ConfusionMatrix (h2o-core 3.42.0 API)

java.lang.Object
- water.Iced
- - hex.ConfusionMatrix

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, Freezable
```
public class ConfusionMatrix
extends Iced
```
See Also:

Serialized Form

Field Summary

Fields
Modifier and Type Field and Description

double[][] _cm

java.lang.String[] _domain

Fields
Modifier and Type	Field and Description
`double[][]`	`_cm`
`java.lang.String[]`	`_domain`

Constructor Summary

Constructors
Constructor and Description

ConfusionMatrix(double[][] value, java.lang.String[] domain)
Constructor for Confusion Matrix

Constructors
Constructor and Description
`ConfusionMatrix(double[][] value, java.lang.String[] domain)` Constructor for Confusion Matrix

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`double`	`accuracy()` The percentage of predictions that are correct.
`void`	`add(ConfusionMatrix other)`
`void`	`add(int i, int j)`
`double`	`class_error(int c)`
`double`	`err_count()`
`double`	`err()`
`double`	`f0point5()` Returns the F-measure which combines precision and recall and weights precision higher than recall.
`double`	`f1()` Returns the F-measure which combines precision and recall.
`double`	`f2()` Returns the F-measure which combines precision and recall and weights recall higher than precision.
`boolean`	`isBinary()`
`double`	`max_per_class_error()` The maximum per-class error
`double`	`mcc()` The Matthews Correlation Coefficient, takes true negatives into account in contrast to F-Score See MCC MCC = Correlation between observed and predicted binary classification
`double`	`mean_per_class_accuracy()`
`double`	`mean_per_class_error()`
`int`	`nclasses()`
`double`	`precision()` The percentage of positive predictions that are correct.
`double`	`recall()` The percentage of positive labeled instances that were predicted as positive.
`int`	`size()`
`double`	`specificity()` The percentage of negative labeled instances that were predicted as negative.
`TwoDimTable`	`table()` Convert this ConfusionMatrix into a fully annotated TwoDimTable
`java.lang.String`	`toASCII()`
`java.lang.String`	`toString()`
`double`	`total_rows()`

Methods inherited from class water.Iced
asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonBytes, toJsonString, write, writeExternal, writeJSON

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

- Field Detail
  - _cm
```
public final double[][] _cm
```
  - _domain
```
public final java.lang.String[] _domain
```
- Constructor Detail
  - ConfusionMatrix
```
public ConfusionMatrix(double[][] value,
                       java.lang.String[] domain)
```
    Constructor for Confusion Matrix
    
    Parameters:
    
    value - 2D square matrix with co-occurrence counts for actual vs predicted class membership
    
    domain - class labels (unified domain between actual and predicted class labels)
- Method Detail
  - add
```
public void add(int i,
                int j)
```
  - size
```
public final int size()
```
  - mean_per_class_error
```
public final double mean_per_class_error()
```
  - mean_per_class_accuracy
```
public final double mean_per_class_accuracy()
```
  - class_error
```
public final double class_error(int c)
```
  - total_rows
```
public double total_rows()
```
  - add
```
public void add(ConfusionMatrix other)
```
  - err
```
public double err()
```
    Returns:
    
    overall classification error
  - err_count
```
public double err_count()
```
  - accuracy
```
public double accuracy()
```
    The percentage of predictions that are correct.
  - specificity
```
public double specificity()
```
    The percentage of negative labeled instances that were predicted as negative.
    
    Returns:
    
    TNR / Specificity
  - recall
```
public double recall()
```
    The percentage of positive labeled instances that were predicted as positive.
    
    Returns:
    
    Recall / TPR / Sensitivity
  - precision
```
public double precision()
```
    The percentage of positive predictions that are correct.
    
    Returns:
    
    Precision
  - mcc
```
public double mcc()
```
    The Matthews Correlation Coefficient, takes true negatives into account in contrast to F-Score See MCC MCC = Correlation between observed and predicted binary classification
    
    Returns:
    
    mcc ranges from -1 (total disagreement) ... 0 (no better than random) ... 1 (perfect)
  - max_per_class_error
```
public double max_per_class_error()
```
    The maximum per-class error
    
    Returns:
    
    max[classErr(i)]
  - nclasses
```
public final int nclasses()
```
  - isBinary
```
public final boolean isBinary()
```
  - f1
```
public double f1()
```
    Returns the F-measure which combines precision and recall.
    C.f. end of http://en.wikipedia.org/wiki/Precision_and_recall.
  - f2
```
public double f2()
```
    Returns the F-measure which combines precision and recall and weights recall higher than precision.
    See F1_score
  - f0point5
```
public double f0point5()
```
    Returns the F-measure which combines precision and recall and weights precision higher than recall.
    See F1_score
  - toString
```
public java.lang.String toString()
```
    Overrides:
    
    toString in class java.lang.Object
  - toASCII
```
public java.lang.String toASCII()
```
  - table
```
public TwoDimTable table()
```
    Convert this ConfusionMatrix into a fully annotated TwoDimTable
    
    Returns:
    
    TwoDimTable

Class ConfusionMatrix

Field Summary

Constructor Summary

Method Summary

Methods inherited from class water.Iced

Methods inherited from class java.lang.Object

Field Detail

_cm

_domain

Constructor Detail

ConfusionMatrix

Method Detail

add

size

mean_per_class_error

mean_per_class_accuracy

class_error

total_rows

add

err

err_count

accuracy

specificity

recall

precision

mcc

max_per_class_error

nclasses

isBinary

f1

f2

f0point5

toString

toASCII

table