Description
This model, extracts drive license 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")
dln_contextual_parser = ContextualParserModel.pretrained("dln_parser","en","clinical/models")\
.setInputCols(["sentence", "token"])\
.setOutputCol("chunk_dln")
chunk_converter = ChunkConverter()\
.setInputCols(["chunk_dln"])\
.setOutputCol("ner_chunk")
parserPipeline = Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
dln_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, SSN #333-44-6666, Driver's license no: A334455B. Driver's license# 12345678. MY DL# B324567 CDL bs34df45
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""
result = model.transform(spark.createDataFrame([[sample_text]]).toDF("text"))
document_assembler = nlp.DocumentAssembler()\
.setInputCol("text")\
.setOutputCol("document")
sentence_detector = nlp.SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")\
.setInputCols(["document"])\
.setOutputCol("sentence")
tokenizer = nlp.Tokenizer()\
.setInputCols(["sentence"])\
.setOutputCol("token")
dln_contextual_parser = medical.ContextualParserModel.pretrained("dln_parser","en","clinical/models")\
.setInputCols(["sentence", "token"])\
.setOutputCol("chunk_dln")
chunk_converter = medical.ChunkConverter()\
.setInputCols(["chunk_dln"])\
.setOutputCol("ner_chunk")
parserPipeline = nlp.Pipeline(stages=[
document_assembler,
sentence_detector,
tokenizer,
dln_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, SSN #333-44-6666, Driver's license no: A334455B. Driver's license# 12345678. MY DL# B324567 CDL bs34df45
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 dln_contextual_parser = ContextualParserModel.pretrained("dln_parser","en","clinical/models")
.setInputCols(Array("sentence", "token"))
.setOutputCol("chunk_dln")
val chunk_converter = new ChunkConverter()
.setInputCols("chunk_dln")
.setOutputCol("ner_chunk")
val parserPipeline = new Pipeline().setStages(Array(
document_assembler,
sentence_detector,
tokenizer,
dln_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, SSN #333-44-6666, Driver's license no: A334455B. Driver's license# 12345678. MY DL# B324567 CDL bs34df45
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 |
|:---------|--------:|------:|:--------|
| A334455B | 271 | 278 | DLN |
| 12345678 | 299 | 306 | DLN |
| B324567 | 316 | 322 | DLN |
| bs34df45 | 328 | 335 | DLN |
Model Information
| Model Name: | dln_parser |
| Compatibility: | Healthcare NLP 6.2.2+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token_doc] |
| Output Labels: | [entity_dln] |
| Language: | en |
| Size: | 4.4 KB |
| Case sensitive: | false |