Spark Pipeline error

Question

I am trying to run a Multinomial Logistic Regression model

from pyspark.sql import SparkSession
spark = SparkSession.builder.appName(\'prepare_data\').getOrC         


        

Answer 1

You need to make sure there are no missing values in your data -- that's why you get the NullPointerException. Also, make sure that all your input features to the VectorAssembler are numeric.

BTW, when you create encoder you might consider specifying the inputCol as StringIndexer.getOuputCol().