Fwd: [pyspark][MLlib] Getting WARN FPGrowth: Input data is not cached for cached data

[Anu B Nair <an...@gmail.com>]

Hi,

Following is my pyspark code, (attached input sample_fpgrowth.txt and
python code along with this mail. Even after I have done cache, I am
getting Warning: Input data is not cached.

















*from pyspark.mllib.fpm import FPGrowthimport pysparkfrom pyspark.context
import SparkContextfrom pyspark.sql.session import SparkSessionsc =
SparkContext('local')data = sc.textFile("sample_fpgrowth.txt")transactions
= data.map(lambda line: line.strip().split(' ')).cache()model =
FPGrowth.train(transactions, minSupport=0.2, numPartitions=10)result =
model.freqItemsets().collect()print(result)*


Understood that it is a warning, but just wanted to know in detail

--

Anu