About jeff_b

jeff_b · ‎03-10-2021

Hi @ballardw ! Thank you for the help. With some modification, the code you provided worked, although I had to create another variable called "rank" from the variable of importance output and merge it back to that dataset. I used that "rank" variable to sort, since I didn't have the Gini variable in the dataset. data ranking; length Variable $100; INPUT rank Variable $; CARDS; 1 high_PA_baseline 2 early_weight_loss .... ; RUN; proc sort data=Variable_Importance; by Variable; run; proc sort data=ranking; by Variable; run; *Merge; data plot; length Variable $100; merge Variable_Importance(in=x) ranking(in=y); by Variable; if x=y; run; proc sgplot data=plot; scatter x=AAEOOB y=Variable ; run; proc sort data=plot out=plot2; by AAEOOB descending rank; run; proc sgplot data=plot2; scatter x=AAEOOB y=Variable ; run;

jeff_b · ‎03-10-2021

Hi @ballardw , Thank you for the reply to my question! The variables of importance output from the proc hpforest procedure sorted by AAEOOB: Yes, I tried to create a label variable from the PROC CONTENTS output and merging it BY VARIABLE with the variable of importance output. However, since the label variable is a character/string variable, I cannot input it on Y-axis in the PROC SGPLOT procedure. I will try using the VALUESFORMAT option. Thanks for the suggestion. For the data sorting, I used the AAEOOB variable, which is absolute error out of bag. I think using this variable or any variable from the variable of importance output for sorting is incorrect, because the proc hpforest procedure uses own method to rank the variables (I guess by dividing mean error rate by SD or something like that), which looks like in the below figure. When I try to sort the output by any variable (MSE, OOB MSE, AE or AAEOOB), the ranking or order of the variables changes and the plot doesn't look like as it's supposed to be. I am not sure why the proc hpforest procedure doesn't include the variable of importance plots in it. I guess I have to use R to get the plot. I was trying to see if I can get one using SAS, too. Thank you for any suggestions with this! The variables of importance output from the proc hpforest procedure:

jeff_b · ‎03-09-2021

Hello, I am trying to obtain a variable importance ranking plot from the proc hpforest procedure in SAS. Here is my code: proc hpforest data=mydata maxtrees=1000 vars_to_try=10 seed=2021 trainfraction=0.7 maxdepth=50 leafsize=6 alpha=0.5 ; target outcome /level=binary; input variable_list / level = interval; ods output VariableImportance = Variable_Importance; run; Then, I am using PROC SPLOT to plot this output. However, I am not getting the plot I want. Somehow, the values are not in the ascending order. Also, I wanted the variable labels in the plots, instead of the variable names as it's hard to understand the plot. proc sgplot data = Variable_Importance; title "The Variable of Importance Plot"; series x=Gini y=Variable /lineattrs=(pattern=shortdash color=royalblue thickness=3) legendlabel='Train Gini' GROUPORDER=ASCENDING ; xaxis label='Train Gini' display=ALL; yaxis label='Variable' display=ALL; run; The plot I want but I also want labels instead of the variable names: The plot I am getting:

jeff_b · ‎02-20-2021

Hi @ballardw ! Thanks for the suggestions! A combination PROC SGPLOT with both bands and scatter worked well. proc sgplot data=allplot; band x=visit lower=Lower upper=Upper / group=Source fillattrs=GraphConfidence1 legendlabel="95% CL" name="band"; scatter x=visit y=Estimate / group=Source yerrorlower=Lower yerrorupper=Upper groupdisplay=overlay; position=bottomright; xaxis grid values=(1 to 3 by 1); yaxis grid colorbands=odd display=(nolabel) discreteorder=data; run;

jeff_b · ‎02-20-2021

Hi @ballardw ! Thank you for the quick reply to my post. I followed your suggestion and combined the 2 data in a data step and plotted them in PROC SGPLOT using both scatter and series. Please see the code below. However, the plot looks a bit messy. I was hoping to get more of connected lines like in time series and 95% CI's as bands around them. Thanks in advance for any suggestions! proc sgplot data=allplot noautolegend; series x=VISIT y=Estimate / group=Source; scatter x=VISIT y=Estimate / group=Source yerrorlower=Lower yerrorupper=Upper groupdisplay=cluster; xaxis grid values=(1 to 3 by 1); yaxis values=(7 to 12 by 1) grid colorbands=odd display=(nolabel) discreteorder=data; run;

jeff_b · ‎02-20-2021

Hello, I'm trying to plot 2 separate PROC MIXED outputs in 1 PROC SGPLOT. Here is the output I am keeping -only estimate and 95% CI's. Could you please suggest a way for me to plot them in the same PROC SGPLOT series plot along with 95% CI's? /*1st output for the total sample*/ proc mixed data = temp; class ID visit group; model outcome = visit group visit *group / cl ; repeated visit / type=un subject=ID r; lsmeans visit group visit *group / cl; ods output lsmeans = plot1(where=(Effect="visit*group")); run; /*2 nd output from a subset of people */ proc mixed data = temp; where subset = 1; class ID visit group; model outcome = visit group visit *group / cl ; repeated visit / type=un subject=ID r; lsmeans visit group visit *group / cl; ods output lsmeans = plot2(where=(Effect="visit*group")); run; *This scatter plot plots a 1 output but can add 95% CI's, while proc sgplot series cannot add 95% CI's. proc sgplot data=plot1; scatter y=Estimate x=visit/ yerrorlower=Lower yerrorupper=Upper markerattrs=(symbol=diamondfilled) group=GRP groupdisplay=cluster; refline 0 / axis=x; xaxis grid values=(1 to 3 by 1); yaxis values=(7 to 12 by 1) grid colorbands=odd display=(nolabel) discreteorder=data; run;

jeff_b · ‎12-27-2019

Thank you Rick! Your response is extremely helpful. Posting my code below: data temp; set SolutionR; Lower=Estimate-1.96*StdErrPred; Upper=Estimate+1.96*StdErrPred; run; proc sort data=temp; by descending Estimate; run; proc sgplot data=temp noautolegend; scatter y=Estimate x=Subject / yerrorlower=Lower yerrorupper=Upper markerattrs=(symbol=diamondfilled); refline 0 / axis=y; xaxis grid; yaxis grid display=(nolabel) discreteorder=data reverse; run;

jeff_b · ‎12-21-2019

Hi, I would appreciate a help with creating a caterpillar plot from the generalized linear mixed (binomial distribution) models with random intercepts output. I came across with an article on creating a caterpillar plot from proc mcmc output using the cater macro: ods graphics on; %CATER(data=postout, var=delta: ); ods graphics off; I want to do a similar plot but with the proc glimmix output (SolutionR=random effect estimates and plotting the ‘wiskers’ as +/- 1.96 x the standard errors).

Online Status	Offline
Date Last Visited	‎03-23-2021 01:40 PM

Re: Variable Importance Plot from the proc hpforest procedure

Re: Variable Importance Plot from the proc hpforest procedure

Variable Importance Plot from the proc hpforest procedure

Re: How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

Re: How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

Re: Caterpillar plots from random-effects proc glimmix output

Caterpillar plots from random-effects proc glimmix output

Re: Variable Importance Plot from the proc hpforest procedure

Re: Variable Importance Plot from the proc hpforest procedure

Variable Importance Plot from the proc hpforest procedure

Re: How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

Re: How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

How to plot using PROC SGPLOT from 2 separate PROC MIXED outputs

Re: Caterpillar plots from random-effects proc glimmix output

Caterpillar plots from random-effects proc glimmix output