Last active
August 29, 2015 14:25
-
-
Save petermreid/1a41a151da199e52d8d5 to your computer and use it in GitHub Desktop.
Titanic
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ut ports to variables | |
dataset1 <- maml.mapInputPort(1) # class: data.frame | |
#Create the AgeGroup bins | |
dataset1$AgeGroup <- ifelse(is.na(dataset1$Age), NA, ifelse(dataset1$Age < 2, "Baby", ifelse(dataset1$Age < 16, "Young", ifelse(dataset1$Age > 60, "Old", "Middle")))) | |
#Parse the Name for Title | |
getTitle <- function(name) {return (sub(" ", "", unlist(strsplit(name, "[,.]"))[2]))} | |
dataset1$Title=apply(matrix(dataset1$Name),1,getTitle) | |
#Aggregate the family memebrs together | |
dataset1$FamilyMembers=dataset1$SibSp+dataset1$Parch | |
#Have another go at AgeGroup to fill in the blanks | |
dataset1$AgeGroup <- ifelse(is.na(dataset1$Age), ifelse((dataset1$Title=="Master"|dataset1$Title=="Miss"), "Young","Middle") ,dataset1$AgeGroup) | |
# Select data.frame to be sent to the output Dataset port | |
maml.mapOutputPort("dataset1"); | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment