Description
This pretrained pipeline is built on the top of ner_eu_clinical_condition model.
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("ner_eu_clinical_condition_pipeline", "eu", "clinical/models")
text = "
Gertaera honetatik bi hilabetetara, umea Larrialdietako Zerbitzura dator 4 egunetan zehar buruko mina eta bekokiko hantura azaltzeagatik, sukarrik izan gabe. Miaketan, haztapen mingarria duen bekokiko hantura bigunaz gain, ez da beste zeinurik azaltzen. Polakiuria eta tenesmo arina ere izan zuen egun horretan hematuriarekin batera. Geroztik sintomarik gabe dago.
"
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("ner_eu_clinical_condition_pipeline", "eu", "clinical/models")
val text = "
Gertaera honetatik bi hilabetetara, umea Larrialdietako Zerbitzura dator 4 egunetan zehar buruko mina eta bekokiko hantura azaltzeagatik, sukarrik izan gabe. Miaketan, haztapen mingarria duen bekokiko hantura bigunaz gain, ez da beste zeinurik azaltzen. Polakiuria eta tenesmo arina ere izan zuen egun horretan hematuriarekin batera. Geroztik sintomarik gabe dago.
"
val result = pipeline.fullAnnotate(text)
Results
| | chunks | begin | end | entities | confidence |
|---:|:-----------|--------:|------:|:-------------------|-------------:|
| 0 | mina | 98 | 101 | clinical_condition | 0.8754 |
| 1 | hantura | 116 | 122 | clinical_condition | 0.8877 |
| 2 | sukarrik | 139 | 146 | clinical_condition | 0.9119 |
| 3 | mingarria | 178 | 186 | clinical_condition | 0.7381 |
| 4 | hantura | 203 | 209 | clinical_condition | 0.8805 |
| 5 | Polakiuria | 256 | 265 | clinical_condition | 0.6683 |
| 6 | sintomarik | 345 | 354 | clinical_condition | 0.9632 |
Model Information
| Model Name: | ner_eu_clinical_condition_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | eu |
| Size: | 1.1 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverterInternalModel