Using SPSS java plugin to retrive AIC from generalized linear model
Locked
 
|
Hi SPSS guru,
I have written apiece of code to retrieve AIC from a generalized linear model using JAVA plugin package spss; import com.ibm.statistics.plugin.StatsException; import com.ibm.statistics.plugin.StatsUtil; /** * * @author s3911541 */ public class SPSSJavaPlugin { /** * @param args the command line arguments */ public static void main(String[] args) { // TODO code application logic here try { StatsUtil.start(); String[] command={ "GET", "FILE='X:/chapter1/patientanalysis10.sav'.", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'.", "GENLIN TrueAdverseEvents (REFERENCE=LAST) WITH sex1 DayOfWeek_Weekends DayOfWeek_Weekday DyOfWeek_Daybeforeafterweekends AdmissionSource_CasualtyAccidentEmerg AdmissionSource_OtherIncludesReferalsfromLMOetc AdmissionSource_WaitingList AdmissionSource_TransferfromOtherAcuteHospExtCareRehabGer AdmissionSource_QualifiedUnqualifiedNewborn AdmissionSource_ChangefromPsychUnitorPsychogeriatric Age add1 bed1 diss1 pe1", "/MODEL sex1 DayOfWeek_Weekends DayOfWeek_Weekday DyOfWeek_Daybeforeafterweekends AdmissionSource_CasualtyAccidentEmerg AdmissionSource_OtherIncludesReferalsfromLMOetc AdmissionSource_WaitingList AdmissionSource_TransferfromOtherAcuteHospExtCareRehabGer AdmissionSource_QualifiedUnqualifiedNewborn AdmissionSource_ChangefromPsychUnitorPsychogeriatric Age add1 bed1 diss1 pe1 INTERCEPT=YES DISTRIBUTION=BINOMIAL LINK=LOGit" , "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=MODEL MAXITERATIONS=100 MAXSTEPHALVING=5 PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD LIKELIHOOD=FULL ", "/MISSING CLASSMISSING=EXCLUDE ", "/PRINT FIT", //"OMSEND TAG='fit'." }; StatsUtil.submit(command); //StatsUtil.stop(); String handle = "Goodness_of_Fit"; String context = "/outputTree"; String xpath = "//category[@text='Akaike's Information Criterion (AIC)']/cell/@text"; Double result = Double.valueOf(StatsUtil.evaluateXPath(handle, context, xpath)[0]); StatsUtil.deleteXPathHandle(handle); } catch (StatsException e) { e.printStackTrace(); } } } However, I got exception at the bold line com.ibm.statistics.plugin.StatsException: Invalid handle object. at com.ibm.statistics.plugin.XDAPI.evaluateXPath(Unknown Source) at com.ibm.statistics.plugin.StatsUtil.evaluateXPath(Unknown Source) at spss.SPSSJavaPlugin.main(SPSSJavaPlugin.java:75) The reasults for GEnrlized linear model shows coorectly but I think my XPath or other things are wronmg..doesn anyobne can help or have any clue..is my XPATh is correct? Thanks for any help |
Re: Using SPSS java plugin to retrive AIC from generalized linear model
|
|
The code in the email is too scrambled
for me to make sense of, but it appears that you have invalid SPSS variable
names in the program. Names are limited to 64 bytes, and at least
one is 75 bytes long. That would presumably cause the procedure to
fail, and there would nothing for OMS to capture for the workspace.
Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: Luckyluke <[hidden email]> To: [hidden email] Date: 09/24/2015 07:37 AM Subject: [SPSSX-L] Using SPSS java plugin to retrive AIC from generalized linear model Sent by: "SPSSX(r) Discussion" <[hidden email]> Hi SPSS guru, I have written apiece of code to retrieve AIC from a generalized linear model using JAVA plugin package spss; import com.ibm.statistics.plugin.StatsException; import com.ibm.statistics.plugin.StatsUtil; /** * * @author s3911541 */ public class SPSSJavaPlugin { /** * @param args the command line arguments */ public static void main(String[] args) { // TODO code application logic here try { StatsUtil.start(); String[] command={ "GET", "FILE='X:/chapter1/patientanalysis10.sav'.", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'.", "GENLIN TrueAdverseEvents (REFERENCE=LAST) WITH sex1 DayOfWeek_Weekends DayOfWeek_Weekday DyOfWeek_Daybeforeafterweekends AdmissionSource_CasualtyAccidentEmerg AdmissionSource_OtherIncludesReferalsfromLMOetc AdmissionSource_WaitingList AdmissionSource_TransferfromOtherAcuteHospExtCareRehabGer AdmissionSource_QualifiedUnqualifiedNewborn AdmissionSource_ChangefromPsychUnitorPsychogeriatric Age add1 bed1 diss1 pe1", "/MODEL sex1 DayOfWeek_Weekends DayOfWeek_Weekday DyOfWeek_Daybeforeafterweekends AdmissionSource_CasualtyAccidentEmerg AdmissionSource_OtherIncludesReferalsfromLMOetc AdmissionSource_WaitingList AdmissionSource_TransferfromOtherAcuteHospExtCareRehabGer AdmissionSource_QualifiedUnqualifiedNewborn AdmissionSource_ChangefromPsychUnitorPsychogeriatric Age add1 bed1 diss1 pe1 INTERCEPT=YES DISTRIBUTION=BINOMIAL LINK=LOGit" , "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=MODEL MAXITERATIONS=100 MAXSTEPHALVING=5 PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD LIKELIHOOD=FULL ", "/MISSING CLASSMISSING=EXCLUDE ", "/PRINT FIT", //"OMSEND TAG='fit'." }; StatsUtil.submit(command); //StatsUtil.stop(); String handle = "Goodness_of_Fit"; String context = "/outputTree"; String xpath = "//category[@text='Akaike's Information Criterion (AIC)']/cell/@text"; *Double result = Double.valueOf(StatsUtil.evaluateXPath(handle, context, xpath)[0]);* StatsUtil.deleteXPathHandle(handle); } catch (StatsException e) { e.printStackTrace(); } } } However, I got exception at the bold line com.ibm.statistics.plugin.StatsException: Invalid handle object. at com.ibm.statistics.plugin.XDAPI.evaluateXPath(Unknown Source) at com.ibm.statistics.plugin.StatsUtil.evaluateXPath(Unknown Source) at spss.SPSSJavaPlugin.main(SPSSJavaPlugin.java:75) The reasults for GEnrlized linear model shows coorectly but I think my XPath or other things are wronmg..doesn anyobne can help or have any clue..is my XPATh is correct? Thanks for any help -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Using-SPSS-java-plugin-to-retrive-AIC-from-generalized-linear-model-tp5730654.html Sent from the SPSSX Discussion mailing list archive at Nabble.com. ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
Re: Using SPSS java plugin to retrive AIC from generalized linear model
Administrator
|
I didn't even notice that!
Maybe try working on useful abbreviations. These names are a complete joke and would be a complete PITA to work with for any period of time. AdmissionSource? Maybe AdmSrc? NOTE: SPSS Supports VARIABLE LABELS? Maybe you DON'T want to have your variable names to be VARIABLE LABELS. HINT: Make sure your code works in a regular syntax window before stuffing into a MACRO/Python/Java wrapper!!! Haven't we been down this road with you previously? ----
Please reply to the list and not to my personal email.
Those desiring my consulting or training services please feel free to email me. --- "Nolite dare sanctum canibus neque mittatis margaritas vestras ante porcos ne forte conculcent eas pedibus suis." Cum es damnatorum possederunt porcos iens ut salire off sanguinum cliff in abyssum?" |
|
|
In reply to this post by Jon K Peck
Hi Thanks for the reply,
I got the same error when I shortened the variable name my commend is as follow: "GET", "FILE='X:/chapter1/patientanalysis10.sav'.", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'.", "DATASET NAME DataSet1 WINDOW=FRONT.", "GENLIN TrueAdverseEvents (ORDER=ASCENDING) BY D_Weekends D_Weekday D_Daybeforeafterweekends A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit sex1 (ORDER=ASCENDING) WITH add1 bed1 diss1 pe1 Age ", "/MODEL D_Weekends D_Weekday D_Daybeforeafterweekends A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit sex1 add1 bed1 diss1 pe1 Age INTERCEPT=YES", "DISTRIBUTION=MULTINOMIAL LINK=CUMLOGIT", "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=ROBUST MAXITERATIONS=100 MAXSTEPHALVING=5", "PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD", "LIKELIHOOD=FULL", "/MISSING CLASSMISSING=EXCLUDE", "/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION." The output shows the AIC and other information regrding the GENLIN but it cant retrieve the AIC using the xpath.. I have put the complete source file here can you mention what is wrong with the codes? |
Re: Using SPSS java plugin to retrive AIC from generalized linear model
|
|
I still see variable names that are too
long, e.g.,
A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList which is 71 characters. Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: Luckyluke <[hidden email]> To: [hidden email] Date: 09/25/2015 07:36 AM Subject: Re: [SPSSX-L] Using SPSS java plugin to retrive AIC from generalized linear model Sent by: "SPSSX(r) Discussion" <[hidden email]> Hi Thanks for the reply, I got the same error when I shortened the variable name my commend is as follow: "GET", "FILE='X:/chapter1/patientanalysis10.sav'.", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'.", "DATASET NAME DataSet1 WINDOW=FRONT.", "GENLIN TrueAdverseEvents (ORDER=ASCENDING) BY D_Weekends D_Weekday D_Daybeforeafterweekends A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit sex1 (ORDER=ASCENDING) WITH add1 bed1 diss1 pe1 Age ", "/MODEL D_Weekends D_Weekday D_Daybeforeafterweekends A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit sex1 add1 bed1 diss1 pe1 Age INTERCEPT=YES", "DISTRIBUTION=MULTINOMIAL LINK=CUMLOGIT", "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=ROBUST MAXITERATIONS=100 MAXSTEPHALVING=5", "PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD", "LIKELIHOOD=FULL", "/MISSING CLASSMISSING=EXCLUDE", "/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION." The output shows the AIC and other information regrding the GENLIN but it cant retrieve the AIC using the xpath.. I have put the complete source file here <http://www.megafileupload.com/9oiY/SPSSJavaPlugin.java> can you mention what is wrong with the codes? -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Using-SPSS-java-plugin-to-retrive-AIC-from-generalized-linear-model-tp5730654p5730665.html Sent from the SPSSX Discussion mailing list archive at Nabble.com. ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
|
|
Hi john,
That is three variables not one variable as having spaces between them...
|
|
In reply to this post by Luckyluke
This later version have added the terminating point after the subcommand /PRINT. Did the GENLIN command work in the SPSS Syntax Window?
Your first line ('GENLIN TrueAdverseEvents (ORDER=ASCENDING) BY D_Weekends ...' is 296 characters, and the /MODEL statement is 248. There is a line length limit of 256 bytes after which the command gets truncated. See Help on 'Running Commands'. Does it work if the variables are on different lines? "GENLIN TrueAdverseEvents (ORDER=ASCENDING) ", " BY D_Weekends D_Weekday D_Daybeforeafterweekends ", " A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList ", " A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit ", " sex1 ", " (ORDER=ASCENDING) ", " WITH add1 bed1 diss1 pe1 Age ", "/MODEL D_Weekends D_Weekday D_Daybeforeafterweekends ", " A_CasualtyAccidentEmerg A_OtherIncludesReferalsfromLMOetc A_WaitingList ", " A_TransferfromOtherAcuteHosp A_QualifiedUnqualifiedNewborn A_ChangefromPsychUnit ", " sex1 add1 bed1 diss1 pe1 Age ", " INTERCEPT=YES DISTRIBUTION=MULTINOMIAL LINK=CUMLOGIT", "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=ROBUST MAXITERATIONS=100 MAXSTEPHALVING=5", " PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ", " ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD LIKELIHOOD=FULL", "/MISSING CLASSMISSING=EXCLUDE", "/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION.", Otherwise you should try to abbreviate your variable names and get each command line to be less than 256 characters. You have all 15 variable names (some very long) in both BY and MODEL lines so efficient abbreviation should make difference in both lines. HTH, PRogman
|
|
|
This post was updated on .
Hi,
I have shortened them but still getting the same error ..as I told it shows the results (including AIC) to the console of Netbeans..but not getting the xpath..I think there is something wrong with my XPATh or expression "GET ", "FILE='X:/chapter1/patientanalysis10.sav'. ", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'. ", "DATASET NAME DataSet1 WINDOW=FRONT.", "GENLIN TrueAdverseEvents (ORDER=ASCENDING) BY D_Weekends D_Weekday D_Beforeafterweekends A_Casualty A_ReferalsfromLMO A_WaitingList A_OtherAcuteHosp A_Newborn A_PsychUnit sex1 (ORDER=ASCENDING) WITH Age add1 bed1 diss1 pe1 ", "/MODEL D_Weekends D_Weekday D_Beforeafterweekends A_Casualty A_ReferalsfromLMO A_WaitingList A_OtherAcuteHosp A_Newborn A_PsychUnit sex1 Age add1 bed1 diss1 pe1 ", "DISTRIBUTION=MULTINOMIAL LINK=CUMLOGIT ", "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=MODEL MAXITERATIONS=100 MAXSTEPHALVING=5 ", "PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD ", "LIKELIHOOD=FULL ", "/MISSING CLASSMISSING=EXCLUDE ", "/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION. " |
Re: Using SPSS java plugin to retrive AIC from generalized linear model
|
|
You have the wrong identifier in your OMS
command. It should look something like
/IF COMMANDS=['Generalized Linear Models'] SUBTYPES=['Goodness of Fit'] Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: Luckyluke <[hidden email]> To: [hidden email] Date: 09/28/2015 07:54 AM Subject: Re: [SPSSX-L] Using SPSS java plugin to retrive AIC from generalized linear model Sent by: "SPSSX(r) Discussion" <[hidden email]> Hi, I have shortened them but still getting the same error ..as I told it shows the results (including AIC) to the console of Netbeans..but not getting the xpath..I think there is something wrong with my XPATh or expression "GET ", "FILE='X:/chapter1/patientanalysis10.sav'. ", "OMS SELECT TABLES ", "/IF COMMANDS=['GENLN'] SUBTYPES=['Goodness of Fit'] ", "/DESTINATION FORMAT=OXML XMLWORKSPACE='Goodness_of_Fit' ", "/TAG='fit'. ", "DATASET NAME DataSet1 WINDOW=FRONT.", "GENLIN TrueAdverseEvents (ORDER=ASCENDING) BY D_Weekends D_Weekday D_Beforeafterweekends A_Casualty A_ReferalsfromLMO A_WaitingList A_OtherAcuteHosp A_Newborn A_PsychUnit sex1 (ORDER=ASCENDING) WITH Age add1 bed1 diss1 pe1 ", "/MODEL D_Weekends D_Weekday D_Beforeafterweekends A_Casualty A_ReferalsfromLMO A_WaitingList A_OtherAcuteHosp A_Newborn A_PsychUnit sex1 Age add1 bed1 diss1 pe1 ", "DISTRIBUTION=MULTINOMIAL LINK=CUMLOGIT ", "/CRITERIA METHOD=FISHER(1) SCALE=1 COVB=MODEL MAXITERATIONS=100 MAXSTEPHALVING=5 ", "PCONVERGE=1E-006(ABSOLUTE) SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 CITYPE=WALD ", "LIKELIHOOD=FULL ", "/MISSING CLASSMISSING=EXCLUDE ", "/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION. " I am just outputing the console to a text file and then getting AIC from that... -- View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Using-SPSS-java-plugin-to-retrive-AIC-from-generalized-linear-model-tp5730654p5730680.html Sent from the SPSSX Discussion mailing list archive at Nabble.com. ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD |
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |