Spam Classifier

Description

Automatically identify messages as being regular messages or Spam.

Classified Labels

spam, ham

Live Demo
Open in Colab
Download

How to use

documentAssembler = DocumentAssembler()\
  .setInputCol("text")\
  .setOutputCol("document")
use = UniversalSentenceEncoder.pretrained(lang="en") \
  .setInputCols(["document"])\
  .setOutputCol("sentence_embeddings")
document_classifier = ClassifierDLModel.pretrained('classifierdl_use_spam', 'en') \
  .setInputCols(["document", "sentence_embeddings"]) \
  .setOutputCol("class")

nlpPipeline = Pipeline(stages=[documentAssembler, use, document_classifier])
light_pipeline = LightPipeline(nlp_pipeline.fit(spark.createDataFrame([['']]).toDF("text")))

annotations = light_pipeline.fullAnnotate('Congratulations! You've won a $1,000 Walmart gift card. Go to http://bit.ly/1234 to claim now.')

val documentAssembler = DocumentAssembler()
  .setInputCol("text")
  .setOutputCol("document")
val use = UniversalSentenceEncoder.pretrained(lang="en")
  .setInputCols(Array("document"))
  .setOutputCol("sentence_embeddings")
val document_classifier = ClassifierDLModel.pretrained('classifierdl_use_spam', 'en')
  .setInputCols(Array("document", "sentence_embeddings"))
  .setOutputCol("class")
val pipeline = new Pipeline().setStages(Array(documentAssembler, use, document_classifier))

val result = pipeline.fit(Seq.empty["Congratulations! You've won a $1,000 Walmart gift card. Go to http://bit.ly/1234 to claim now."].toDS.toDF("text")).transform(data)
import nlu

text = ["""Congratulations! You've won a $1,000 Walmart gift card. Go to http://bit.ly/1234 to claim now."""]
spam_df = nlu.load('classify.spam.use').predict(text, output_level='document')
spam_df[["document", "spam"]]

Results

+------------------------------------------------------------------------------------------------+------------+
|document                                                                                        |class       |
+------------------------------------------------------------------------------------------------+------------+
|Congratulations! You've won a $1,000 Walmart gift card. Go to http://bit.ly/1234 to claim now.  | spam       |
+------------------------------------------------------------------------------------------------+------------+

Model Information

Model Name classifierdl_use_spam
Model Class ClassifierDLModel
Spark Compatibility 2.5.3
Spark NLP Compatibility 2.4
License open source
Edition public
Input Labels [document, sentence_embeddings]
Output Labels [class]
Language en
Upstream Dependencies tfhub_use

Data Source

This model is trained on UCI spam dataset. https://archive.ics.uci.edu/ml/machine-learning-databases/00228/smsspamcollection.zip

Benchmarking

Accuracy of the model with USE Embeddings is 0.86

              precision    recall  f1-score   support

         ham       0.86      1.00      0.92      1440
        spam       0.00      0.00      0.00       238

    accuracy                           0.86      1678
   macro avg       0.43      0.50      0.46      1678
weighted avg       0.74      0.86      0.79      1678