Community Spring Cleaning week is here! Join your fellow Maveryx in digging through your old posts and marking comments on them as solved. Learn more here!

Alteryx Designer Desktop Discussions

Find answers, ask questions, and share expertise about Alteryx Designer Desktop and Intelligence Suite.
SOLVED

Predictive Tools: Logistic Regression Error

arnorian_intapp
5 - Atom

I'm running a simple Logistic Regression for data in my salesforce that simply will predict if opportunity is won or lost based on number of days.

 

I'm not sure where error is coming from since my data set is very simple with just two fiields: stage field and age. I had run this workflow without any issues yesterday.

 

Not sure what is causing this.

 

I get the following 3 errors:

  1. Error in density.default(x, bw = bw, n = n...)
  2. executed halted
  3. The R.exe exit code (1) indicated an error

Thanks

 

4 REPLIES 4
Thableaus
17 - Castor
17 - Castor

Hi @arnorian_intapp 

 

This error is probably related to how your data looks like.


Does your data have enough variation? What I'd recommend you to is to run some Data Investigation Tools (like Frequency table, Field Summary) to profile your data. Predictive models are very strict regarding to data quality, so this is a "must" step before running any model.


Cheers,

JonA
Alteryx
Alteryx

Hi @arnorian_intapp,

 

I just ran into this issue, saw this thread...added a data cleansing tool upstream of my logistic regression and the error was fixed.

 

R doesn't like null values apparently.

TomKing
5 - Atom

Thanks JonA - this helped me!  Inserting a simple data cleaning tool with default settings got me past the "Error: Logistic Regression (3): Tool #127: Error in density.default(x, bw = bw, n = n, ...) : " - TomK

philipwhalen12
5 - Atom

I was having the same issue! This helped so much. Thank you all, cheers.

Labels