org.tensorflow.metadata.v0.NaturalLanguageStatisticsOrBuilder Maven / Gradle / Ivy
The newest version!
// Generated by the protocol buffer compiler. DO NOT EDIT!
// source: tensorflow_metadata/proto/v0/statistics.proto
// Protobuf Java Version: 3.25.4
package org.tensorflow.metadata.v0;
public interface NaturalLanguageStatisticsOrBuilder extends
// @@protoc_insertion_point(interface_extends:tensorflow.metadata.v0.NaturalLanguageStatistics)
com.google.protobuf.MessageOrBuilder {
/**
*
* Fraction of feature input tokens considered in-vocab.
*
*
* double feature_coverage = 1;
* @return The featureCoverage.
*/
double getFeatureCoverage();
/**
*
* Average token length of tokens used by the feature.
*
*
* double avg_token_length = 2;
* @return The avgTokenLength.
*/
double getAvgTokenLength();
/**
*
* Histogram containing the distribution of token lengths.
*
*
* .tensorflow.metadata.v0.Histogram token_length_histogram = 3;
* @return Whether the tokenLengthHistogram field is set.
*/
boolean hasTokenLengthHistogram();
/**
*
* Histogram containing the distribution of token lengths.
*
*
* .tensorflow.metadata.v0.Histogram token_length_histogram = 3;
* @return The tokenLengthHistogram.
*/
org.tensorflow.metadata.v0.Histogram getTokenLengthHistogram();
/**
*
* Histogram containing the distribution of token lengths.
*
*
* .tensorflow.metadata.v0.Histogram token_length_histogram = 3;
*/
org.tensorflow.metadata.v0.HistogramOrBuilder getTokenLengthHistogramOrBuilder();
/**
*
* Min / max sequence lengths.
*
*
* int64 min_sequence_length = 10;
* @return The minSequenceLength.
*/
long getMinSequenceLength();
/**
* int64 max_sequence_length = 11;
* @return The maxSequenceLength.
*/
long getMaxSequenceLength();
/**
*
* Histogram containing the distribution of sequence lengths.
*
*
* .tensorflow.metadata.v0.Histogram sequence_length_histogram = 9;
* @return Whether the sequenceLengthHistogram field is set.
*/
boolean hasSequenceLengthHistogram();
/**
*
* Histogram containing the distribution of sequence lengths.
*
*
* .tensorflow.metadata.v0.Histogram sequence_length_histogram = 9;
* @return The sequenceLengthHistogram.
*/
org.tensorflow.metadata.v0.Histogram getSequenceLengthHistogram();
/**
*
* Histogram containing the distribution of sequence lengths.
*
*
* .tensorflow.metadata.v0.Histogram sequence_length_histogram = 9;
*/
org.tensorflow.metadata.v0.HistogramOrBuilder getSequenceLengthHistogramOrBuilder();
/**
*
* Number of of sequences which do not match the location constraint.
*
*
* int64 location_misses = 4;
* @return The locationMisses.
*/
long getLocationMisses();
/**
*
* Reported sequences that are sampled from the input and have small
* avg_token_length, low feature converage, or do not match the location
* regex.
*
*
* repeated string reported_sequences = 5;
* @return A list containing the reportedSequences.
*/
java.util.List
getReportedSequencesList();
/**
*
* Reported sequences that are sampled from the input and have small
* avg_token_length, low feature converage, or do not match the location
* regex.
*
*
* repeated string reported_sequences = 5;
* @return The count of reportedSequences.
*/
int getReportedSequencesCount();
/**
*
* Reported sequences that are sampled from the input and have small
* avg_token_length, low feature converage, or do not match the location
* regex.
*
*
* repeated string reported_sequences = 5;
* @param index The index of the element to return.
* @return The reportedSequences at the given index.
*/
java.lang.String getReportedSequences(int index);
/**
*
* Reported sequences that are sampled from the input and have small
* avg_token_length, low feature converage, or do not match the location
* regex.
*
*
* repeated string reported_sequences = 5;
* @param index The index of the value to return.
* @return The bytes of the reportedSequences at the given index.
*/
com.google.protobuf.ByteString
getReportedSequencesBytes(int index);
/**
*
* Statistics for specified tokens. TokenStatistics are only reported for
* tokens specified in SequenceValueConstraints in the schema.
*
*
* repeated .tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics token_statistics = 6;
*/
java.util.List
getTokenStatisticsList();
/**
*
* Statistics for specified tokens. TokenStatistics are only reported for
* tokens specified in SequenceValueConstraints in the schema.
*
*
* repeated .tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics token_statistics = 6;
*/
org.tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics getTokenStatistics(int index);
/**
*
* Statistics for specified tokens. TokenStatistics are only reported for
* tokens specified in SequenceValueConstraints in the schema.
*
*
* repeated .tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics token_statistics = 6;
*/
int getTokenStatisticsCount();
/**
*
* Statistics for specified tokens. TokenStatistics are only reported for
* tokens specified in SequenceValueConstraints in the schema.
*
*
* repeated .tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics token_statistics = 6;
*/
java.util.List
getTokenStatisticsOrBuilderList();
/**
*
* Statistics for specified tokens. TokenStatistics are only reported for
* tokens specified in SequenceValueConstraints in the schema.
*
*
* repeated .tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatistics token_statistics = 6;
*/
org.tensorflow.metadata.v0.NaturalLanguageStatistics.TokenStatisticsOrBuilder getTokenStatisticsOrBuilder(
int index);
/**
*
* The rank histogram for the tokens of the feature.
* The rank is used to measure of how commonly the token is found in the
* dataset. The most common token would have a rank of 1, with the second-most
* common value having a rank of 2, and so on.
*
*
* .tensorflow.metadata.v0.RankHistogram rank_histogram = 7;
* @return Whether the rankHistogram field is set.
*/
boolean hasRankHistogram();
/**
*
* The rank histogram for the tokens of the feature.
* The rank is used to measure of how commonly the token is found in the
* dataset. The most common token would have a rank of 1, with the second-most
* common value having a rank of 2, and so on.
*
*
* .tensorflow.metadata.v0.RankHistogram rank_histogram = 7;
* @return The rankHistogram.
*/
org.tensorflow.metadata.v0.RankHistogram getRankHistogram();
/**
*
* The rank histogram for the tokens of the feature.
* The rank is used to measure of how commonly the token is found in the
* dataset. The most common token would have a rank of 1, with the second-most
* common value having a rank of 2, and so on.
*
*
* .tensorflow.metadata.v0.RankHistogram rank_histogram = 7;
*/
org.tensorflow.metadata.v0.RankHistogramOrBuilder getRankHistogramOrBuilder();
/**
* .tensorflow.metadata.v0.WeightedNaturalLanguageStatistics weighted_nl_statistics = 8;
* @return Whether the weightedNlStatistics field is set.
*/
boolean hasWeightedNlStatistics();
/**
* .tensorflow.metadata.v0.WeightedNaturalLanguageStatistics weighted_nl_statistics = 8;
* @return The weightedNlStatistics.
*/
org.tensorflow.metadata.v0.WeightedNaturalLanguageStatistics getWeightedNlStatistics();
/**
* .tensorflow.metadata.v0.WeightedNaturalLanguageStatistics weighted_nl_statistics = 8;
*/
org.tensorflow.metadata.v0.WeightedNaturalLanguageStatisticsOrBuilder getWeightedNlStatisticsOrBuilder();
}
© 2015 - 2025 Weber Informatics LLC | Privacy Policy