This node is the start of the feature selection loop. The
feature selection loop allows you to select, from all the features in
the input data set, the subset of features that is best for model
construction.
With this node you determine (i) which features/columns
are to be held
fixed in the selection process.
These constant or
"static" features/columns are included in each loop
iteration and are
exempt from elimination; (ii) which selection
strategy is to be used
on the other (variable) features/columns and
its settings; and (iii)
the specific settings of the selected strategy.
The following feature selection strategies are available:
- Forward Feature Selection is an iterative approach. It starts with having no feature selected. In each iteration, the feature that improves the model the most is added to the feature set.
- Backward Feature Elimination is an iterative approach. It starts with having all features selected. In each iteration, the feature that has on its removal the least impact on the models performance is removed.
- Genetic Algorithm is a stochastic approach that bases its optimization on the mechanics of biological evolution and genetics. Similar to natural selection, different solutions (individuals) are carried and mutated from generation to generation based on their performance (fitness). This approach converges into a local optimum and enabling early stopping might be recommended. See, e.g., this article for more insights.
- Random is a simple approach that selects feature combinations randomly. There is no converging and by chance (one of) the best feature combination will be drawn in an early iteration, so that early stopping might be recommended.
Options
Advanced Options
Popular Predecessors
- Column Filter11 %
- Numeric Binner4 %
- Partitioning4 %
Number To String3 %- Normalizer3 %
Excel Reader (XLS)3 %- CSV Reader2 %
File Reader2 %- Feature Selection Loop Start (1:1)2 %
- Number to String2 %
- Math Formula (Multi Column)1 %
Linear Correlation1 %- Missing Value1 %
- Category to Number1 %
Excel Reader (XLS)1 %- Math Formula1 %
- Excel Reader1 %
Row Filter (deprecated)< 1 %- X-Partitioner< 1 %
Numeric Scorer< 1 %- SMOTE< 1 %
- Table Manipulator< 1 %
- Table Creator< 1 %
List Files< 1 %- Constant Value Column< 1 %
- Value Counter< 1 %
- Missing Value Column Filter< 1 %
- Low Variance Filter< 1 %
- Parameter Optimization Loop Start< 1 %
- Group Loop Start< 1 %
- Concatenate< 1 %
- Column Resorter< 1 %
- Table Row to Variable< 1 %
- Scorer< 1 %
- Double to Integer< 1 %
Table Row To Variable Loop Start< 1 %Column Rename< 1 %- Row Sampling< 1 %
- Shuffle< 1 %
- Color Manager< 1 %
- Numeric Scorer< 1 %
- Random Forest Predictor< 1 %
- RowID< 1 %
- String Manipulation (Variable)< 1 %
- Parameter Optimization Loop End< 1 %
- Normalizer (Apply)< 1 %
Transfer Files< 1 %- Table Reader< 1 %
- Counting Loop Start< 1 %
- ARFF Reader< 1 %
CSV Reader< 1 %- Java Snippet< 1 %
- Feature Selection Loop End< 1 %
- Auto-Binner< 1 %
- Number to Category (Apply)< 1 %
- One to Many< 1 %
- Correlation Filter< 1 %
- Domain Calculator< 1 %
- Reference Column Filter< 1 %
Row Splitter (deprecated)< 1 %- GroupBy< 1 %
- String Manipulation< 1 %
- String Replacer< 1 %
- Numeric Outliers< 1 %
Database Reader< 1 %- Feature Selection Filter< 1 %
- MDS< 1 %
- PCA< 1 %
- String to Number< 1 %
- Constant Value Column Filter< 1 %
- Missing Value (Apply)< 1 %
- Normalizer (PMML)< 1 %
- Rule Engine< 1 %
- Statistics< 1 %
- Data Generator< 1 %
- File Reader< 1 %
- Column Appender< 1 %
- Joiner< 1 %
- Expand Bit Vector< 1 %
Naive Bayes Learner< 1 %String To Number< 1 %- Lag Column< 1 %
- Column Splitter< 1 %
- JSON to Table< 1 %
- Feature Selection Loop Start (2:2)< 1 %
Number To String (PMML)< 1 %- Number to String (PMML)< 1 %
- ROC Curve (legacy)< 1 %
Generic Loop Start< 1 %- Target Shuffling< 1 %
- Equal Size Sampling< 1 %
- Table Transposer< 1 %
Table Row to Variable< 1 %- Denormalizer< 1 %
- Sorter< 1 %
- Rule-based Row Filter< 1 %
- Category to Number (Apply)< 1 %
- Math Formula (Variable)< 1 %
- Integer Configuration< 1 %
- Remove Empty Rows< 1 %
- RDKit Descriptor Calculation< 1 %
CSV Writer< 1 %Counting Loop Start< 1 %PCA Apply< 1 %- Cell Splitter By Position< 1 %
Merge Variables< 1 %- String Input (legacy)< 1 %
- Molecular Properties< 1 %
- String Similarity< 1 %
- Range Filter< 1 %
Table Reader< 1 %Recursive Loop Start< 1 %- k-Means< 1 %
Scorer< 1 %- Linear Correlation< 1 %
- Number Rounder< 1 %
- Rule-based Row Splitter< 1 %
- Cache< 1 %
- Counter Generation< 1 %
Column Selection Configuration< 1 %- Scatter Plot (JavaScript)< 1 %
- R Source (Table)< 1 %
- Linear Regression Learner< 1 %
- Logistic Regression Learner< 1 %
- Random Forest Learner< 1 %
- Row Filter (Labs)< 1 %
- Reference Column Resorter< 1 %
- Scorer (JavaScript)< 1 %
Table Row to Variable< 1 %K Nearest Neighbor< 1 %PCA< 1 %- Regression Predictor< 1 %
Column Appender< 1 %Joiner< 1 %- Rank< 1 %
Rank Correlation< 1 %- Spark to Table< 1 %
- Random Label Assigner< 1 %
- Prediction Fusion< 1 %
XLS Reader< 1 %- Moving Average< 1 %
- String to Date/Time (legacy)< 1 %
Auto Active Learn Loop End< 1 %- Binary Objects to Strings< 1 %
- Inject Variables (Data)< 1 %
Table Column to Variable< 1 %Database Connection Table Reader< 1 %Backward Feature Elimination Start (2:2)< 1 %Loop End< 1 %Recursive Loop End< 1 %- X-Aggregator< 1 %
- Naive Bayes Learner< 1 %
- Decision Tree Learner< 1 %
- SVM Predictor< 1 %
- PCA Compute< 1 %
- PCA Inversion< 1 %
- Tree Ensemble Learner< 1 %
Tree Ensemble Predictor< 1 %- Case Converter< 1 %
Cell Splitter< 1 %- Column Rename (Regex)< 1 %
- CAIM Binner< 1 %
- Edit Numeric Domain< 1 %
- Nominal Value Row Filter< 1 %
- Pivot< 1 %
- Column Filter (PMML)< 1 %
- Kaplan-Meier Estimator< 1 %
- End IF< 1 %
- IF Switch< 1 %
- Crosstab< 1 %
- Parallel Chunk Start< 1 %
- DB Reader< 1 %
- One Row to Many< 1 %
- TimeDelay Loop Start< 1 %
- Similarity Search< 1 %
- Boosting Learner Loop Start< 1 %
- Column Expressions< 1 %
- Java Snippet (simple)< 1 %
- Column Filter (legacy)< 1 %
- Multiple Selection Widget< 1 %
Python Script (1⇒1)< 1 %- String to Date&Time< 1 %
- RDKit From Molecule< 1 %
- RDKit Fingerprint< 1 %
Flow Variable IF Switch (Flow Variable Value)< 1 %- Java Edit Variable< 1 %
- Table Row to Variable Loop Start< 1 %
- Naive Bayes Predictor< 1 %
- K Nearest Neighbor< 1 %
- Polynomial Regression Learner< 1 %
- PCA Apply< 1 %
- Random Forest Learner (Regression)< 1 %
- Column Name Extractor< 1 %
- Column Merger< 1 %
- String to Number (PMML)< 1 %
- Data Explorer< 1 %
- Linear Discriminant Analysis< 1 %
CASE Switch Variable (Start)< 1 %- Distance Matrix Reader< 1 %
- PMML Predictor< 1 %
- Voting Loop End< 1 %
- H2O Random Forest Learner< 1 %
- Column Filter Configuration< 1 %
Views
- This node has no views
Workflows
01_AnalyticsKNIME Hub- 01_AnalyticsKNIME Hub
- 01_Bike_Restocking_Alert_Training_w_Feature_SelectionKNIME Hub
- 01_Feature_Elimination_Done_ManuallyKNIME Hub
- 01_Feature_Elimination_with_Naive_BayesKNIME Hub
- Show all 140 workflows
Links
- KNIME E-Learning Course: Section 7.2. Re-executing Workflow Parts: Loopswww.knime.com/knime-introductory-course/chapter7/section2
- Feature selection-exercise- I am not understanding how to doby stelfrich on 2018-09-28forum.knime.com/p/48193
Developers
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.