bofei.xiao created SPARK-8096:
---------------------------------
Summary: use csv data to build a classification model,how to
convert dataframe field to label and features
Key: SPARK-8096
URL: https://issues.apache.org/jira/browse/SPARK-8096
Project: Spark
Issue Type: Bug
Reporter: bofei.xiao
given i have a csv file data.csv
target,age,sex,height
1,18,1,170
0,25,1,165
.....
now,i want build a decisitin model
step 1:load csv data as dataframe
val data= sqlContext.load("com.databricks.spark.csv",:Map("path" -> "data.csv",
"header" -> "true")
step 2:build a decisiontree model
but decisiontree need a RDD[LabelPoint] input
Q:how to convert the dataframe to RDD[LabelPoint]
thanks!
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
