OHDSI Home | Forums | Wiki | Github

Patient Level Prediction - Run analysis - Error

Hi All,

Using ATLAS, new Patient Level Prediction analysis created. Now i downloaded the prediction_study.zip package from ATLAS.

When I run the prediction using Rstudio, i am getting error.

In the console its shows this error

“No plpData - probably empty cohort issue
Patient-Level Prediction Package version 3.0.10”

In the log file:

2020-08-18 20:39:29 [Main thread] TRACE PatientLevelPrediction 3 Error with getPlpData:Error: Error executing SQL: cannot change working directory An error report has been created at D:/atlas_prediction/errorReport.txt

ErrorReport.txt:

DBMS:
sql server

Error:
cannot change working directory

SQL:
SELECT *
FROM (
SELECT row_id, covariate_id, covariate_value FROM #cov_1 UNION ALL
SELECT row_id, covariate_id, covariate_value FROM #cov_2 UNION ALL
SELECT row_id, covariate_id, covariate_value FROM #cov_3 UNION ALL
SELECT row_id, covariate_id, covariate_value FROM #cov_4 UNION ALL
SELECT row_id, covariate_id, covariate_value FROM #cov_5
) all_covariates;

R version:
R version 3.6.0 (2019-04-26)

Platform:
x86_64-w64-mingw32

Attached base packages:

  • stats
  • graphics
  • grDevices
  • utils
  • datasets
  • methods
  • base

Other attached packages:

  • test (0.0.1)
  • DatabaseConnector (2.4.2)
    ===================================

Can anyone please advise, what could be the issue.

thanks in advance
regards
Chidam

the most cases of the “cannot change working directory” in my experience, there was a typo or unclear directory in fftemp directory setting.

1 Like

Hi Chungsoo_Kim,

Thanks for your reply. Actually in the CodeToRun.R, I set the options(fftempdir="./cache"), Initially i thought the code will create this folder automatically. After your reply, I create cache folder manually, now i am getting different error. Can you please advise, have you faced this error

please advise, thanks
Chidam

Hi Chungsoo_Kim,

Thanks for your advise. Now i am using full path in the script.

In the R console. No error.

But its not generating report. In the log files, it shows different error

Please advise if you have any experience in this error.

thanks in advance
chidam

Log file:

2020-08-20 23:28:40 [Main thread] INFO test execute Creating cohorts
2020-08-20 23:28:44 [Main thread] INFO test createCohorts Counting cohorts
2020-08-20 23:28:44 [Main thread] INFO test execute Running predictions
2020-08-20 23:28:44 [Main thread] TRACE PatientLevelPrediction Creating reference table
2020-08-20 23:28:44 [Main thread] TRACE PatientLevelPrediction Writing settings csv to D:/atlas_prediction/plp1Results/settings.csv
2020-08-20 23:28:44 [Main thread] TRACE PatientLevelPrediction Running setting 1
2020-08-20 23:29:34 [Main thread] TRACE PatientLevelPrediction Done plpData.
2020-08-20 23:29:34 [Main thread] TRACE PatientLevelPrediction Saving data in setting 1
2020-08-20 23:29:35 [Main thread] TRACE PatientLevelPrediction Setting population settings for setting 1
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction outcomeId: 46
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction binary: TRUE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction includeAllOutcomes: TRUE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction firstExposureOnly: FALSE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction washoutPeriod: 365
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction removeSubjectsWithPriorOutcome: FALSE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction requireTimeAtRisk: TRUE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction minTimeAtRisk: 364
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction riskWindowStart: 1
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction addExposureDaysToStart: FALSE
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction riskWindowEnd: 365
2020-08-20 23:29:35 [Main thread] DEBUG PatientLevelPrediction addExposureDaysToEnd: FALSE
2020-08-20 23:29:35 [Main thread] TRACE PatientLevelPrediction Requiring 365 days of observation prior index date
**2020-08-20 23:29:36 [Main thread] TRACE PatientLevelPrediction 3 Error with pop:Error in $<-.data.frame(*tmp*, “riskStart”, value = 1L): replacement has 1 row, data has 0
2020-08-20 23:29:36 [Main thread] TRACE PatientLevelPrediction Done pop.
2020-08-20 23:29:36 [Main thread] TRACE PatientLevelPrediction Running runPlp for setting 1
2020-08-20 23:29:36 [Main thread] INFO PatientLevelPrediction Patient-Level Prediction Package version 3.0.10
** 2020-08-20 23:29:36 [Main thread] TRACE PatientLevelPrediction 3
2020-08-20 23:29:36 [Main thread] TRACE PatientLevelPrediction Done runPlp.
t