#!/usr/bin/env python # coding: utf-8 # In[5]: scores = spark.read.csv("/Users/blairhudson/Downloads/ml-20m/genome-scores.csv",header=True) scores.take(5) sqlContext.registerFunction("stringLengthString", lambda x: len(x)) # In[7]: sqlContext.registerFunction("stringLengthString", lambda x: len(x)) sqlContext.sql("SELECT stringLengthString('test')").collect() # In[ ]: #