About Zachary

Zachary · ‎12-29-2014

Looking for a way to format the following output so that the column percents show up with zero decimal places: proc freq data = CombineScoredTemp; tables _node_ * Bin_SLR /nopercent norow nofreq; run; Of course I could copy & paste it into Excel. Then format it. Then I would want more decimal places. Also, is there a way to output these column percents so that a % shows up with the numbers? Thank you very much in advance.

Zachary · ‎12-19-2014

What do you think of the following for my solution? proc rank data = CombineScoredTemp groups = 100000000 out = CombineScoredTemp; var Predicted_SLR; ranks PERCENTILE_SLR; run; data CombineScoredTemp; set CombineScoredTemp; PERCENTILE_SLR = PERCENTILE_SLR / 1000000; run; Only problem I see is that it is limited to 6 decimal places. Maybe 7.

Zachary · ‎12-18-2014

I am probably missing something. I run the following code and it makes a nice CDF plot: ods table cdfplot = want;; proc univariate data = CombineScoredTemp; var Predicted_SLR; cdfplot Predicted_SLR; run; quit; But it does not add the percentiles to the data file. Plus, I receive a warning saying that the CDFPlot was not created. I am sure that both of these are related, somehow. I am pretty sure I just mis-read the supplied code or something. But I am currently lost. I especially am interested in setting this right as I recently read an article on the web very much trashing the PERCENTRANK() procedure in Excel. Thank you, as usual.

Zachary · ‎12-18-2014

Thank you for all of the answers. CDF seems to show the most promise. But how may I modify the code to accomodate saving the actual percentile on a record-by-record basis? This would be the equivalent of a PERCENTRANK() function in Excel. Thanks.

Zachary · ‎12-18-2014

Thanks Wendy. You rule!

Zachary · ‎12-17-2014

I use the following code to obtain the percentiles of over 100,000 observations: proc rank data = CombineScoredTemp groups = 100 out = CombineScoredTemp; var Predicted_SLR; ranks Percentile_SLR; run; But it provides the percentiles as integers. Any suggestions on how to get a real number out of this? Thank you, as usual.

Zachary · ‎12-17-2014

I am very near settled on what I want my final Decision Tree to look like. Unfortunately it has taken a lot of interactive selecting of other (2nd best) types of variables and selective pruning. I just figured out how to import a previous tree structure into a new tree beautifully. That is what I want to do, so far. BUT, I also wish to prune one particular node before it is final. When I import the structure of the other tree it does not let me interactively change the new tree without starting from scratch again. Surely I must be doing something wrrong. Please let me know the steps to (1) retain a model from before then (2) move forward almost as if I created it from scratch. Thank you, as usual.

Zachary · ‎12-17-2014

Please view the following code: proc corr data = L_P1.UWR_10YrData plots(maxpoints = none) = matrix(nvar = all); var D_DELQ_DEFU_INDN D_DELQ_NATL_PCTL D_DELQ_SCR D_FAIL_DEFU_INDN D_FAIL_NATL_PCTL D_FAIL_SCR; with BLEND_GROSS_LOAD; run; How may I simplify my code so that it does not request a plot? While on this topic, is there also a way to request all _numeric_ vars that begin with a prefix of D_? Thank you.

Zachary · ‎12-05-2014

PI am using Enterprise Miner (EM) Decision Trees to investigate a wide variety of models. To simplify things I have two models using the same dataset. I would like to use the same data and same data partition for both model runs. The only difference between the two models are a different Target variable for each. It was highly recommended to set the Drop specifier to Y rather than set the Level specifier to Rejected. But the problem is that when I do this the variable literally gets rejected from my EM run and I cannot choose to change the Target variable to another one when I do my second model. I hope that makes sense. Any recommendations? Also, there are some variables that I want to still be included within my EM dataset for posterity, but there is no way I will use it within the model itself. So basically my variables are either Level = Target, Input, or Key. Can anyone suggest the best way to code these up so that there are no future problems down the line? I suppose I can set them to INPUT then set Drop = Y, and call it a day. Thank you.

Zachary · ‎12-04-2014

It was already set to No by default. Thank you for the suggestion there.

Zachary · ‎12-03-2014

Thank you again for all of the valuable advice. But I have a huge problem. My diagram is rather simple. I have a data node, a data partition node, then a decision tree node. One of my colleagues and I were "interactively" changing the results of the decision tree mode to be more in alignment with what our results should substantively say. Ultimately we did it using the interactive feature of the decision tree node, then we closed it. We changed a few more things and ultimately re-ran the decision tree node to sort of start over again. But it also re-ran the data partition as well - we cannot figure out why. Before I fully implement the code generator I would like to somehow lock-down the other nodes. Is this possible with EM to insure that nothing will change?

Zachary · ‎12-01-2014

Imagine a data-set with 100 variables. Many of them would be character or string variables with numeric codes in them. Assume they all had values of zero or 1. The correlations would then be point-biserial correlations versus a continuous variable. But this is after each of the variables is converted from character to numeric. That is the part where if I add zero to each value it automatically takes care of it. Thank you very much.

Zachary · ‎12-01-2014

Any of the correlations I would do for the character variables would be for Boolean (Y/N, dichotomous ) types of variables. One solution I thought of was simply to add a 0 to every variable in my dataset. But surely there must be a better way? Thank you in advance.

Zachary · ‎11-28-2014

I am on 13.1, and yes I found the score code node. Thank you very much. Do you recommend I use the Optimized SAS Code or just the regular SAS Code? What are the differences? Also, there are a lot of code statements in there that I am not familiar with. Do you suggest I just have my code point to my data file/library then just run all of this code that was generated? Or do you recommend anything else? Below are some of the initial statements in my code - not making a lot of sense to me right now: _ARBFMT_12 = PUT( BU , BEST12.); %DMNORMIP( _ARBFMT_12); IF _ARBFMT_12 IN ('1' ) THEN DO; IF NOT MISSING(PURE_PREMIUM ) AND 5112.5 <= PURE_PREMIUM THEN DO; _ARBFMT_12 = PUT( SMNQ_D_POST_CODE , BEST12.); %DMNORMIP( _ARBFMT_12); IF _ARBFMT_12 IN ('3' ) THEN DO; _NODE_ = 81; _LEAF_ = 21; May I ask for an example of how the Score Code node is incorporated with EG? The reason that I am a little nervous is because I plan on applying this code to a new datset with the same variables. I am much more accustomed to simple code. Thank you again.

Zachary · ‎11-26-2014

Thank you for all of the thoughtful responses. I have been requested to somewhat steer clear of the SAS Admin duties - but that could change.

Online Status	Offline
Date Last Visited	‎09-15-2015 07:13 PM

Number vars to consider in split search - What is the default for the ...

Re: Enterprise Miner Cutoff Node & Intepretation

Re: Enterprise Miner Cutoff Node & Intepretation

Re: Enterprise Miner Cutoff Node & Intepretation

Enterprise Miner Cutoff Node & Intepretation

Subset Decision Trees Within Enterprise Miner

Re: How to Properly Rename an Enterprise Miner Project

Re: Turn Histogram into a Line Graph - With Markers

Re: Turn Histogram into a Line Graph - With Markers

Turn Histogram into a Line Graph - With Markers

Re: Turn Histogram into a Line Graph - With Markers

Re: Word list search

Re: After SAS Code Node Variables Disappear- Rather, Never Appear

Re: Best Way to Finalize a Model Using 100% Data After 80/20 Training/...

Re: Is SAS Deployment the Correct Forum for Co-Worker Not Able to Conn...

Enterprise Miner Cutoff Node & Intepretation

Re: Turn Histogram into a Line Graph - With Markers

Re: Edit Using SAS Code Seems to Not Work

Looking for Precision Up to Maybe 8 Decimal Places in proc rank

EM Decision Trees - Stratification or Not - Validation or Test?

Formatting 2X2 Crosstabulation

Re: Looking for Precision Up to Maybe 8 Decimal Places in proc rank

Re: Looking for Precision Up to Maybe 8 Decimal Places in proc rank

Re: Looking for Precision Up to Maybe 8 Decimal Places in proc rank

Re: Importing One Decision Tree into Another Within Enterprise Miner

Looking for Precision Up to Maybe 8 Decimal Places in proc rank

Importing One Decision Tree into Another Within Enterprise Miner

Simplest Proc Corr Code

Specifying Levels, Roles, and Drop Codes in Enterprise Miner

Re: Best Way to Finalize a Model Using 100% Data After 80/20 Training/...

Re: Best Way to Finalize a Model Using 100% Data After 80/20 Training/...

Re: Quick & Dirty Way to Do Proc Corr on Both Numeric and Character Va...

Quick & Dirty Way to Do Proc Corr on Both Numeric and Character Variab...

Re: Best Way to Finalize a Model Using 100% Data After 80/20 Training/...

Re: Is SAS Deployment the Correct Forum for Co-Worker Not Able to Conn...