spark_nlp_pretrained_pipeline_ner_pos_lemmatization.py

1import sparknlp
2from sparknlp.pretrained import PretrainedPipeline
3
4# Start Spark Session with Spark NLP
5spark = sparknlp.start()
6
7# Download a pre-trained pipeline
8pipeline = PretrainedPipeline("explain_document_dl", lang="en")
9
10# Annotate some text
11text = "The Mona Lisa is a 16th century oil painting created by Leonardo. It's held at the Louvre in Paris."
12result = pipeline.annotate(text)
13
14# Check the results
15print(result.keys())
16print(result['entities'])
17
18# Alternatively, transform a Spark DataFrame
19data = spark.createDataFrame([[text]]).toDF("text")
20result_df = pipeline.transform(data)
21result_df.show()