All Implemented Interfaces:
```
public abstract class PreferenceOptimizationDataStats
extends JsonSerializable
                    
```
Statistics computed for datasets used for preference optimization. This data type is not supported in Gemini API.

Nested Class Summary

Nested Classes
Modifier and Type	Class	Description
`public abstract class`	`PreferenceOptimizationDataStats.Builder`	Builder for PreferenceOptimizationDataStats.

Field Summary

Fields
Modifier and Type	Field	Description
`public final static String`	`MAX_READ_LENGTH_PROPERTY`

Constructor Summary

Constructors
Constructor	Description
`PreferenceOptimizationDataStats()`

Enum Constant Summary

Enum Constants
Enum Constant	Description

Method Summary

Modifier and Type	Method	Description
`abstract Optional<List<Long>>`	`droppedExampleIndices()`	Output only.
`abstract Optional<List<String>>`	`droppedExampleReasons()`	Output only.
`abstract Optional<DatasetDistribution>`	`scoreVariancePerExampleDistribution()`	Output only.
`abstract Optional<DatasetDistribution>`	`scoresDistribution()`	Output only.
`abstract Optional<Long>`	`totalBillableTokenCount()`	Output only.
`abstract Optional<Long>`	`tuningDatasetExampleCount()`	Output only.
`abstract Optional<Long>`	`tuningStepCount()`	Output only.
`abstract Optional<List<GeminiPreferenceExample>>`	`userDatasetExamples()`	Output only.
`abstract Optional<DatasetDistribution>`	`userInputTokenDistribution()`	Output only.
`abstract Optional<DatasetDistribution>`	`userOutputTokenDistribution()`	Output only.
`static PreferenceOptimizationDataStats.Builder`	`builder()`	Instantiates a builder for PreferenceOptimizationDataStats.
`abstract PreferenceOptimizationDataStats.Builder`	`toBuilder()`	Creates a builder with the same values as this instance.
`static PreferenceOptimizationDataStats`	`fromJson(String jsonString)`	Deserializes a JSON string to a PreferenceOptimizationDataStats object.

Methods inherited from class com.google.genai.JsonSerializable
fromJsonNode, fromJsonString, objectMapper, setMaxReadLength, stringToJsonNode, toJson, toJsonNode, toJsonString
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - PreferenceOptimizationDataStats
```
PreferenceOptimizationDataStats()
```
- Method Detail
  - droppedExampleIndices
```
 abstract Optional<List<Long>> droppedExampleIndices()
```
    Output only. A partial sample of the indices (starting from 1) of the dropped examples.
  - droppedExampleReasons
```
 abstract Optional<List<String>> droppedExampleReasons()
```
    Output only. For each index in `dropped_example_indices`, the user-facing reason why the example was dropped.
  - scoreVariancePerExampleDistribution
```
 abstract Optional<DatasetDistribution> scoreVariancePerExampleDistribution()
```
    Output only. Dataset distributions for scores variance per example.
  - scoresDistribution
```
 abstract Optional<DatasetDistribution> scoresDistribution()
```
    Output only. Dataset distributions for scores.
  - totalBillableTokenCount
```
 abstract Optional<Long> totalBillableTokenCount()
```
    Output only. Number of billable tokens in the tuning dataset.
  - tuningDatasetExampleCount
```
 abstract Optional<Long> tuningDatasetExampleCount()
```
    Output only. Number of examples in the tuning dataset.
  - tuningStepCount
```
 abstract Optional<Long> tuningStepCount()
```
    Output only. Number of tuning steps for this Tuning Job.
  - userDatasetExamples
```
 abstract Optional<List<GeminiPreferenceExample>> userDatasetExamples()
```
    Output only. Sample user examples in the training dataset.
  - userInputTokenDistribution
```
 abstract Optional<DatasetDistribution> userInputTokenDistribution()
```
    Output only. Dataset distributions for the user input tokens.
  - userOutputTokenDistribution
```
 abstract Optional<DatasetDistribution> userOutputTokenDistribution()
```
    Output only. Dataset distributions for the user output tokens.
  - builder
```
 static PreferenceOptimizationDataStats.Builder builder()
```
    Instantiates a builder for PreferenceOptimizationDataStats.
  - toBuilder
```
 abstract PreferenceOptimizationDataStats.Builder toBuilder()
```
    Creates a builder with the same values as this instance.
  - fromJson
```
 static PreferenceOptimizationDataStats fromJson(String jsonString)
```
    Deserializes a JSON string to a PreferenceOptimizationDataStats object.

Class PreferenceOptimizationDataStats

Nested Class Summary

Field Summary

Constructor Summary

Enum Constant Summary

Method Summary

Methods inherited from class com.google.genai.JsonSerializable

Methods inherited from class java.lang.Object

Constructor Detail

PreferenceOptimizationDataStats

Method Detail

droppedExampleIndices

droppedExampleReasons

scoreVariancePerExampleDistribution

scoresDistribution

totalBillableTokenCount

tuningDatasetExampleCount

tuningStepCount

userDatasetExamples

userInputTokenDistribution

userOutputTokenDistribution

builder

toBuilder

fromJson