in PROC HPNEURAL, what is the right syntax in using character level variables. You can see from PROC LOGISTIC that this is handled appropriately through the class statement. see below.   PROC LOGISTIC DATA=lib1.Training_Atlantic outmodel=sasuser.HS_log_Model; Class  LISTTYPEClasfnListSrcRentExcHse (Ref='R') NUMLISTSourcesFromWhichRecCame     PROV1  ; MODEL My_RESPONDER_FLAG( EVENT='1' ) =   X1  LISTTYPEClasfnListSrcRentExcHse   NUMLISTSourcesFromWhichRecCame   Non_Resp  HKINTERSECT   PROV1                                        /selection=backward  lackfit rsq stb; store HS_log_Model; RUN; ... View more

what is the specific code or routines to incorporate the learning rate in PROC HPNEURAL  ... View more

have attempted to determine variable contributions by using the weights of each variable which are located in the input layer. See attached output file from PROC HPNEURAL where the output file occurs from the OUTMODEL statement .You will note that I use only the weights reported in the input layer because each input layer is connected to all the hidden layers. So the real differentiator are the weights of the variables in the input layer.  You will see that the highlighted section(in green) represents the information which I  would use to calculate a given variable's contribution (i.e. sum up all the node weights(absolute) for that variable and then divide by the total weights of all nodes and all variables) but for the input layer only. Do not need to worry about the hidden layers as all the hidden layers and their weights map back to each node in the input layer. see attached file. ... View more

Similar to what we  can do in terms of variable importance in regression type routines where we determine the partial R2 of a given variable and then divide by the total R2 of the entire equeation. In neural nets, I understand we use weight of a given variable that are indicated across all the nodes and then sum it up and then divide by the weights of all variables across all the nodes. does anyone have SAS code to do this.    ... View more

Need help in understanding how the data is transcribed here from image to numbers. Here is the code:   Need help in understanding how the data is transcribed here from image to numbers. Here is the code: filename decomp "C:\Users\Richard Boire\Desktop\train-images.idx3-ubyte"; data train_images; infile decomp recfm=n; *input var $256.; input var PIB1.; run; proc print data=train_images(obs=10);run; Here is the output(printed off 1st 10 records) Obs var 1 0 2 0 3 8 4 3 5 0 6 0 7 234 8 96 9 0 10 0       ... View more

see below SAS code and errors. any suggestions     filename foo url 169      'http://support.sas.com/techsup/service_intro.html'; 170 171  data file2; 172     infile foo length=len; 173     input record $varying200. len; 174     put record $varying200. len; 175     if _n_=15 then stop; 176  run; ERROR: Invalid reply received from the HTTP server. Use the debug option for more info. NOTE: The SAS System stopped processing this step because of errors. WARNING: The data set WORK.FILE2 may be incomplete.  When this step was stopped there were 0          observations and 1 variables. NOTE: DATA statement used (Total process time):       real time           0.48 seconds       cpu time            0.09 seconds   ... View more

See below log file output. be great if anyone can advise.   645  proc hpsvm data=LIB1.DEVASS method=activeset; 2646       kernel rbf / k_par = 1.5; 2647      /* input 2648   /level=nominal;*/ 2649       input 2650       PAYCASHDRAWEROTHR PAYBILLADJ 2651 2652  JOINGROUPTENURE 2653 2654   TOT12ERSBASICCOST 2655   PC_PRMMSINSUR 2656   LTVGROUPDESC1 2657    PCPAY12 2658    AGE 2659  /level=interval; 2660       target RESPONSE; 2661       output outclass=outclass outfit=outfit outest=outest; 2662   run; NOTE: For a binary or nominal target, descending order is used. NOTE: For HPSVM target variable, the binary type is used. NOTE: The HPSVM procedure is executing in single-machine mode. ERROR: The SAS System stopped processing this step because of insufficient memory. NOTE: There were 25107 observations read from the data set LIB1.DEVASS. ... View more

here is the error when I read this data. there are no observations. Why ?    filename data '\\kashmir\BFD\sample_json1_may26.txt'; 6300  data datatest; 6301   infile data lrecl = 32000 truncover scanover; 6302   input @'"text": "' text $255. @'"from_user": "' from_user $255. @'"created_at": "' created_at 6302! $255. ; 6303  /*text = substr(text,1,index(text,'",')-2); from_user = substr( from_user,1,index( 6303! from_user,'",')-2); 6304  created_at = substr(created_at,1,index(created_at,'",')-2); run; 6305    */ NOTE: The infile DATA is:       Filename=\\kashmir\BFD\sample_json1_may26.txt,       RECFM=V,LRECL=32000,File Size (bytes)=1989,       Last Modified=26May2017:12:28:24,       Create Time=26May2017:12:09:11 NOTE: 3 records were read from the infile DATA.       The minimum record length was 1.       The maximum record length was 1134. NOTE: SAS went to a new line when INPUT @'CHARACTER_STRING' scanned past the end of a line. NOTE: The data set WORK.DATATEST has 0 observations and 3 variables. NOTE: DATA statement used (Total process time):       real time           0.03 seconds       cpu time            0.03 seconds 6306  proc print data=dataset;run; ERROR: File WORK.DATASET.DATA does not exist. NOTE: The SAS System stopped processing this step because of errors. NOTE: PROCEDURE PRINT used (Total process time):       real time           0.00 seconds       cpu time            0.00 seconds   ... View more

How would I convert this to a SAS dataset with rows being records and columns being variables if I do not have a JSON engine   {"widget": {     "debug": "on",     "window": {         "title": "Sample Konfabulator Widget",         "name": "main_window",         "width": 500,         "height": 500     },     "image": {         "src": "Images/Sun.png",         "name": "sun1",         "hOffset": 250,         "vOffset": 250,         "alignment": "center"     },     "text": {         "data": "Click Here",         "size": 36,         "style": "bold",         "name": "text1",         "hOffset": 250,         "vOffset": 100,         "alignment": "center",         "onMouseUp": "sun1.opacity = (sun1.opacity / 100) * 90;"     } }}    ... View more

Any documentation or code examples that produces simple programming examples to read in xml data to structured rows and columns in SAS ... View more

Given the output below after running some code in manipulating data from JSON. data x; infile '\\kashmir\BFD\sample.json.txt' lrecl=320000 dsd dlm='{},:[]'; input x : $400. @@; run; data want;  merge x x(firstobs=2 rename=(x=value));  if lowcase(x) in ("id" "time" "ip_address" "identity" "page" "user_agent" "answer" "comment" "sessionid"  "language" "locale" "channel"); run; proc print data=want; run;   Output:                  Obs    x             value                    1    id            89702492                    2    time          2016-10-06 14:26:25 UTC                    3    ip_address    111.111.111.111                    4    identity      xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                    5    page          https://secure.hello.com                    6    user_agent    Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit                    7    answer        Other please say                    8    comment       I dont know                    9    SessionID     4444444444                   10    Language      fr                   11    Locale        Be                   12    Channel       Affiliate                   13    id            89702444                   14    time          2014-10-14 14:26:25 UTC                   15    ip_address    111.111.111.111                   16    identity      xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx                   17    page          https://secure.goodbye.com                   18    user_agent    Mozilla/5.0 (Windows NT 6.3; WOW64) ricjie                   19    answer        Other please say                   20    comment       I dont know                   21    SessionID     3124444444                   22    Language      fr                   23    Locale        Be                   24    Channel       nothing     How do I convert above data such that a new record begins with the key ID and all the subsequent keys along with ID are variables. So in above case, have two records with variables beginning with ID and ending in channel.      ... View more

Is there simple base SAS programming that read in the following JSON type data. See below example.   { Tenure: 2 spend: 5   } {  tenure:6 products:4 region:PQ spend:7 } { Credit score:100 region:ont tenure:7 country:can } { Credit score:50 country:US } { Tenure:5 region:US spend:100 creditscore:300 }     ... View more