This node draws ROC curves for two-class classification problems. The input table must contain a column with the real class values (including all class values as possible values) and a second column with the probabilities that an item (=row) will be classified as being from the selected class. Therefore only learners/predictors that output class probabilities can be used.
In order to create a ROC curve for a model, the input table is first sorted by the class probabilities for the positive class i.e. rows for which the model is certain that it belongs to the positive class are sorted to front. Then the sorted rows are checked if the real class value is the actually the positive class. If so, the ROC curve goes up one step, if not it goes one step to the right. Ideally, all positive rows are sorted to front, so you have a line going up to 100% first and then going straight to right. As a rule of thumb, the greater the area under the curve, the better is the model.
You may compare the ROC curves of several trained models by first joining the class probability columns from the different predictors into one table and then selecting several column in the column filter panel.
The black diagonal line in the diagram is the random line which is the worst possible performance a model can achieve.
Additionally a static SVG image can be rendered, which is then made available at the first output port.
Note, this node is currently under development. Future versions of the node might have more or changed functionality.
The node supports custom CSS styling. You can simply put CSS rules into a single string and set it as a flow variable 'customCSS' in the node configuration dialog. You will find the list of available classes and their description on our documentation page.
Options
ROC Curve Settings
General Plot Options
Axis Configuration
View Controls
Popular Predecessors
Joiner5 %- Scorer5 %
- Decision Tree Predictor4 %
- Logistic Regression Predictor2 %
- ROC Curve (legacy)2 %
Random Forest Predictor2 %Number To String2 %- Naive Bayes Predictor2 %
String To Number2 %- ROC Curve (JavaScript)2 %
K Nearest Neighbor2 %Naive Bayes Predictor2 %- Random Forest Predictor1 %
- Scorer (JavaScript)1 %
- XGBoost Predictor1 %
Regression Predictor1 %- Joiner1 %
- Column Appender1 %
- Regression Predictor1 %
- X-Aggregator< 1 %
Tree Ensemble Predictor< 1 %- Numeric Scorer< 1 %
- Rule Engine< 1 %
Python Script (1⇒1)< 1 %Row Filter (deprecated)< 1 %- Line Plot (JavaScript)< 1 %
- K Nearest Neighbor< 1 %
- MultiLayerPerceptron Predictor< 1 %
- PMML Predictor< 1 %
- SVM Predictor< 1 %
- Random Forest Predictor (Regression)< 1 %
- GroupBy< 1 %
- Pivot< 1 %
- One to Many< 1 %
Gradient Boosted Trees Predictor< 1 %- Weka Predictor (3.7)< 1 %
Loop End< 1 %Numeric Scorer< 1 %- Column Filter< 1 %
- Partitioning< 1 %
- Table View (JavaScript)< 1 %
- File Reader< 1 %
- PNN Predictor< 1 %
- Gradient Boosted Trees Predictor (Regression)< 1 %
- Tree Ensemble Predictor< 1 %
- Denormalizer< 1 %
Color Appender< 1 %- Spark Scorer< 1 %
- Lift Chart (JavaScript)< 1 %
- Column Comparator< 1 %
- String to Number< 1 %
- Crosstab< 1 %
- Logistic Regression Learner< 1 %
- Entropy Scorer< 1 %
- Math Formula< 1 %
- SOTA Predictor< 1 %
- Gradient Boosted Trees Predictor< 1 %
- Rule-based Row Filter< 1 %
- Lift Chart (legacy)< 1 %
- Fingerprint Bayesian Predictor< 1 %
- K Nearest Neighbor (Distance Function)< 1 %
- Rank Correlation< 1 %
- Tree Ensemble Statistics< 1 %
- Category to Number< 1 %
- Scatter Plot (JavaScript)< 1 %
- Catch Errors (Data Ports)< 1 %
- Cross Joiner< 1 %
- Numeric Outliers< 1 %
- CSV Reader< 1 %
- Data Explorer< 1 %
- Python Script (legacy)< 1 %
- Table Reader< 1 %
- Column Renamer< 1 %
File Reader< 1 %- k-Means< 1 %
- Random Forest Learner< 1 %
- Simple Regression Tree Predictor< 1 %
- Missing Value< 1 %
- Table Transposer< 1 %
- Prediction Fusion< 1 %
- LIBSVMPredictor< 1 %
- Java Snippet (simple)< 1 %
- Parameter Optimization Loop End< 1 %
- R Predictor< 1 %
- Numeric Binner< 1 %
- Number to String< 1 %
- Double to Integer< 1 %
- Reference Row Filter< 1 %
- Statistics< 1 %
- Heatmap (JavaScript)< 1 %
- Column List Loop Start< 1 %
- Number to Category (Apply)< 1 %
- Table Manipulator< 1 %
- Table Creator< 1 %
Naive Bayes Learner< 1 %- Fuzzy Rule Predictor< 1 %
Scorer< 1 %- Tree Ensemble Learner< 1 %
- Concatenate< 1 %
Concatenate (Optional in)< 1 %- Normalizer< 1 %
Column Rename< 1 %- Sorter< 1 %
- Color Manager< 1 %
- Spark to Table< 1 %
- DL4J Feedforward Predictor (Classification) (legacy)< 1 %
- H2O to Table< 1 %
- Decision Tree View (JavaScript)< 1 %
Database Reader< 1 %- Feature Selection Loop End< 1 %
- Group Loop Start< 1 %
- X-Partitioner< 1 %
- Naive Bayes Learner< 1 %
- Cluster Assigner< 1 %
- Linear Regression Learner< 1 %
- PMML Gradient Boosted Trees Predictor< 1 %
- Many to One< 1 %
- Constant Value Column< 1 %
- Linear Correlation< 1 %
- Missing Value Column Filter< 1 %
- Number to String (PMML)< 1 %
- String to Number (PMML)< 1 %
- RowID< 1 %
- String Manipulation< 1 %
- Value Counter< 1 %
- Column Expressions< 1 %
- H2O Binomial Scorer< 1 %
- String Configuration< 1 %
- XGBoost Predictor (Regression)< 1 %
- Loop End< 1 %
- Duplicate Row Filter< 1 %
- Workflow Executor< 1 %
- Excel Reader< 1 %
- Binary Classification Inspector< 1 %
- Python Predictor (legacy)< 1 %
Random Forest Predictor< 1 %Random Forest Learner< 1 %- Data Generator< 1 %
- Box Plot (legacy)< 1 %
Excel Reader (XLS)< 1 %- Fingerprint Similarity< 1 %
- PNN Learner (DDA)< 1 %
- SMOTE< 1 %
- Random Forest Learner (Regression)< 1 %
- Normalizer (Apply)< 1 %
- IF Switch< 1 %
- PMML Compiling Predictor< 1 %
- Keras Network Executor< 1 %
- Table Column to Variable< 1 %
- Ungroup< 1 %
Loop End (3 ports)< 1 %- ARFF Reader< 1 %
- Java Snippet< 1 %
Gradient Boosted Trees Predictor< 1 %Row Splitter (deprecated)< 1 %- Ruleset Predictor< 1 %
DL Network Executor< 1 %- R to Table< 1 %
- Java Edit Variable< 1 %
- Fuzzy Rule Learner< 1 %
- PCA Apply< 1 %
- Column Name Extractor< 1 %
- Rule-based Row Splitter< 1 %
CASE Switch Data (End)< 1 %H2O Binomial Scorer< 1 %- Single Selection Widget< 1 %
- Edit Nominal Domain< 1 %
- Equal Size Sampling< 1 %
- Linear Discriminant Analysis< 1 %
- Capture Workflow End< 1 %
Loop End (2 ports)< 1 %Column Appender< 1 %- String Replacer< 1 %
- Single sample t-test< 1 %
- DL4J Feedforward Predictor (Regression) (legacy)< 1 %
Python Edit Variable< 1 %PMML Gradient Boosted Trees Predictor< 1 %- Tree Ensemble Predictor (Regression)< 1 %
String To Number (PMML)< 1 %- Nominal Probability Distribution Creator< 1 %
- Ruleset Editor< 1 %
- Similarity Search< 1 %
- Parallel Coordinates Plot (JavaScript)< 1 %
- H2O Multinomial Scorer< 1 %
- Category to Class< 1 %
- Dictionary Tagger< 1 %
- Boolean Configuration< 1 %
- Value Selection (legacy)< 1 %
- Tile View (JavaScript)< 1 %
- Value Selection Widget< 1 %
Python Predictor< 1 %- Lipinski's Rule-of-Five< 1 %
- Threshold Analyzer< 1 %
- Reference Column Filter< 1 %
CASE Switch Data (Start)< 1 %- Outlier Removal< 1 %
CSV Reader< 1 %- Loop End (Column Append)< 1 %
Recursive Loop End< 1 %- Polynomial Regression Learner< 1 %
- Auto-Binner< 1 %
- Column Resorter< 1 %
- Domain Calculator< 1 %
- Column Splitter< 1 %
- SDF Reader< 1 %
XLS Reader< 1 %- Generic JavaScript View (JavaScript)< 1 %
- Table Editor (JavaScript)< 1 %
- Parameter Optimization Loop Start< 1 %
- Information Gain Calculator< 1 %
- Forge Build Machine Learning< 1 %
- Activity Profiling< 1 %
- MzTabReader< 1 %
- Fingerprint Similarity< 1 %
- Virtual Screening Metrics< 1 %
- Create Collection Column< 1 %
Variable to Table Column< 1 %Table Column to Variable< 1 %Table Row to Variable< 1 %Table Reader< 1 %- Feature Selection Filter< 1 %
Interval Loop Start< 1 %Recursive Loop End (2 ports)< 1 %- Silhouette Coefficient< 1 %
- Fuzzy c-Means< 1 %
PCA< 1 %- PCA Compute< 1 %
- PCA< 1 %
Tree Ensemble Predictor (Regression)< 1 %- PMML Simple Regression Tree Predictor< 1 %
- Binner (Dictionary)< 1 %
- Create Byte Vector< 1 %
- Column Aggregator< 1 %
Linear Correlation< 1 %- Filter Apply< 1 %
- Nominal Value Row Filter< 1 %
- Nominal Value Row Splitter< 1 %
- Row Filter (Labs)< 1 %
- Reference Row Splitter< 1 %
- Low Variance Filter< 1 %
- Missing Value (Apply)< 1 %
Number To String (PMML)< 1 %- Number Rounder< 1 %
- String Manipulation (Variable)< 1 %
- Top k Row Filter< 1 %
- Renderer to Image< 1 %
- Decision Tree to Ruleset< 1 %
- End IF< 1 %
- Extract Table Dimension< 1 %
Merge Variables< 1 %- Extract Color< 1 %
- Shape Appender< 1 %
- Shape Manager< 1 %
- Fingerprint Bayesian Learner< 1 %
- DB Reader< 1 %
K Nearest Neighbor (Distance Function)< 1 %- DL Python Network Executor< 1 %
- Sunburst Chart (JavaScript)< 1 %
- Boosting Learner Loop End< 1 %
- PMML Ensemble Predictor< 1 %
- PMML to Cell< 1 %
- External Tool< 1 %
- H2O MOJO Predictor (Classification)< 1 %
- Math Formula (Multi Column)< 1 %
- Math Formula (Variable)< 1 %
Excel Reader (XLS)< 1 %- Java Edit Variable (simple)< 1 %
- Term Co-Occurrence Counter< 1 %
- Dictionary Filter< 1 %
- Term Vector< 1 %
- Single Selection Configuration< 1 %
- CSS Editor< 1 %
- Single Selection (legacy)< 1 %
- Tag Cloud (JavaScript)< 1 %
- Column Filter Widget< 1 %
- JSON to Table< 1 %
Python Script (1⇒2)< 1 %- Moving Average< 1 %
- Fingerprint Similarity< 1 %
- RDKit Descriptor Calculation< 1 %
- MolConverter< 1 %
- Strings to Binary Objects< 1 %
- Extract Variables (Data)< 1 %
- Cell Splitter< 1 %
- Column Auto Type Cast< 1 %
- Denormalizer (PMML)< 1 %
- Rule Engine Variable< 1 %
- Standardized Cronbach Alpha< 1 %
- Linear Discriminant Analysis Compute< 1 %
- Enrichment Plotter (legacy)< 1 %
- Random Matcher< 1 %
- H2O Gradient Boosting Machine Learner< 1 %
- Radar Plot Appender< 1 %
- Document Vector< 1 %
- Boolean Widget< 1 %
- Date&Time to String< 1 %
- String to Duration< 1 %
Views
- Interactive View: ROC Curve
- Displays a ROC curve visualization of the input data.
Workflows
[Latest] Consolidated 3 Mar 1210KNIME Hub- 00 Install extensionsKNIME Hub
- 00 Install extensionsKNIME Hub
- 00 Install extensionsKNIME Hub
- 00_Decision_Tree_solutionKNIME Hub
- Show all 626 workflows
Links
- No links available
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.