This node trains a support vector machine on the input data. It supports a number of different kernels (HyperTangent, Polynomial and RBF). The SVM learner supports multiple class problems as well (by computing the hyperplane between each class and the rest), but note that this will increase the runtime.
The SVM learning algorithm used is described in the following papers: Fast Training of Support Vector Machines using Sequential Minimal Optimization, by John C. Platt and Improvements to Platt's SMO Algorithm for SVM Classifier Design, by S. S. Keerthi et. al.
Options
Popular Predecessors
- Partitioning21 %
- Normalizer7 %
- X-Partitioner7 %
Scorer5 %- Parameter Optimization Loop Start4 %
- Column Filter4 %
String To Number2 %Excel Reader (XLS)2 %- Number to String2 %
- CSV Reader2 %
- SMOTE2 %
- File Reader1 %
- One to Many1 %
- Equal Size Sampling1 %
- Missing Value1 %
- SVM Predictor< 1 %
- Row Filter< 1 %
PCA< 1 %- String to Number< 1 %
- Excel Reader< 1 %
Linear Correlation< 1 %- Table Reader< 1 %
Database Reader< 1 %- Row Sampling< 1 %
- Scorer< 1 %
- Normalizer (Apply)< 1 %
- Chunk Loop Start< 1 %
- Category to Number< 1 %
- Numeric Scorer< 1 %
- Bootstrap Sampling< 1 %
Column Appender< 1 %- Column Splitter< 1 %
Excel Reader (XLS)< 1 %- Table Row to Variable< 1 %
Table Row To Variable Loop Start< 1 %CSV Reader< 1 %File Reader< 1 %Column Rename< 1 %- String Replacer< 1 %
- k-Means< 1 %
- Naive Bayes Learner< 1 %
- Category to Number (Apply)< 1 %
Number To String (PMML)< 1 %- Parameter Optimization Loop End< 1 %
- Table Creator< 1 %
- Column Aggregator< 1 %
- Normalizer (PMML)< 1 %
- String Manipulation< 1 %
- Scatter Plot (JavaScript)< 1 %
- Number to String (PMML)< 1 %
- Table View (JavaScript)< 1 %
- ROC Curve (JavaScript)< 1 %
- Parameter Optimization Loop Start (Table)< 1 %
Loop End< 1 %Naive Bayes Predictor< 1 %- Logistic Regression Predictor< 1 %
- Math Formula< 1 %
- Feature Selection Loop Start (1:1)< 1 %
- Data Explorer< 1 %
- Statistics< 1 %
- Data Generator< 1 %
- LIBSVMPredictor< 1 %
XLS Reader< 1 %- Extract Table Spec< 1 %
- Table Row to Variable Loop Start< 1 %
- Table Manipulator< 1 %
- Value Counter< 1 %
- ARFF Reader< 1 %
Table Reader< 1 %- Feature Selection Filter< 1 %
Interval Loop Start< 1 %- PNN Predictor< 1 %
- Decision Tree Predictor< 1 %
- Linear Regression Learner< 1 %
- Logistic Regression Learner< 1 %
- Concatenate< 1 %
- Correlation Filter< 1 %
- Row Splitter< 1 %
- GroupBy< 1 %
- Rule Engine< 1 %
CASE Switch Data (Start)< 1 %- Color Manager< 1 %
- ROC Curve (legacy)< 1 %
- Category to Class< 1 %
- Document Vector< 1 %
- Naive Bayes Predictor< 1 %
- Cluster Assigner< 1 %
- PCA< 1 %
- Random Forest Learner< 1 %
- Column Expressions< 1 %
- Binary Objects to Strings< 1 %
- File Reader (Complex Format)< 1 %
- Joiner< 1 %
- Math Formula (Variable)< 1 %
- Table Column to Variable< 1 %
Naive Bayes Learner< 1 %K Nearest Neighbor< 1 %- Numeric Binner< 1 %
- Expand Bit Vector< 1 %
Joiner< 1 %String To Number (PMML)< 1 %Document vector< 1 %Variable to Table Row< 1 %Excel Reader (XLS)< 1 %- String to Date&Time< 1 %
- RDKit Fingerprint< 1 %
- Canonical SMILES< 1 %
- Column Filter (legacy)< 1 %
- X-Aggregator< 1 %
Numeric Scorer< 1 %Random Forest Predictor< 1 %- Random Forest Predictor< 1 %
Number To String< 1 %- Missing Value (Apply)< 1 %
- Rule-based Row Filter< 1 %
- Rule-based Row Splitter< 1 %
- Extract Table Dimension< 1 %
- RDKit Descriptor Calculation< 1 %
Table Row to Variable< 1 %Counting Loop Start< 1 %- Nominal Value Row Filter< 1 %
- String Manipulation (Variable)< 1 %
- Linear Discriminant Analysis Apply< 1 %
- Box Plot (legacy)< 1 %
- Shape Manager< 1 %
- 3D Scatter Plot (Plotly)< 1 %
- TF< 1 %
- Fingerprint From Binary String< 1 %
- String to Number (PMML)< 1 %
- RDKit Canon SMILES< 1 %
- Outlier Removal< 1 %
Random Forest Learner< 1 %Cell Splitter< 1 %- Number to Category (Apply)< 1 %
- Missing Value Column Filter< 1 %
- Reference Row Filter< 1 %
- Low Variance Filter< 1 %
Linear Discriminant Analysis< 1 %Merge Variables< 1 %- Parallel Chunk Start< 1 %
Strings To Document< 1 %- Double Input (legacy)< 1 %
- Python Source (legacy)< 1 %
- R Source (Table)< 1 %
- Strings to Binary Objects< 1 %
- Try (Data Ports)< 1 %
- Extract Variables (Data)< 1 %
Database Connection Table Reader< 1 %Backward Feature Elimination Start (1:1)< 1 %Generic Loop Start< 1 %- PNN Learner (DDA)< 1 %
- DBSCAN< 1 %
- Decision Tree Learner< 1 %
- PCA Apply< 1 %
- Auto-Binner< 1 %
- Table Validator< 1 %
- Edit Nominal Domain< 1 %
- Column Filter (PMML)< 1 %
- IF Switch< 1 %
- HiLite Table (legacy)< 1 %
- K Nearest Neighbor (Distance Function)< 1 %
- Similarity Search< 1 %
- Parallel Coordinates Plot (JavaScript)< 1 %
- PMML Predictor< 1 %
Read Excel Sheet Names (XLS)< 1 %- Java Edit Variable (simple)< 1 %
- Bag Of Words Creator< 1 %
- Duration to Number< 1 %
- Fingerprints< 1 %
- Catch Errors (Data Ports)< 1 %
- Model Loop Start< 1 %
- Split Collection Column< 1 %
Table Row to Variable< 1 %Recursive Loop End< 1 %- Fuzzy Rule Learner< 1 %
- Hierarchical Clustering< 1 %
- MultiLayerPerceptron Predictor< 1 %
PCA Apply< 1 %- Association Rule Learner< 1 %
- Create Bit Vector< 1 %
- Domain Calculator< 1 %
- Double to Integer< 1 %
- Reference Column Filter< 1 %
- RowID< 1 %
- Shuffle< 1 %
- Numeric Outliers< 1 %
- Timer Info< 1 %
- SDF Reader< 1 %
Vocabulary Extractor (legacy)< 1 %- Document Data Extractor< 1 %
- Document Vector Hashing Applier< 1 %
- Gaussian Convolution< 1 %
Python Script (1⇒1)< 1 %- R Snippet< 1 %
- Canvas Fingerprint Reader< 1 %
- PLS Model Building< 1 %
- Table Row To Variable Run-for-time Loop Start< 1 %
- logP< 1 %
- Maccs Fingerprint< 1 %
- MolImporter< 1 %
- Polar Surface Area< 1 %
- Active Learning Loop End< 1 %
Exploration/Exploitation Scorer< 1 %- Create Collection Column< 1 %
Variable to Table Column< 1 %- Inject Variables (Data)< 1 %
Line Reader< 1 %List Files< 1 %- Java Snippet< 1 %
Loop End (2 ports)< 1 %- Column List Loop Start< 1 %
- Fuzzy Rule Predictor< 1 %
PCA Compute< 1 %- Polynomial Regression Learner< 1 %
- Regression Predictor< 1 %
- SVM Learner< 1 %
- PCA Compute< 1 %
- Random Forest Learner (Regression)< 1 %
- Create Byte Vector< 1 %
- Expand Byte Vector< 1 %
Cell Replacer< 1 %- Column Auto Type Cast< 1 %
- String to SVG< 1 %
- Lag Column< 1 %
- Column Merger< 1 %
- Cross Joiner< 1 %
- Edit Numeric Domain< 1 %
- Filter Apply Row Splitter< 1 %
- Nominal Value Row Splitter< 1 %
- Row Filter (Labs)< 1 %
- Denormalizer< 1 %
- Pivot< 1 %
- One to Many (PMML)< 1 %
- Numeric Row Splitter< 1 %
- Sorter< 1 %
String Replace (Dictionary)< 1 %- Cronbach Alpha< 1 %
Rank Correlation< 1 %CASE Switch Data (End)< 1 %- Cache< 1 %
- Conditional Box Plot (legacy)< 1 %
- Fingerprint Bayesian Learner< 1 %
- Distance Matrix Calculate< 1 %
- k-Medoids< 1 %
- Boosting Learner Loop End< 1 %
- Boosting Learner Loop Start< 1 %
PMML Predictor< 1 %- Prediction Fusion< 1 %
Read XLS Sheet Names< 1 %- Java Snippet (simple)< 1 %
- Word Vector Apply (legacy)< 1 %
- IDF< 1 %
- Case Converter< 1 %
Dictionary tagger< 1 %- Strings to Document< 1 %
- Term Vector< 1 %
- Boolean Input (legacy)< 1 %
- Columns to JSON< 1 %
- JSON to Table< 1 %
- Image to DataRow< 1 %
Python Script (1⇒1)< 1 %Python Edit Variable< 1 %- Date&Time Difference< 1 %
- Date&Time to String< 1 %
Extract Date&Time Fields< 1 %- Moving Aggregator< 1 %
- Gaussian< 1 %
- Variable Creator< 1 %
- Feature Selection Loop Start (2:2)< 1 %
- Counting Loop Start< 1 %
- Tree Ensemble Learner< 1 %
- Tree Ensemble Learner (Regression)< 1 %
- Column Resorter< 1 %
- Normalizer Apply (PMML)< 1 %
- Nominal Probability Distribution Creator< 1 %
- Ungroup< 1 %
- Rule Engine Variable< 1 %
- Ruleset to Table< 1 %
- Standardized Cronbach Alpha< 1 %
- Linear Discriminant Analysis< 1 %
- DB Reader< 1 %
- DB Query Reader< 1 %
- Nominal Row Filter Configuration< 1 %
- Double Configuration< 1 %
- Integer Configuration< 1 %
- Python Script (legacy)< 1 %
- Create Date&Time Range< 1 %
- Remove Empty Rows< 1 %
Views
- SVM View
- Shows the trained Support Vector Machines for each class with their corresponding support vectors.
Workflows
Credit Scoring Model(diksha kumari)KNIME Hub- (test) credit score modelKNIME Hub
- 01_Combining_Classifiers_using_Prediction_FusionKNIME Hub
- 01_CreditScoringKNIME Hub
- 01_CreditScoringKNIME Hub
- Show all 371 workflows
Links
- What do “SVM Learner” parameters mean?by taka on 2019-07-17forum.knime.com/p/65726
- Export PMML that outputs class probabilitiesby mlauber71 on 2019-01-22forum.knime.com/p/53278
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.