Discovery Engine v1beta API - Class QualityMetrics (1.0.0-beta15)

Version 1.0.0-beta15

• 1.0.0-beta18 (latest)
• 1.0.0-beta17

public sealed class QualityMetrics : IMessage<QualityMetrics>, IEquatable<QualityMetrics>, IDeepCloneable<QualityMetrics>, IBufferMessage, IMessage

Reference documentation and code samples for the Discovery Engine v1beta API class QualityMetrics.

Describes the metrics produced by the evaluation.

Inheritance

object > QualityMetrics

Implements

IMessageQualityMetrics, IEquatableQualityMetrics, IDeepCloneableQualityMetrics, IBufferMessage, IMessage

Inherited Members

object.GetHashCode()

object.GetType()

object.ToString()

Namespace

Google.Cloud.DiscoveryEngine.V1Beta

Assembly

Google.Cloud.DiscoveryEngine.V1Beta.dll

Constructors

QualityMetrics()

public QualityMetrics()

QualityMetrics(QualityMetrics)

public QualityMetrics(QualityMetrics other)

Parameter
Name	Description
other	QualityMetrics

Properties

DocNdcg

public QualityMetrics.Types.TopkMetrics DocNdcg { get; set; }

Normalized discounted cumulative gain (NDCG) per document, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery] with three retrieved documents (D1, D2, D3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [D3 (0), D1 (1), D2 (1)] Ideal: [D1 (1), D2 (1), D3 (0)]

Calculate NDCG@3 for each [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]:

• DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
• Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
• NDCG@3: 1.13/1.63 = 0.693

Property Value
Type	Description
QualityMetricsTypesTopkMetrics

DocPrecision

public QualityMetrics.Types.TopkMetrics DocPrecision { get; set; }

Precision per document, at various top-k cutoff levels.

Precision is the fraction of retrieved documents that are relevant.

Example (top-5):

• For a single [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], If 4 out of 5 retrieved documents in the top-5 are relevant, precision@5 = 4/5 = 0.8

Property Value
Type	Description
QualityMetricsTypesTopkMetrics

DocRecall

public QualityMetrics.Types.TopkMetrics DocRecall { get; set; }

Recall per document, at various top-k cutoff levels.

Recall is the fraction of relevant documents retrieved out of all relevant documents.

Example (top-5):

• For a single [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], If 3 out of 5 relevant documents are retrieved in the top-5, recall@5 = 3/5 = 0.6

Property Value
Type	Description
QualityMetricsTypesTopkMetrics

PageNdcg

public QualityMetrics.Types.TopkMetrics PageNdcg { get; set; }

Normalized discounted cumulative gain (NDCG) per page, at various top-k cutoff levels.

NDCG measures the ranking quality, giving higher relevance to top results.

Example (top-3): Suppose [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery] with three retrieved pages (P1, P2, P3) and binary relevance judgements (1 for relevant, 0 for not relevant):

Retrieved: [P3 (0), P1 (1), P2 (1)] Ideal: [P1 (1), P2 (1), P3 (0)]

Calculate NDCG@3 for [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery]:

• DCG@3: 0/log2(1+1) + 1/log2(2+1) + 1/log2(3+1) = 1.13
• Ideal DCG@3: 1/log2(1+1) + 1/log2(2+1) + 0/log2(3+1) = 1.63
• NDCG@3: 1.13/1.63 = 0.693

Property Value
Type	Description
QualityMetricsTypesTopkMetrics

PageRecall

public QualityMetrics.Types.TopkMetrics PageRecall { get; set; }

Recall per page, at various top-k cutoff levels.

Recall is the fraction of relevant pages retrieved out of all relevant pages.

Example (top-5):

• For a single [SampleQuery][google.cloud.discoveryengine.v1beta.SampleQuery], if 3 out of 5 relevant pages are retrieved in the top-5, recall@5 = 3/5 = 0.6

Property Value
Type	Description
QualityMetricsTypesTopkMetrics