May 2017
Intermediate to advanced
294 pages
7h 33m
English
$ spark-shell
scala> val houses = spark.createDataFrame(Seq( (1620000d,2100), (1690000d,2300), (1400000d,2046), (2000000d,4314), (1060000d,1244), (3830000d,4608), (1230000d,2173), (2400000d,2750), (3380000d,4010), (1480000d,1959) )).toDF("price","size")
scala> houses.stat.corr("price","size") correlation: Double = 0.8577177736252574
scala> houses.stat.corr("price","size","pearson") ...Read now
Unlock full access