Description
This model is a bioBERT based classifier that can classify source of emotional stress in text.
Predicted Entities
Family_Issues, Financial_Problem, Health_Fatigue_or_Physical Pain, Other, School, Work, Social_Relationships
How to use
document_assembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
sequence_classifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_stressor_onnx", "en", "clinical/models")\
.setInputCols(["document", "token"])\
.setOutputCol("class")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
sequence_classifier
])
data = spark.createDataFrame([["All the panic about the global pandemic has been stressing me out!"]]).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
document_assembler = nlp.DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")
tokenizer = nlp.Tokenizer() \
.setInputCols(["document"]) \
.setOutputCol("token")
sequenceClassifier = medical.BertForSequenceClassification.pretrained("bert_sequence_classifier_stressor_onnx", "en", "clinical/models")\
.setInputCols(["document","token"])\
.setOutputCol("classes")
pipeline = nlp.Pipeline(stages=[
document_assembler,
tokenizer,
sequenceClassifier
])
data = spark.createDataFrame([["All the panic about the global pandemic has been stressing me out!"]]).toDF("text")
model = pipeline.fit(data)
result = model.transform(data)
import com.johnsnowlabs.nlp.base._
import com.johnsnowlabs.nlp.annotators._
import org.apache.spark.ml.Pipeline
import spark.implicits._
val documentAssembler = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val sentenceDetector = new SentenceDetectorDLModel()
.pretrained("sentence_detector_dl","xx")
.setInputCols(["document"])
.setOutputCol("sentence")
val tokenizer = new Tokenizer()
.setInputCols("document")
.setOutputCol("token")
val tokenClassifier = MedicalBertForTokenClassifier
.pretrained("bert_sequence_classifier_stressor_onnx", "en", "clinical/models")
.setInputCols("token", "document")
.setOutputCol("ner")
.setCaseSensitive(true)
val nerConverter = new NerConverter()
.setInputCols("document", "token", "ner")
.setOutputCol("ner_chunk")
val pipeline = new Pipeline()
.setStages(Array(
documentAssembler,
sentenceDetector,
tokenizer,
tokenClassifier,
nerConverter
))
val data = Seq("All the panic about the global pandemic has been stressing me out!").toDF("text")
val model = pipeline.fit(data)
val result = model.transform(data)
Results
+------------------------------------------------------------------+-----------------------------------+
|text |class |
+------------------------------------------------------------------+-----------------------------------+
|All the panic about the global pandemic has been stressing me out!|[Health, Fatigue, or Physical Pain]|
+------------------------------------------------------------------+-----------------------------------+
Model Information
| Model Name: | bert_sequence_classifier_stressor_onnx |
| Compatibility: | Healthcare NLP 6.1.1+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [label] |
| Language: | en |
| Size: | 437.7 MB |
| Case sensitive: | true |