predict.ranger -> predict -> predict.ranger.forest Execution halted" I wonder what is used as the testing dataset in fast queue and whether there are specific columns that are present in the Aug 25th training data set but not present in the test dataset. (I think the key folder and was_preterm, was_early_preterm columns are in training only). Also, another technical difficulty arises since I cannot debug my docker image locally. When I run the built docker image locally and supply it with the training_data as the input parameter, it cannot properly find the input file and will instead print out the error message "/input//alpha_diversity/alpha_diversity.csv" is an invalid path. This is a bit weird to me as I have already changed the input directory to training_data. I am modifying the run_model.r file from the provided R sample (https://github.com/Sage-Bionetworks-Challenges/ptb-challenge-r-sample-model/blob/main/run_model.R), and the docker run command I have used is as following, "docker run --rm --network none -v $pwd/training_data_2022-08-25:/input:ro -v $pwd/output:/output:rw docker.synapse.org/syn36336616/ptb-dream-test:v2". I am using $pwd as I am using Windows Powershell with the linux backend. Let me know what you think. Thanks a lot!" />

Dear organizers, We have kept getting errors when we submit to the Fast Queue lane to test our model (submission id: 9725972). The log file says, "i Use `spec()` to retrieve the full column specification for this data. i Specify the column types or set `show_col_types = FALSE` to quiet this message. Rows: 300 Columns: 2119 Error in predict.ranger.forest(forest, data, predict.all, num.trees, type, : Error: One or more independent variables not found in data. Calls: predict -> predict.ranger -> predict -> predict.ranger.forest Execution halted" I wonder what is used as the testing dataset in fast queue and whether there are specific columns that are present in the Aug 25th training data set but not present in the test dataset. (I think the key folder and was_preterm, was_early_preterm columns are in training only). Also, another technical difficulty arises since I cannot debug my docker image locally. When I run the built docker image locally and supply it with the training_data as the input parameter, it cannot properly find the input file and will instead print out the error message "/input//alpha_diversity/alpha_diversity.csv" is an invalid path. This is a bit weird to me as I have already changed the input directory to training_data. I am modifying the run_model.r file from the provided R sample (https://github.com/Sage-Bionetworks-Challenges/ptb-challenge-r-sample-model/blob/main/run_model.R), and the docker run command I have used is as following, "docker run --rm --network none -v $pwd/training_data_2022-08-25:/input:ro -v $pwd/output:/output:rw docker.synapse.org/syn36336616/ptb-dream-test:v2". I am using $pwd as I am using Windows Powershell with the linux backend. Let me know what you think. Thanks a lot!

Created by Shengqi Hang sqhang
Dear @sqhang , The Fast Lane queue is configured to mount as its input a subset (without replacement) of the 08-25-2022 training data. You are also correct in that the Fast Lane will not include any of the "outcome" columns in the metadata file, including "was_preterm", "was_early_preterm", "was_term", and "delivery_wk". I know this is silly to ask, but just for a sanity check -- does the training data folder you are mounting contain the `alpha_diversity/alpha_diversity.csv` file? Your Docker run looks correct to me otherwise. Hope this helps!

Invalid submission on Fast Queue page is loading…