movies.py

# issue movies query
conf = {"es.resource" : "movies/logs", "es.query" : "?q=name:bourne"}
movies = sc.newAPIHadoopRDD("org.elasticsearch.hadoop.mr.EsInputFormat",\
    "org.apache.hadoop.io.NullWritable", "org.elasticsearch.hadoop.mr.LinkedMapWritable", conf=conf)

# place results in table
moviesRows = movies.map(lambda p: Row(id=int(p[1]['id']), name=p[1]['name']))
moviesRowsList = moviesRows.collect()
schemaMovies = sqlContext.createDataFrame(moviesRowsList)
schemaMovies.registerTempTable("movies")
sqlContext.cacheTable("movies")