and relative margin
svm_variants.brmm.RMM2Node Classify with 2-norm SVM relaxation (b in target function) for BRMM
svm_variants.brmm.RMMClassifierMatlabNode Classify with Relative Margin Machine using original matlab code
svm_variants.brmm.RmmPerceptronNode Online Learning variants of the 2-norm RMM
svm_variants.brmm.SVR2BRMMNode Simple wrapper around epsilon-SVR with BRMM parameter mapping
svm_variants.external.LibSVMClassifierNode Classify like a Standard SVM with the LibSVM settings.
svm_variants.external.LiblinearClassifierNode Code Integration of external linear SVM classifier program

data_selection


data_selection Selection of data

filter_windows.FilterWindowsNode Filter out the windows depending on their label.
instance_selection.InstanceSelectionNode Retain only a certain percentage of the instances
instance_selection.ReduceOverrepresentedClassNode Reject instances to balance categories for classification

debug


debug Support nodes for debugging of node chains, other nodes, etc.

exchange_data.ExchangeDataNode Exchange the data against some self created data
print_data.EstimateBandwidthNode Estimates the Bandwidth of the data which is forwarded through this node
print_data.PrintDataNode Print out formatted data.
sleep.SleepNode Sleeps for a fixed amount of time
subflow_timing_node.SubflowTimingNode Measure and dump the average time consumption of a given subflow

feature_generation


feature_generation Generate features from a time series (amplitudes or frequency spectrum for example)

correlation_features.ClassAverageCorrelationFeatureNode Compute pearson correlation between channel segments and class averages
correlation_features.CoherenceFeatureNode Compute pairwise coherence of two channels with matplotlib.mlab.cohere
correlation_features.PearsonCorrelationFeatureNode Compute pearson correlation of all pairs of channels
correlation_features.StatisticalFeatureNode Compute statistical features, e.g.
frequency_features.FrequencyBandFeatureNode Extract features based on the Frequency-band power
frequency_features.STFTFeaturesNode Extract features based on the Short-term Fourier Transform
time_domain_features.CustomChannelWiseFeatureNode Use the result of a transformation of the time series as features.
time_domain_features.LocalStraightLineFeatureNode Fit straight lines to channel segments and uses coefficients as features.
time_domain_features.SimpleDifferentiationFeatureNode Use differences between successive times on the same channel.
time_domain_features.TimeDomainDifferenceFeatureNode Use differences between channels and/or times as features.
time_domain_features.TimeDomainFeaturesNode Use the samples of the time series as features
wavelet.PywtWaveletNode Extract features based on the discrete wavelet transform from pywavelets

feature_selection


feature_selection Select features by learning algorithms or simple name filtering

feature_filter.FeatureNameFilterNode Filter feature vectors by name patterns or indices
random_feature_selection.RandomFeatureSelectionNode Randomly select a given number of features
relief.ReliefFeatureSelectionNode Feature selection based on the RELIEF algorithm

meta


meta Nodes, wrapping other groups of nodes or node chains

classifier_wrapper.SVMComplexityLayerNode Calculate the minimal complexity, where the soft margin is inactive
classifier_wrapper.SplitClassifierLayerNode Split the overrepresented class in the training set for multiple training.
consume_training_data.ConsumeTrainingDataNode Split training data for internal usage and usage of successor nodes
flow_node.BacktransformationNode Determine underlying linear transformation of classifier or regression algorithm
flow_node.BatchAdaptSubflowNode Load and retrain a pre-trained NodeChain for recalibration
flow_node.FlowNode Encapsulate a whole node chain from YAML specification or path into a single node
flow_node.UnsupervisedRetrainingFlowNode Use classified label for retraining
parameter_optimization.GridSearchNode Grid search for optimizing the parameterization of a subflow
parameter_optimization.PatternSearchNode Extension of the standard Pattern Search algorithm
same_input_layer.ClassificationFlowsLoaderNode Combine an ensemble of pretrained node chains
same_input_layer.MultiClassLayerNode Wrap the one vs.
same_input_layer.SameInputLayerNode Encapsulates a set of other nodes that are executed in parallel in the flow.
stream_windowing.StreamWindowingNode Get a stream of time series objects and window them inside a flow.

postprocessing


postprocessing Final modification or clean up of FeatureVector and PredictionVector

compression.RandomFeatureCompressionNode Compress the data using a number of random vectors
feature_normalization.EuclideanFeatureNormalizationNode Normalize feature vectors to Euclidean norm with respect to dimensions
feature_normalization.FeatureNormalizationNode General node for Feature Normalization
feature_normalization.GaussianFeatureNormalizationNode Transform the features, such that they have zero mean and variance one
feature_normalization.HistogramFeatureNormalizationNode Transform the features, such that they have zero mean in the main bit in the histogram and variance one on that bit.
feature_normalization.InfinityNormFeatureNormalizationNode Normalize feature vectors with infinity norm to [-1,1]
feature_normalization.OutlierFeatureNormalizationNode Map the feature vectors of the training set to the range [0,1]^n
score_transformation.LinearFitNode Linear mapping between score and [0,1]
score_transformation.LinearTransformationNode Scaling and offset shift, and relabeling due to new decision boundary
score_transformation.PlattsSigmoidFitNode Map prediction scores to probability estimates with a sigmoid fit
score_transformation.SigmoidTransformationNode Transform score to interval [0,1] with a sigmoid function
threshold_optimization.ThresholdOptimizationNode Optimize the classification threshold for a specified metric

preprocessing


preprocessing Standard preprocessing of the incoming TimeSeries

clip.ClipNode Clip all values to a certain range of values
differentiation.Simple2DifferentiationNode Calculate difference to previous time point to generate new TimeSeries
differentiation.Simple5DifferentiationNode Calculate smoothed derivative using 5 time points
filtering.FFTBandPassFilterNode Band-pass filtering using a Fourier transform
filtering.FIRFilterNode Band-pass or low-pass filtering with a time domain convolution based on a FIR filter kernel
filtering.HighPassFilterNode High-pass filtering with a FIR filter
filtering.IIRFilterNode Band-pass or low-pass filtering with a direct form IIR filter
filtering.SimpleLowPassFilterNode Low-pass filtering with the given cutoff frequency using SciPy
filtering.TkeoNode Calculate the energy of a signal with the Teager Kaiser Energy Operator (TKEO) as new signal
filtering.VarianceFilterNode Take the variance as filtered data or standardize with moving variance and mean
normalization.DcRemovalNode Perform a realtime DC removal on the selected channels
normalization.DetrendingNode Eliminate trend on the selected channels with the given function (default: mean)
normalization.DevariancingNode Apply devariancing method on training data and use the result for scaling
normalization.EuclideanNormalizationNode Scale all channels to norm one
normalization.LocalStandardizationNode Z-Score transformation (zero mean, variance of one)
normalization.MaximumStandardizationNode Standardize by subtracting the mean and dividing by maximum value
normalization.MemoryStandardizationNode Z-Score transformation with respect to the last order windows
normalization.SubsetNormalizationNode Z-Score transformation by the mean and variance of a subset of the samples
reorder_memory.ReorderMemoryNode Reorder the memory of the TimeSeries
subsampling.DecimationFIRNode Downsampling with a preceding FIR filter
subsampling.DecimationIIRNode Downsampling with a preceding IIR filter
subsampling.DownsamplingNode Pure downsampling without filter
subsampling.FFTResamplingNode Downsampling with a FFT filter
subsampling.SubsamplingNode Downsampling with a simple low pass filter
window_func.ScaleNode Scale all value by a constant factor
window_func.WindowFuncNode Multiply the TimeSeries with a window

regression


regression Regression of the incoming signal

scikit_decorators.OptSVRRegressorSklearnNode Decorator wrapper around SVRRegressorSklearnNode

scikit_nodes


scikit_nodes Wrap the algorithms defined in scikit.learn in pySPACE nodes

ARDRegressionSklearnNode Bayesian ARD regression.
AdaBoostClassifierSklearnNode An AdaBoost classifier.
AdaBoostRegressorSklearnNode An AdaBoost regressor.
AdditiveChi2SamplerTransformerSklearnNode Approximate feature map for additive chi2 kernel.
BaggingClassifierSklearnNode A Bagging classifier.
BaggingRegressorSklearnNode A Bagging regressor.
BayesianRidgeRegressorSklearnNode Bayesian ridge regression
BernoulliNBClassifierSklearnNode Naive Bayes classifier for multivariate Bernoulli models.
BernoulliRBMTransformerSklearnNode Bernoulli Restricted Boltzmann Machine (RBM).
BinarizerTransformerSklearnNode Binarize data (set feature values to 0 or 1) according to a threshold
BirchTransformerSklearnNode Implements the Birch clustering algorithm.
CalibratedClassifierCVSklearnNode Probability calibration with isotonic regression or sigmoid.
CountVectorizerTransformerSklearnNode Convert a collection of text documents to a matrix of token counts
DecisionTreeClassifierSklearnNode A decision tree classifier.
DecisionTreeRegressorSklearnNode A decision tree regressor.
DictVectorizerTransformerSklearnNode Transforms lists of feature-value mappings to vectors.
DictionaryLearningTransformerSklearnNode Dictionary learning
ElasticNetCVRegressorSklearnNode Elastic Net model with iterative fitting along a regularization path
ElasticNetRegressorSklearnNode Linear regression with combined L1 and L2 priors as regularizer.
ExtraTreeClassifierSklearnNode An extremely randomized tree classifier.
ExtraTreeRegressorSklearnNode An extremely randomized tree regressor.
ExtraTreesClassifierSklearnNode An extra-trees classifier.
ExtraTreesRegressorSklearnNode An extra-trees regressor.
FactorAnalysisTransformerSklearnNode Factor Analysis (FA)
FeatureAgglomerationTransformerSklearnNode Agglomerate features.
FeatureHasherTransformerSklearnNode Implements feature hashing, aka the hashing trick.
ForestRegressorSklearnNode Base class for forest of trees-based regressors.
FunctionTransformerSklearnNode Constructs a transformer from an arbitrary callable.
GaussianNBClassifierSklearnNode Gaussian Naive Bayes (GaussianNB)
GaussianProcessRegressorSklearnNode The Gaussian Process model class.
GaussianRandomProjectionHashTransformerSklearnNode This node has been automatically generated by wrapping the sklearn.neighbors.approximate.GaussianRandomProjectionHash class from the sklearn library.
GaussianRandomProjectionTransformerSklearnNode Reduce dimensionality through Gaussian random projection
GenericUnivariateSelectTransformerSklearnNode Univariate feature selector with configurable strategy.
GradientBoostingClassifierSklearnNode Gradient Boosting for classification.
GradientBoostingRegressorSklearnNode Gradient Boosting for regression.
GridSearchCVTransformerSklearnNode Exhaustive search over specified parameter values for an estimator.
HashingVectorizerTransformerSklearnNode Convert a collection of text documents to a matrix of token occurrences
ImputerTransformerSklearnNode Imputation transformer for completing missing values.
IncrementalPCATransformerSklearnNode Incremental principal components analysis (IPCA).
IsomapTransformerSklearnNode Isomap Embedding
IsotonicRegressionSklearnNode Isotonic regression model.
KNeighborsClassifierSklearnNode Classifier implementing the k-nearest neighbors vote.
KNeighborsRegressorSklearnNode Regression based on k-nearest neighbors.
KernelCentererTransformerSklearnNode Center a kernel matrix
KernelPCATransformerSklearnNode Kernel Principal component analysis (KPCA)
KernelRidgeRegressorSklearnNode Kernel ridge regression.
LabelBinarizerTransformerSklearnNode Binarize labels in a one-vs-all fashion
LabelEncoderTransformerSklearnNode Encode labels with value between 0 and n_classes-1.
LabelPropagationClassifierSklearnNode Label Propagation classifier
LabelSpreadingClassifierSklearnNode LabelSpreading model for semi-supervised learning
LarsCVRegressorSklearnNode Cross-validated Least Angle Regression model
LarsRegressorSklearnNode Least Angle Regression model a.k.a.
LassoCVRegressorSklearnNode Lasso linear model with iterative fitting along a regularization path
LassoLarsCVRegressorSklearnNode Cross-validated Lasso, using the LARS algorithm
LassoLarsICRegressorSklearnNode Lasso model fit with Lars using BIC or AIC for model selection
LassoLarsRegressorSklearnNode Lasso model fit with Least Angle Regression a.k.a.
LassoRegressorSklearnNode Linear Model trained with L1 prior as regularizer (aka the Lasso)
LatentDirichletAllocationTransformerSklearnNode Latent Dirichlet Allocation with online variational Bayes algorithm
LinearDiscriminantAnalysisClassifierSklearnNode Linear Discriminant Analysis
LinearRegressionSklearnNode Ordinary least squares Linear Regression.
LinearSVCClassifierSklearnNode Linear Support Vector Classification.
LinearSVRRegressorSklearnNode Linear Support Vector Regression.
LocallyLinearEmbeddingTransformerSklearnNode Locally Linear Embedding
LogisticRegressionCVClassifierSklearnNode Logistic Regression CV (aka logit, MaxEnt) classifier.
LogisticRegressionClassifierSklearnNode Logistic Regression (aka logit, MaxEnt) classifier.
MaxAbsScalerTransformerSklearnNode Scale each feature by its maximum absolute value.
MinMaxScalerTransformerSklearnNode Transforms features by scaling each feature to a given range.
MiniBatchDictionaryLearningTransformerSklearnNode Mini-batch dictionary learning
MiniBatchSparsePCATransformerSklearnNode Mini-batch Sparse Principal Components Analysis
MultiLabelBinarizerTransformerSklearnNode Transform between iterable of iterables and a multilabel format
MultiTaskElasticNetCVRegressorSklearnNode Multi-task L1/L2 ElasticNet with built-in cross-validation.
MultiTaskElasticNetRegressorSklearnNode Multi-task ElasticNet model trained with L1/L2 mixed-norm as regularizer
MultiTaskLassoCVRegressorSklearnNode Multi-task L1/L2 Lasso with built-in cross-validation.
MultiTaskLassoRegressorSklearnNode Multi-task Lasso model trained with L1/L2 mixed-norm as regularizer
MultinomialNBClassifierSklearnNode Naive Bayes classifier for multinomial models
NMFTransformerSklearnNode Non-Negative Matrix Factorization (NMF)
NearestCentroidClassifierSklearnNode Nearest centroid classifier.
NormalizerTransformerSklearnNode Normalize samples individually to unit norm.
NuSVCClassifierSklearnNode Nu-Support Vector Classification.
NuSVRRegressorSklearnNode Nu Support Vector Regression.
NystroemTransformerSklearnNode Approximate a kernel map using a subset of the training data.
OneHotEncoderTransformerSklearnNode Encode categorical integer features using a one-hot aka one-of-K scheme.
OneVsOneClassifierSklearnNode One-vs-one multiclass strategy
OneVsRestClassifierSklearnNode One-vs-the-rest (OvR) multiclass/multilabel strategy
OrthogonalMatchingPursuitCVRegressorSklearnNode Cross-validated Orthogonal Matching Pursuit model (OMP)
OrthogonalMatchingPursuitRegressorSklearnNode Orthogonal Matching Pursuit model (OMP)
OutputCodeClassifierSklearnNode (Error-Correcting) Output-Code multiclass strategy
PCATransformerSklearnNode Principal component analysis (PCA)
PassiveAggressiveClassifierSklearnNode Passive Aggressive Classifier
PassiveAggressiveRegressorSklearnNode Passive Aggressive Regressor
PatchExtractorTransformerSklearnNode Extracts patches from a collection of images
PerceptronClassifierSklearnNode Perceptron
PolynomialFeaturesTransformerSklearnNode Generate polynomial and interaction features.
ProjectedGradientNMFTransformerSklearnNode Non-Negative Matrix Factorization (NMF)
QuadraticDiscriminantAnalysisClassifierSklearnNode Quadratic Discriminant Analysis
RANSACRegressorSklearnNode RANSAC (RANdom SAmple Consensus) algorithm.
RBFSamplerTransformerSklearnNode Approximates feature map of an RBF kernel by Monte Carlo approximation of its Fourier transform.
RFECVTransformerSklearnNode Feature ranking with recursive feature elimination and cross-validated selection of the best number of features.
RFETransformerSklearnNode Feature ranking with recursive feature elimination.
RadiusNeighborsClassifierSklearnNode Classifier implementing a vote among neighbors within a given radius
RadiusNeighborsRegressorSklearnNode Regression based on neighbors within a fixed radius.
RandomForestClassifierSklearnNode A random forest classifier.
RandomForestRegressorSklearnNode A random forest regressor.
RandomTreesEmbeddingTransformerSklearnNode An ensemble of totally random trees.
RandomizedLassoTransformerSklearnNode Randomized Lasso.
RandomizedLogisticRegressionTransformerSklearnNode Randomized Logistic Regression
RandomizedPCATransformerSklearnNode Principal component analysis (PCA) using randomized SVD
RandomizedSearchCVTransformerSklearnNode Randomized search on hyper parameters.
RidgeCVRegressorSklearnNode Ridge regression with built-in cross-validation.
RidgeClassifierCVSklearnNode Ridge classifier with built-in cross-validation.
RidgeClassifierSklearnNode Classifier using Ridge regression.
RidgeRegressorSklearnNode Linear least squares with l2 regularization.
RobustScalerTransformerSklearnNode Scale features using statistics that are robust to outliers.
SGDClassifierSklearnNode Linear classifiers (SVM, logistic regression, a.o.) with SGD training.
SGDRegressorSklearnNode Linear model fitted by minimizing a regularized empirical loss with SGD
SVCClassifierSklearnNode C-Support Vector Classification.
SVRRegressorSklearnNode Epsilon-Support Vector Regression.
SelectFdrTransformerSklearnNode Filter: Select the p-values for an estimated false discovery rate
SelectFprTransformerSklearnNode Filter: Select the pvalues below alpha based on a FPR test.
SelectFromModelTransformerSklearnNode Meta-transformer for selecting features based on importance weights.
SelectFweTransformerSklearnNode Filter: Select the p-values corresponding to Family-wise error rate
SelectKBestTransformerSklearnNode Select features according to the k highest scores.
SelectPercentileTransformerSklearnNode Select features according to a percentile of the highest scores.
SkewedChi2SamplerTransformerSklearnNode Approximates feature map of the “skewed chi-squared” kernel by Monte Carlo approximation of its Fourier transform.
SparseCoderTransformerSklearnNode Sparse coding
SparsePCATransformerSklearnNode Sparse Principal Components Analysis (SparsePCA)
SparseRandomProjectionTransformerSklearnNode Reduce dimensionality through sparse random projection
StandardScalerTransformerSklearnNode Standardize features by removing the mean and scaling to unit variance
TfidfTransformerSklearnNode Transform a count matrix to a normalized tf or tf-idf representation
TfidfVectorizerTransformerSklearnNode Convert a collection of raw documents to a matrix of TF-IDF features.
TheilSenRegressorSklearnNode Theil-Sen Estimator: robust multivariate regression model.
TruncatedSVDTransformerSklearnNode Dimensionality reduction using truncated SVD (aka LSA).
VarianceThresholdTransformerSklearnNode Feature selector that removes all low-variance features.
VotingClassifierSklearnNode Soft Voting/Majority Rule classifier for unfitted estimators.

sink


sink Collect incoming signal types for further processing or to store in datasets

analyzer_sink.AnalyzerSinkNode Store all TimeSeries that are passed to it in an collection of type AnalyzerCollection
classification_performance_sink.LeaveOneOutSinkNode Request the leave one out metrics from the input node
classification_performance_sink.PerformanceSinkNode Calculate performance measures from standard prediction vectors and store them
classification_performance_sink.SlidingWindowSinkNode Calculate and store performance measures from classifications of sliding windows
feature_vector_sink.FeatureVectorSinkNode Collect all FeatureVector elements that are passed through it in a collection of type feature_vector.
nil_sink.NilSinkNode Store only meta information and perform training and testing
nil_sink.OnlyTrainSinkNode Store only meta information and perform training but not testing
prediction_vector_sink.PredictionVectorSinkNode Collect all PredictionVectorDataset elements that are passed through it in a collection of type prediction_vector.
ssnr_sink.SSNRSinkNode Sink node that collects SSNR metrics in actual and virtual sensor space.
time_series_sink.TimeSeriesSinkNode Collect all time series objects in a collection

source


source Load a special signal or data type as a stream of samples

external_generator_source.ExternalGeneratorSourceNode Yield the data provided by an external generator
feature_vector_source.FeatureVectorSourceNode Source for samples of type FeatureVector
prediction_vector_source.PredictionVectorSourceNode Source for samples of type
random_time_series_source.RandomTimeSeriesSourceNode Generate random data and act as a source for windowed TimeSeries
test_source_nodes.DataGenerationTimeSeriesSourceNode Generate data of two classes for testing
test_source_nodes.SimpleTimeSeriesSourceNode A simple test class for unit tests
time_series_source.Stream2TimeSeriesSourceNode Transformation of streaming data to windowed time series
time_series_source.TimeSeries2TimeSeriesSourceNode Source for streamed time series data for later windowing
time_series_source.TimeSeriesSourceNode Source for windowed TimeSeries saved in pickle format via TimeSeriesSinkNode

spatial_filtering


spatial_filtering Erase and/or recombine channels of multivariate TimeSeries

channel_difference.HemisphereDifferenceNode Build new EEG channels using the difference between left and right hemisphere of the brain
channel_selection.ChannelNameSelectorNode Project onto a subset of channels based on their name
channel_selection.ConstantChannelCleanupNode Remove channels that contain invalid(e.g.
csp.CSPNode Common Spatial Pattern filtering
fda.FDAFilterNode Reuse the implementation of Fisher’s Discriminant Analysis provided by mdp
ica.ICAWrapperNode Wrapper around the Independent Component Analysis filtering of mdp
pca.PCAWrapperNode Reuse the implementation of the Principal Component Analysis of mdp
rereferencing.AverageReferenceNode Rereference EEG signal against the average of a selected set of electrodes
rereferencing.LaplacianReferenceNode Apply the Laplacian spatial filter
sensor_selection.SensorSelectionRankingNode Iteratively choose sensors depending on a ranking function
sensor_selection.SensorSelectionSSNRNode Select sensors based on maximizing the SSNR
spatial_filtering.SpatialFilteringNode Base class for spatial filters and simple channel reduction
xdawn.AXDAWNNode Adaptive xDAWN spatial filter for enhancing event-related potentials.
xdawn.SparseXDAWNNode Sparse xDAWN spatial filter for enhancing event-related potentials.
xdawn.XDAWNNode xDAWN spatial filter for enhancing event-related potentials.

splitter


splitter Control how data is split into training and testing data

all_train_splitter.AllTrainSplitterNode Use all available data for training
cv_splitter.CrossValidationSplitterNode Perform (stratified) cross-validation
traintest_splitter.TrainTestSplitterNode Split data into one training and one test data set with a fixed ratio
transfer_splitter.TransferSplitterNode Allow to split data into training and test data sets according to different window definitions

type_manipulation


type_manipulation Manipulation of the data data_types

change_attributes.ChangeTimeSeriesAttributesNode Change the attributes of incoming TimeSeries
float_conversion.Int2FloatNode Converts all the entries in the data set to either
float_conversion.NaN2NumberNode Converts all the NaN enetries in the data set to 0.0
marker_to_mux_channel.MarkerToMuxChannelNode Extract markers of time series object and convert them to a normal data channel.
type_conversion.CastDatatypeNode Changes the datatype of the data
type_conversion.Feature2MonoTimeSeriesNode Convert feature vector to time series with only one time stamp
type_conversion.FeatureVector2TimeSeriesNode Convert feature vector to time series
type_conversion.Features2PredictionNode Use the feature vectors as prediction values
type_conversion.MonoTimeSeries2FeatureNode Convert time series with only one time stamp to feature vector
type_conversion.Prediction2FeaturesNode Use the prediction values as features

visualization


visualization Visualize the single different data samples or averages

average_and_feature_vis.AverageFeatureVisNode Visualize time domain features in the context of average time series.
eeg_visualization.ElectrodeCoordinationPlotNode Node for plotting EEG time series as topographies.
feature_vector_vis.LLEVisNode Show a 2d scatter plot of all FeatureVector based on Locally Linear Embedding (LLE) from MDP
feature_vector_vis.MnistVizNode Node for plotting MNIST Data
time_series_vis.HistogramPlotNode Creates a histogram of the given channels for the given point in time
time_series_vis.ScatterPlotNode Creates a scatter plot of the given channels for the given point in time
time_series_vis.SpectrumPlotNode Construct spectrogram of the data using FFT
time_series_vis.TimeSeriesPlotNode A node that allows to monitor the processing of time series

Mapping of Node Names to Class Names

Mapping of Class Names to Node Names