com.google.api.services.bigquery.model

Class AggregateClassificationMetrics

java.lang.Object

java.util.AbstractMap<java.lang.String,java.lang.Object>

com.google.api.client.util.GenericData

com.google.api.client.json.GenericJson

com.google.api.services.bigquery.model.AggregateClassificationMetrics

All Implemented Interfaces:

java.lang.Cloneable, java.util.Map<java.lang.String,java.lang.Object>

public final class AggregateClassificationMetrics
extends com.google.api.client.json.GenericJson

Aggregate metrics for classification models. For multi-class models, the metrics are either macro-averaged: metrics are calculated for each label and then an unweighted average is taken of those values or micro-averaged: the metric is calculated globally by counting the total number of correctly predicted rows.

This is the Java data model class that specifies how to parse/serialize into the JSON that is transmitted over HTTP when working with the BigQuery API. For a detailed explanation see: https://developers.google.com/api-client-library/java/google-http-java-client/json

Author:

Google, Inc.

Nested Class Summary

Nested classes/interfaces inherited from class com.google.api.client.util.GenericData

com.google.api.client.util.GenericData.Flags

Nested classes/interfaces inherited from class java.util.AbstractMap

java.util.AbstractMap.SimpleEntry<K,V>, java.util.AbstractMap.SimpleImmutableEntry<K,V>

Nested classes/interfaces inherited from interface java.util.Map

java.util.Map.Entry<K,V>

Constructor Summary

Constructors

Constructor and Description
AggregateClassificationMetrics()

Method Summary

Modifier and Type	Method and Description
AggregateClassificationMetrics	clone()
java.lang.Double	getAccuracy() Accuracy is the fraction of predictions given the correct label.
java.lang.Double	getF1Score() The F1 score is an average of recall and precision.
java.lang.Double	getLogLoss() Logarithmic Loss.
java.lang.Double	getPrecision() Precision is the fraction of actual positive predictions that had positive actual labels.
java.lang.Double	getRecall() Recall is the fraction of actual positive labels that were given a positive prediction.
java.lang.Double	getRocAuc() Area Under a ROC Curve.
java.lang.Double	getThreshold() Threshold at which the metrics are computed.
AggregateClassificationMetrics	set(java.lang.String fieldName, java.lang.Object value)
AggregateClassificationMetrics	setAccuracy(java.lang.Double accuracy) Accuracy is the fraction of predictions given the correct label.
AggregateClassificationMetrics	setF1Score(java.lang.Double f1Score) The F1 score is an average of recall and precision.
AggregateClassificationMetrics	setLogLoss(java.lang.Double logLoss) Logarithmic Loss.
AggregateClassificationMetrics	setPrecision(java.lang.Double precision) Precision is the fraction of actual positive predictions that had positive actual labels.
AggregateClassificationMetrics	setRecall(java.lang.Double recall) Recall is the fraction of actual positive labels that were given a positive prediction.
AggregateClassificationMetrics	setRocAuc(java.lang.Double rocAuc) Area Under a ROC Curve.
AggregateClassificationMetrics	setThreshold(java.lang.Double threshold) Threshold at which the metrics are computed.

Methods inherited from class com.google.api.client.json.GenericJson

getFactory, setFactory, toPrettyString, toString

Methods inherited from class com.google.api.client.util.GenericData

entrySet, get, getClassInfo, getUnknownKeys, put, putAll, remove, setUnknownKeys

Methods inherited from class java.util.AbstractMap

clear, containsKey, containsValue, equals, hashCode, isEmpty, keySet, size, values

Methods inherited from class java.lang.Object

finalize, getClass, notify, notifyAll, wait, wait, wait

Methods inherited from interface java.util.Map

compute, computeIfAbsent, computeIfPresent, forEach, getOrDefault, merge, putIfAbsent, remove, replace, replace, replaceAll

Constructor Detail

AggregateClassificationMetrics

public AggregateClassificationMetrics()

Method Detail

getAccuracy

public java.lang.Double getAccuracy()

Accuracy is the fraction of predictions given the correct label. For multiclass this is a micro-averaged metric.

Returns:

value or null for none

setAccuracy

public AggregateClassificationMetrics setAccuracy(java.lang.Double accuracy)

Accuracy is the fraction of predictions given the correct label. For multiclass this is a micro-averaged metric.

Parameters:

accuracy - accuracy or null for none

getF1Score

public java.lang.Double getF1Score()

The F1 score is an average of recall and precision. For multiclass this is a macro-averaged metric.

Returns:

value or null for none

setF1Score

public AggregateClassificationMetrics setF1Score(java.lang.Double f1Score)

The F1 score is an average of recall and precision. For multiclass this is a macro-averaged metric.

Parameters:

f1Score - f1Score or null for none

getLogLoss

public java.lang.Double getLogLoss()

Logarithmic Loss. For multiclass this is a macro-averaged metric.

Returns:

value or null for none

setLogLoss

public AggregateClassificationMetrics setLogLoss(java.lang.Double logLoss)

Logarithmic Loss. For multiclass this is a macro-averaged metric.

Parameters:

logLoss - logLoss or null for none

getPrecision

public java.lang.Double getPrecision()

Precision is the fraction of actual positive predictions that had positive actual labels. For multiclass this is a macro-averaged metric treating each class as a binary classifier.

Returns:

value or null for none

setPrecision

public AggregateClassificationMetrics setPrecision(java.lang.Double precision)

Precision is the fraction of actual positive predictions that had positive actual labels. For multiclass this is a macro-averaged metric treating each class as a binary classifier.

Parameters:

precision - precision or null for none

getRecall

public java.lang.Double getRecall()

Recall is the fraction of actual positive labels that were given a positive prediction. For multiclass this is a macro-averaged metric.

Returns:

value or null for none

setRecall

public AggregateClassificationMetrics setRecall(java.lang.Double recall)

Recall is the fraction of actual positive labels that were given a positive prediction. For multiclass this is a macro-averaged metric.

Parameters:

recall - recall or null for none

getRocAuc

public java.lang.Double getRocAuc()

Area Under a ROC Curve. For multiclass this is a macro-averaged metric.

Returns:

value or null for none

setRocAuc

public AggregateClassificationMetrics setRocAuc(java.lang.Double rocAuc)

Area Under a ROC Curve. For multiclass this is a macro-averaged metric.

Parameters:

rocAuc - rocAuc or null for none

getThreshold

public java.lang.Double getThreshold()

Threshold at which the metrics are computed. For binary classification models this is the positive class threshold. For multi-class classfication models this is the confidence threshold.

Returns:

value or null for none

setThreshold

public AggregateClassificationMetrics setThreshold(java.lang.Double threshold)

Threshold at which the metrics are computed. For binary classification models this is the positive class threshold. For multi-class classfication models this is the confidence threshold.

Parameters:

threshold - threshold or null for none

set

public AggregateClassificationMetrics set(java.lang.String fieldName,
                                          java.lang.Object value)

Overrides:

set in class com.google.api.client.json.GenericJson

clone

public AggregateClassificationMetrics clone()

Overrides:

clone in class com.google.api.client.json.GenericJson