twitter_xlm_roberta_base_sentiment_pdc(cardiff)

from pyspark.ml import Pipeline

document_assembler = DocumentAssembler() \
    .setInputCol('text') \
    .setOutputCol('document')

tokenizer = Tokenizer() \
    .setInputCols(['document']) \
    .setOutputCol('token')

sequenceClassifier = XlmRoBertaForSequenceClassification.pretrained('twitter_xlm_roberta_base_sentiment_pdc')\
  .setInputCols(["document",'token'])\
  .setOutputCol("class")

pipeline = Pipeline(stages=[
    document_assembler, 
    tokenizer,
    sequenceClassifier    
])

# couple of simple examples
example = spark.createDataFrame([['사랑해!'], ["T'estimo! ❤️"], ["I love you!"], ['Mahal kita!']]).toDF("text")

result = pipeline.fit(example).transform(example)

# result is a DataFrame
result.select("text", "class.result").show()