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 light gray diagonal line in the diagram is the random line which is the worst possible performance a
model can achieve.
Options
Popular Predecessors
Random Forest Predictor11 %Naive Bayes Predictor11 %K Nearest Neighbor8 %Regression Predictor6 %Number To String5 %Gradient Boosted Trees Predictor5 %Numeric Scorer4 %- Logistic Regression Predictor4 %
Tree Ensemble Predictor3 %- Scorer3 %
- Decision Tree Predictor2 %
- SVM Predictor2 %
Random Forest Predictor2 %- Random Forest Predictor2 %
Random Forest Learner1 %Naive Bayes Learner< 1 %- ROC Curve (JavaScript)< 1 %
Scorer< 1 %Tree Ensemble Predictor< 1 %Column Appender< 1 %Logistic Regression Learner< 1 %- Naive Bayes Predictor< 1 %
- Joiner< 1 %
- X-Aggregator< 1 %
- Gradient Boosted Trees Predictor< 1 %
PMML Predictor< 1 %Concatenate (Optional in)< 1 %- Decision Tree to Ruleset< 1 %
- Naive Bayes Learner< 1 %
- Numeric Scorer< 1 %
- Tree Ensemble Predictor< 1 %
- ROC Curve (legacy)< 1 %
Excel Reader (XLS)< 1 %- Java Snippet< 1 %
Linear Correlation< 1 %- Cluster Assigner< 1 %
- MultiLayerPerceptron Predictor< 1 %
Tree Ensemble Learner< 1 %K Nearest Neighbor (Distance Function)< 1 %String To Number (PMML)< 1 %Simple Regression Tree Predictor< 1 %Excel Reader (XLS)< 1 %- K Nearest Neighbor< 1 %
- Value Counter< 1 %
- Parameter Optimization Loop End< 1 %
PMML Ensemble Predictor< 1 %- Group Loop Start< 1 %
- Color Manager< 1 %
XLS Reader< 1 %- JPMML Classifier< 1 %
- Table View (JavaScript)< 1 %
- XGBoost Predictor (Regression)< 1 %
Table Reader< 1 %- k-Means< 1 %
- SOTA Predictor< 1 %
- Nominal Value Row Filter< 1 %
Row Splitter (deprecated)< 1 %Joiner< 1 %Number To String (PMML)< 1 %- Rule Engine< 1 %
DL Network Executor< 1 %Binary Scorer< 1 %- Threshold Analyzer< 1 %
- Decision Tree View (JavaScript)< 1 %
- File Reader< 1 %
PCA Compute< 1 %- Regression Predictor< 1 %
PMML Gradient Boosted Trees Predictor< 1 %- Simple Regression Tree Predictor< 1 %
- Prediction Fusion< 1 %
- Text Classifier Predictor< 1 %
- Number to String< 1 %
- String to Number (PMML)< 1 %
- Column Appender< 1 %
- Excel Reader< 1 %
- BERT Predictor< 1 %
Database Reader< 1 %Random Forest Predictor (Regression)< 1 %- Random Forest Learner< 1 %
- Concatenate< 1 %
- Auto-Binner< 1 %
- Category to Number< 1 %
- One to Many< 1 %
- Cross Joiner< 1 %
- Equal Size Sampling< 1 %
- Missing Value Column Filter< 1 %
- GroupBy< 1 %
- Sorter< 1 %
- Rule-based Row Filter< 1 %
- Statistics< 1 %
- LIBSVMPredictor< 1 %
- Weka Predictor (3.7)< 1 %
- Scorer (JavaScript)< 1 %
- XGBoost Predictor< 1 %
- ARFF Reader< 1 %
- Silhouette Coefficient< 1 %
- String to Number< 1 %
- Pivot< 1 %
- Number to String (PMML)< 1 %
- Column Expressions< 1 %
- Numeric Outliers< 1 %
Loop End< 1 %- X-Partitioner< 1 %
- Fuzzy Rule Predictor< 1 %
- PNN Predictor< 1 %
- Hierarchical Clustering< 1 %
PCA< 1 %- Linear Regression Learner< 1 %
- Logistic Regression Learner< 1 %
- Entropy Scorer< 1 %
Random Forest Learner< 1 %Gradient Boosted Trees Predictor< 1 %- Gradient Boosted Trees Predictor (Regression)< 1 %
- Tree Ensemble Predictor (Regression)< 1 %
- Random Forest Predictor (Regression)< 1 %
- Bootstrap Sampling< 1 %
- Column Resorter< 1 %
- Double to Integer< 1 %
- Column Filter< 1 %
Row Filter (deprecated)< 1 %- Denormalizer< 1 %
- Normalizer< 1 %
- Partitioning< 1 %
- Missing Value< 1 %
Column Rename< 1 %- Crosstab< 1 %
- Lift Chart (legacy)< 1 %
- H2O to Table< 1 %
- Math Formula< 1 %
- Scatter Plot (JavaScript)< 1 %
- R to Table< 1 %
Loop End (3 ports)< 1 %- Strings to Binary Objects< 1 %
- Edit Nominal Domain< 1 %
- Data Explorer< 1 %
- K Nearest Neighbor (Distance Function)< 1 %
- PMML Predictor< 1 %
- H2O Binomial Scorer< 1 %
- CSV Reader< 1 %
- Weka Predictor (3.6) (legacy)< 1 %
- Moving Average< 1 %
Binary Scorer< 1 %- Low Variance Filter< 1 %
- Column Renamer< 1 %
- Unpivot< 1 %
File Reader< 1 %Backward Feature Elimination Filter< 1 %Cell Splitter< 1 %- Column Comparator< 1 %
- HiLite Table (legacy)< 1 %
- Extract Color< 1 %
- Distance Matrix Calculate< 1 %
DL4J Feedforward Predictor (legacy)< 1 %- DL4J Feedforward Predictor (Classification) (legacy)< 1 %
H2O Binomial Scorer< 1 %Excel Reader (XLS)< 1 %- R Predictor< 1 %
- Feature Selection Filter< 1 %
- Tree Ensemble Learner< 1 %
- Table Manipulator< 1 %
- Lift Chart (JavaScript)< 1 %
- Random Forest Learner (Regression)< 1 %
Cell Replacer< 1 %- Normalizer (Apply)< 1 %
- Missing Value (Apply)< 1 %
- Shape Manager< 1 %
- H2O Numeric Scorer< 1 %
- String Input (legacy)< 1 %
Counting Loop Start< 1 %- PMML Gradient Boosted Trees Predictor< 1 %
- Linear Discriminant Analysis Apply< 1 %
- H2O MOJO Predictor (Classification)< 1 %
- Weka Cluster Assigner (3.7)< 1 %
Python Script (1⇒1)< 1 %- Moving Aggregator< 1 %
Backward Feature Elimination Start (1:1)< 1 %- Loop End (Column Append)< 1 %
- PNN Learner (DDA)< 1 %
Tree Ensemble Learner< 1 %- Column Renamer (Dictionary)< 1 %
- Correlation Filter< 1 %
- Rule-based Row Splitter< 1 %
CASE Switch Data (Start)< 1 %- PMML to SQL< 1 %
- Fingerprint Bayesian Predictor< 1 %
- k-Medoids< 1 %
- PMML to Cell< 1 %
- Voting Loop End< 1 %
- Math Formula (Multi Column)< 1 %
- Java Snippet (simple)< 1 %
Python Predictor< 1 %- R Snippet< 1 %
- Shapefile Polygon Reader< 1 %
Loop End (2 ports)< 1 %PCA Apply< 1 %- Polynomial Regression Learner< 1 %
- Column Rename (Regex)< 1 %
- Many to One< 1 %
- One to Many (PMML)< 1 %
- Rule-based Row Filter (Dictionary)< 1 %
- Data Generator< 1 %
- Fingerprint Bayesian Learner< 1 %
H2O MOJO Predictor (Classification)< 1 %- Python Predictor (legacy)< 1 %
- RDKit Descriptor Calculation< 1 %
- RDKit Substructure Counter< 1 %
- Create Collection Column< 1 %
- Rank Correlation< 1 %
- Extract Table Spec< 1 %
- Association Rule Learner (Borgelt)< 1 %
- Date&Time-based Row Filter< 1 %
- Range Splitter< 1 %
Python Plot< 1 %- Split Collection Column< 1 %
- Inject Variables (Data)< 1 %
CSV Reader< 1 %Database Connection Table Reader< 1 %- Table Creator< 1 %
- Feature Selection Loop End< 1 %
- Feature Selection Loop Start (1:1)< 1 %
- Column List Loop Start< 1 %
Variable Condition Loop End< 1 %- Fuzzy Rule Learner< 1 %
- Fuzzy c-Means< 1 %
- DBSCAN< 1 %
- SMOTE< 1 %
- Tree Ensemble Learner (Regression)< 1 %
- Numeric Binner< 1 %
- Number to Category (Apply)< 1 %
String To Number< 1 %- Column Aggregator< 1 %
- Constant Value Column< 1 %
- Domain Calculator< 1 %
- Denormalizer (PMML)< 1 %
- RowID< 1 %
- Numeric Row Splitter< 1 %
- Row Sampling< 1 %
- Column Splitter< 1 %
- String Manipulation< 1 %
- String Replacer< 1 %
- End IF< 1 %
- Enrichment Plotter (legacy)< 1 %
Color Appender< 1 %- Spark Scorer< 1 %
- Parallel Chunk End< 1 %
- Boosting Learner Loop End< 1 %
- Boosting Predictor Loop End< 1 %
- Item Set Finder (Borgelt)< 1 %
- TF< 1 %
- Category to Class< 1 %
- Column Filter (legacy)< 1 %
Python Predictor< 1 %Python Script (2⇒2)< 1 %- Database List< 1 %
- IScreen< 1 %
- R Snippet (2:1)< 1 %
- Fingerprint Similarity< 1 %
- 2D/3D Scatterplot< 1 %
- Virtual Screening Metrics< 1 %
Element Selector< 1 %- ARIMA Predictor< 1 %
- Binary Objects to Strings< 1 %
Variable to Table Column< 1 %Table Row to Variable< 1 %Table Row To Variable Loop Start< 1 %- Chunk Loop Start< 1 %
Recursive Loop End< 1 %- Hierarchical Cluster Assigner< 1 %
- Association Rule Learner< 1 %
- PCA Compute< 1 %
Tree Ensemble Learner (Regression)< 1 %Tree Ensemble Predictor (Regression)< 1 %Random Forest Learner (Regression)< 1 %- PMML Simple Regression Tree Predictor< 1 %
- Create Bit Vector< 1 %
- Column Auto Type Cast< 1 %
- Category to Number (Apply)< 1 %
- Lag Column< 1 %
- Duplicate Row Filter< 1 %
- Extract Missing Value Cause< 1 %
- Filter Apply Row Splitter< 1 %
- Reference Row Filter< 1 %
- Column Filter (PMML)< 1 %
- Normalizer (PMML)< 1 %
- Rank< 1 %
- Reference Column Resorter< 1 %
- String Splitter (Regex)< 1 %
- Number Rounder< 1 %
- Shuffle< 1 %
- Target Shuffling< 1 %
- Table Transposer< 1 %
- Ungroup< 1 %
- Ruleset Predictor< 1 %
- One-way ANOVA< 1 %
- Single sample t-test< 1 %
- Linear Discriminant Analysis Compute< 1 %
- Linear Discriminant Analysis< 1 %
- Empty Table Switch< 1 %
- Box Plot (legacy)< 1 %
- Scatter Plot (legacy)< 1 %
- Interactive Table (legacy)< 1 %
- PMML Compiling Predictor< 1 %
- Spark Numeric Scorer< 1 %
- SDF Reader< 1 %
- Random Label Assigner< 1 %
- Similarity Search< 1 %
- DL Python Network Executor< 1 %
- PMML Ensemble Predictor< 1 %
- DL4J Feedforward Predictor (Regression) (legacy)< 1 %
H2O Random Forest Learner< 1 %Read Excel Sheet Names (XLS)< 1 %- Spark Line Appender< 1 %
- String to Term< 1 %
- Nominal Row Filter Configuration< 1 %
- Column Selection Configuration< 1 %
- Column Selection (legacy)< 1 %
- Line Plot (JavaScript)< 1 %
Python Script (1⇒1)< 1 %Python Script (2⇒1)< 1 %- Duration to Number< 1 %
Extract Date&Time Fields< 1 %- String to Date/Time (legacy)< 1 %
XML Reader< 1 %- Binned Performance< 1 %
- RDKit To InChI< 1 %
- RDKit To Molecule< 1 %
- Table to String< 1 %
- Loop End< 1 %
- PMML Gradient Boosted Trees Predictor (Regression)< 1 %
- Tree Ensemble Statistics< 1 %
- Cell Splitter< 1 %
- Column Merger< 1 %
- Linear Correlation< 1 %
- Table Validator (Reference)< 1 %
- Constant Value Column Filter< 1 %
- Row Filter (Labs)< 1 %
- Nominal Probability Distribution Creator< 1 %
- Top k Row Filter< 1 %
- Spark to Table< 1 %
- TensorFlow Network Executor< 1 %
- H2O Random Forest Learner< 1 %
- Table Editor (JavaScript)< 1 %
- Convolution Kernel Creator< 1 %
- Binary Classification Inspector< 1 %
- Python Script (legacy)< 1 %
Views
- ROC Curves
- ROC curves
Workflows
01_Guided_Analytics_for_ML_AutomationKNIME Hub- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- 01_Guided_Analytics_for_ML_AutomationKNIME Hub
- Show all 159 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.