4413868535

Build Type

push

github

Committed by GitHub

Commit Message

SPARKNLP-746: Handle empty validation sets (#13615)

Run Details

8597 of 12936 relevant lines covered (66.46%)

0.66 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

0.0

/src/main/scala/com/johnsnowlabs/nlp/annotators/common/EmbeddingsWithSentence.scala

/*
 * Copyright 2017-2022 John Snow Labs
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.johnsnowlabs.nlp.annotators.common

import com.johnsnowlabs.nlp.{Annotation, AnnotatorType}

object EmbeddingsWithSentence extends Annotated[TokenizedSentence] {

  override def annotatorType: String = AnnotatorType.WORD_EMBEDDINGS

  override def unpack(annotations: Seq[Annotation]): Seq[TokenizedSentence] = {
    val tokens = annotations
      .filter(_.annotatorType == annotatorType)
      .toArray

    val sentences = SentenceSplit.unpack(annotations)

    /** // Evaluate whether to enable this validation to check proper usage of DOCUMENT and
      * SENTENCE within entire pipelines require(tokens.map(_.metadata.getOrElse("sentence",
      * "0").toInt).distinct.length == sentences.length, "Inconsistencies found in pipeline.
      * Tokens in sentences does not match with sentence count")
      */
    sentences
      .map(sentence => {
        val sentenceTokens = tokens
          .filter(token => token.begin >= sentence.start & token.end <= sentence.end)
          .map(token => IndexedToken(token.result, token.begin, token.end))
        sentenceTokens
      })
      .zipWithIndex
      .map { case (indexedTokens, index) => TokenizedSentence(indexedTokens, index) }
      .filter(_.indexedTokens.nonEmpty)

  }

  override def pack(sentences: Seq[TokenizedSentence]): Seq[Annotation] = {
    sentences.flatMap { sentence =>
      sentence.indexedTokens.map { token =>
        Annotation(
          annotatorType,
          token.begin,
          token.end,
          token.token,
          Map("sentence" -> sentence.sentenceIndex.toString))
      }
    }
  }
}

1	/*
2	* Copyright 2017-2022 John Snow Labs
3	*
4	* Licensed under the Apache License, Version 2.0 (the "License");
5	* you may not use this file except in compliance with the License.
6	* You may obtain a copy of the License at
7	*
8	* http://www.apache.org/licenses/LICENSE-2.0
9	*
10	* Unless required by applicable law or agreed to in writing, software
11	* distributed under the License is distributed on an "AS IS" BASIS,
12	* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13	* See the License for the specific language governing permissions and
14	* limitations under the License.
15	*/
16
17	package com.johnsnowlabs.nlp.annotators.common
18
19	import com.johnsnowlabs.nlp.{Annotation, AnnotatorType}
20
21	object EmbeddingsWithSentence extends Annotated[TokenizedSentence] {
22
23	override def annotatorType: String = AnnotatorType.WORD_EMBEDDINGS	×
24
25	override def unpack(annotations: Seq[Annotation]): Seq[TokenizedSentence] = {
26	val tokens = annotations
27	.filter(_.annotatorType == annotatorType)	×
28	.toArray	×
29
30	val sentences = SentenceSplit.unpack(annotations)	×
31
32	/** // Evaluate whether to enable this validation to check proper usage of DOCUMENT and
33	* SENTENCE within entire pipelines require(tokens.map(_.metadata.getOrElse("sentence",
34	* "0").toInt).distinct.length == sentences.length, "Inconsistencies found in pipeline.
35	* Tokens in sentences does not match with sentence count")
36	*/
37	sentences
38	.map(sentence => {	×
39	val sentenceTokens = tokens
40	.filter(token => token.begin >= sentence.start & token.end <= sentence.end)	×
41	.map(token => IndexedToken(token.result, token.begin, token.end))	×
42	sentenceTokens
43	})
44	.zipWithIndex	×
45	.map { case (indexedTokens, index) => TokenizedSentence(indexedTokens, index) }	×
46	.filter(_.indexedTokens.nonEmpty)	×
47
48	}
49
50	override def pack(sentences: Seq[TokenizedSentence]): Seq[Annotation] = {
51	sentences.flatMap { sentence =>	×
52	sentence.indexedTokens.map { token =>	×
53	Annotation(	×
54	annotatorType,	×
55	token.begin,	×
56	token.end,	×
57	token.token,	×
58	Map("sentence" -> sentence.sentenceIndex.toString))	×
59	}
60	}
61	}
62	}

JohnSnowLabs / spark-nlp / 4413868535

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous