Description
This model, extracts vehicle identifier number entities from clinical texts.
How to use
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = Tokenizer() \
.setInputCols(["sentence"]) \
.setOutputCol("token")
vin_contextual_parser = ContextualParserModel.pretrained("vin_parser","en","clinical/models") \
.setInputCols(["sentence", "token"]) \
.setOutputCol("chunk_vin")
chunk_converter = ChunkConverter() \
.setInputCols(["chunk_vin"]) \
.setOutputCol("ner_chunk")
parserPipeline = Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
vin_contextual_parser,
chunk_converter
])
model = parserPipeline.fit(spark.createDataFrame([[""]]).toDF("text"))
sample_text = """Name : Hendrickson, Ora, Record date: 2093-01-13, # 719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, VIN 4Y1SL65848Z411439, VIN 1HGCM82633A123456 - VIN JH4KA7560MC012345 - VIN 5YJSA1E14HF123456
SSN #333-44-6666, Driver's license no:A334455B, plate 34NLP34.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""
result = model.transform(spark.createDataFrame([[sample_text]]).toDF("text"))
val document_assembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentence_detector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
.setInputCols("document")
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("sentence")
.setOutputCol("token")
val vin_contextual_parser = ContextualParserModel.pretrained("vin_parser","en","clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("chunk_vin")
val chunk_converter = new ChunkConverter()
.setInputCols("chunk_vin")
.setOutputCol("ner_chunk")
val parserPipeline = new Pipeline().setStages(Array(
document_assembler,
sentence_detector,
tokenizer,
vin_contextual_parser,
chunk_converter
))
val sample_text = """Name : Hendrickson, Ora, Record date: 2093-01-13, # 719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, VIN 4Y1SL65848Z411439, VIN 1HGCM82633A123456 - VIN JH4KA7560MC012345 - VIN 5YJSA1E14HF123456
SSN #333-44-6666, Driver's license no:A334455B, plate 34NLP34.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""
val data = Seq(sample_text).toDF("text")
val results = parserPipeline.fit(data).transform(data)
Results
+-----------------+-----+---+-----+
| chunk|begin|end|label|
+-----------------+-----+---+-----+
|1HGBH41JXMN109286| 213|229| VIN|
|4Y1SL65848Z411439| 236|252| VIN|
|1HGCM82633A123456| 259|275| VIN|
|JH4KA7560MC012345| 283|299| VIN|
|5YJSA1E14HF123456| 307|323| VIN|
+-----------------+-----+---+-----+
Model Information
| Model Name: | vin_parser |
| Compatibility: | Healthcare NLP 5.5.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence, token] |
| Output Labels: | [entity_vin_code] |
| Language: | en |
| Size: | 9.3 KB |
| Case sensitive: | false |