In R's predicting modeling, sometimes there is an error:
Error: variables ‘xxx" were specified with different types from the fit
How to fix it?
Mainly the reason for it is that in the data where we did the predicting the data type for some variables are different from the data type for some variables from the modeling.
You can check the data types in the data where we will do the predicting.
Once I found that , there were some quotes in the data which made the data into character. Then I unquoted the data and made the data types into numerical. problem solved.
Sample script:
newData=noquote(newData)
newData$in_dream1<-as.numeric(newData$in_dream1)
newData$selected_by1<-as.numeric(newData$selected_by1)
newData$form1<-as.numeric(newData$form1)
newData$points_game1<-as.numeric(newData$points_game1)
newData$element_type1<-as.factor(newData$element_type1)
Subscribe to:
Post Comments (Atom)
-
I tried to commit script to bitbucket using sourcetree. I first cloned from bitbucket using SSH, and I got an error, "authentication ... -
https://github.com/boto/boto3/issues/134 import boto3 import botocore client = boto3.client('s3') result = client.list_obje...
-
Previously, I wanted to install "script" on Atom to run PHP. And there was some problem, like the firewall. So I tried atom-runner...
No comments:
Post a Comment