Description
This model is a BioBERT based classifier that can classify self-report the exact age into social media data.
Predicted Entities
self_report_age, no_report
Live Demo Open in Colab Copy S3 URI
How to use
document_assembler = DocumentAssembler() \
.setInputCol('text') \
.setOutputCol('document')
tokenizer = Tokenizer() \
.setInputCols(['document']) \
.setOutputCol('token')
sequenceClassifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_self_reported_age_tweet", "en", "clinical/models")\
.setInputCols(["document",'token'])\
.setOutputCol("class")
pipeline = Pipeline(stages=[
document_assembler,
tokenizer,
sequenceClassifier
])
data = spark.createDataFrame(["Who knew I would spend my Saturday mornings at 21 still watching Disney channel",
"My girl, Fancy, just turned 17. She’s getting up there, but she still has the energy of a puppy"], StringType()).toDF("text")
result = pipeline.fit(data).transform(data)
# Checking results
result.select("text", "class.result").show(truncate=False)
val documenter = new DocumentAssembler()
.setInputCol("text")
.setOutputCol("document")
val tokenizer = new Tokenizer()
.setInputCols(Array("document"))
.setOutputCol("token")
val sequenceClassifier = MedicalBertForSequenceClassification.pretrained("bert_sequence_classifier_self_reported_age_tweet", "en", "clinical/models")
.setInputCols(Array("document","token"))
.setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(documenter, tokenizer, sequenceClassifier))
val data = Seq(Array("Who knew I would spend my Saturday mornings at 21 still watching Disney channel",
"My girl, Fancy, just turned 17. She’s getting up there, but she still has the energy of a puppy")).toDS.toDF("text")
val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("en.classify.self_reported_age").predict("""My girl, Fancy, just turned 17. She’s getting up there, but she still has the energy of a puppy""")
Results
+-----------------------------------------------------------------------------------------------+-----------------+
|text |result |
+-----------------------------------------------------------------------------------------------+-----------------+
|Who knew I would spend my Saturday mornings at 21 still watching Disney channel |[self_report_age]|
|My girl, Fancy, just turned 17. She’s getting up there, but she still has the energy of a puppy|[no_report] |
+-----------------------------------------------------------------------------------------------+-----------------+
Model Information
| Model Name: | bert_sequence_classifier_self_reported_age_tweet |
| Compatibility: | Healthcare NLP 4.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [document, token] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 406.5 MB |
| Case sensitive: | true |
| Max sentence length: | 128 |
Benchmarking
label precision recall f1-score support
no_report 0.939016 0.900332 0.919267 1505
self_report_age 0.801849 0.873381 0.836088 695
accuracy - - 0.891818 2200
macro-avg 0.870433 0.886857 0.877678 2200
weighted-avg 0.895684 0.891818 0.892990 2200