Evaluation (deeplearning4j-core 0.4-rc3.7 API)

java.lang.Object
- org.deeplearning4j.eval.Evaluation<T>

All Implemented Interfaces:

Serializable
```
public class Evaluation<T extends Comparable<? super T>>
extends Object
implements Serializable
```
Evaluation metrics: precision, recall, f1

Author:

Adam Gibson

See Also:

Serialized Form

Constructor Summary

Constructors
Constructor and Description

Evaluation()

Evaluation(int numClasses)

Evaluation(List<String> labels)

Evaluation(Map<Integer,String> labels)

Constructors
Constructor and Description
`Evaluation()`
`Evaluation(int numClasses)`
`Evaluation(List<String> labels)`
`Evaluation(Map<Integer,String> labels)`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`double`	`accuracy()` Accuracy: (TP + TN) / (P + N)
`void`	`addToConfusion(Integer real, Integer guess)` Adds to the confusion matrix
`int`	`classCount(Integer clazz)` Returns the number of times the given label has actually occurred
`void`	`eval(org.nd4j.linalg.api.ndarray.INDArray realOutcomes, org.nd4j.linalg.api.ndarray.INDArray guesses)` Collects statistics on the real outcomes vs the guesses.
`void`	`eval(int predictedIdx, int actualIdx)` Evaluate a single prediction (one prediction at a time)
`void`	`evalTimeSeries(org.nd4j.linalg.api.ndarray.INDArray labels, org.nd4j.linalg.api.ndarray.INDArray predicted)` Convenience method for evaluation of time series.
`double`	`f1()` TP: true positive FP: False Positive FN: False Negative F1 score: 2 * TP / (2TP + FP + FN)
`double`	`f1(Integer classLabel)` Calculate f1 score for a given class
`double`	`falseNegatives()` False negatives: correctly rejected
`double`	`falsePositives()` False positive: wrong guess
`String`	`getClassLabel(Integer clazz)`
`double`	`getNumRowCounter()`
`void`	`incrementFalseNegatives(Integer classLabel)`
`void`	`incrementFalsePositives(Integer classLabel)`
`void`	`incrementTrueNegatives(Integer classLabel)`
`void`	`incrementTruePositives(Integer classLabel)`
`double`	`negative()` Total negatives true negatives + false positives
`double`	`positive()` Returns all of the positive guesses: true positive + false negative
`double`	`precision()` Total precision based on guesses so far
`double`	`precision(Integer classLabel)` Returns the precision for a given label
`double`	`recall()` Returns the recall for the outcomes
`double`	`recall(Integer classLabel)` Get the recall for a particular class label
`String`	`stats()` Method to obtain the classification report, as a String
`double`	`trueNegatives()` True negatives: correctly rejected
`double`	`truePositives()` True positives: correctly rejected

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

- Constructor Detail
  - Evaluation
```
public Evaluation()
```
  - Evaluation
```
public Evaluation(int numClasses)
```
  - Evaluation
```
public Evaluation(List<String> labels)
```
  - Evaluation
```
public Evaluation(Map<Integer,String> labels)
```
- Method Detail
  - eval
```
public void eval(org.nd4j.linalg.api.ndarray.INDArray realOutcomes,
                 org.nd4j.linalg.api.ndarray.INDArray guesses)
```
    Collects statistics on the real outcomes vs the guesses. This is for logistic outcome matrices. Note that an IllegalArgumentException is thrown if the two passed in matrices aren't the same length.
    
    Parameters:
    
    realOutcomes - the real outcomes (labels - usually binary)
    
    guesses - the guesses/prediction (usually a probability vector)
  - evalTimeSeries
```
public void evalTimeSeries(org.nd4j.linalg.api.ndarray.INDArray labels,
                           org.nd4j.linalg.api.ndarray.INDArray predicted)
```
    Convenience method for evaluation of time series. Reshapes time series (3d) to 2d, then calls eval
    
    See Also:
    
    eval(INDArray, INDArray)
  - eval
```
public void eval(int predictedIdx,
                 int actualIdx)
```
    Evaluate a single prediction (one prediction at a time)
    
    Parameters:
    
    predictedIdx - Index of class predicted by the network
    
    actualIdx - Index of actual class
  - stats
```
public String stats()
```
    Method to obtain the classification report, as a String
    
    Returns:
    
    A (multi-line) String with accuracy, precision, recall, f1 score etc
  - precision
```
public double precision(Integer classLabel)
```
    Returns the precision for a given label
    
    Parameters:
    
    classLabel - the label
    
    Returns:
    
    the precision for the label
  - precision
```
public double precision()
```
    Total precision based on guesses so far
    
    Returns:
    
    the total precision based on guesses so far
  - recall
```
public double recall(Integer classLabel)
```
    Get the recall for a particular class label
    
    Parameters:
    
    classLabel - Integer the indicate which class
    
    Returns:
    
    Recall rate as a double
  - recall
```
public double recall()
```
    Returns the recall for the outcomes
    
    Returns:
    
    the recall for the outcomes
  - f1
```
public double f1(Integer classLabel)
```
    Calculate f1 score for a given class
    
    Parameters:
    
    classLabel - the label to calculate f1 for
    
    Returns:
    
    the f1 score for the given label
  - f1
```
public double f1()
```
    TP: true positive FP: False Positive FN: False Negative F1 score: 2 * TP / (2TP + FP + FN)
    
    Returns:
    
    the f1 score or harmonic mean based on current guesses
  - accuracy
```
public double accuracy()
```
    Accuracy: (TP + TN) / (P + N)
    
    Returns:
    
    the accuracy of the guesses so far
  - truePositives
```
public double truePositives()
```
    True positives: correctly rejected
    
    Returns:
    
    the total true positives so far
  - trueNegatives
```
public double trueNegatives()
```
    True negatives: correctly rejected
    
    Returns:
    
    the total true negatives so far
  - falsePositives
```
public double falsePositives()
```
    False positive: wrong guess
    
    Returns:
    
    the count of the false positives
  - falseNegatives
```
public double falseNegatives()
```
    False negatives: correctly rejected
    
    Returns:
    
    the total false negatives so far
  - negative
```
public double negative()
```
    Total negatives true negatives + false positives
    
    Returns:
    
    the overall negative count
  - positive
```
public double positive()
```
    Returns all of the positive guesses: true positive + false negative
    
    Returns:
  - incrementTruePositives
```
public void incrementTruePositives(Integer classLabel)
```
  - incrementTrueNegatives
```
public void incrementTrueNegatives(Integer classLabel)
```
  - incrementFalseNegatives
```
public void incrementFalseNegatives(Integer classLabel)
```
  - incrementFalsePositives
```
public void incrementFalsePositives(Integer classLabel)
```
  - addToConfusion
```
public void addToConfusion(Integer real,
                           Integer guess)
```
    Adds to the confusion matrix
    
    Parameters:
    
    real - the actual guess
    
    guess - the system guess
  - classCount
```
public int classCount(Integer clazz)
```
    Returns the number of times the given label has actually occurred
    
    Parameters:
    
    clazz - the label
    
    Returns:
    
    the number of times the label actually occurred
  - getNumRowCounter
```
public double getNumRowCounter()
```
  - getClassLabel
```
public String getClassLabel(Integer clazz)
```

Class Evaluation<T extends Comparable<? super T>>

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

Evaluation

Evaluation

Evaluation

Evaluation

Method Detail

eval

evalTimeSeries

eval

stats

precision

precision

recall

recall

f1

f1

accuracy

truePositives

trueNegatives

falsePositives

falseNegatives

negative

positive

incrementTruePositives

incrementTrueNegatives

incrementFalseNegatives

incrementFalsePositives

addToConfusion

classCount

getNumRowCounter

getClassLabel