Dear Challenge Organizers, Our team, Metformin-121, has a submission (ID: 9760510) that resulted in an INVALID status with the error message "Container did not generate a file called predictions.csv". We have successfully run our Docker container in a local test that mimics the official environment (including using the --network none flag), and it correctly generates the predictions.csv file. This leads us to believe the error may be due to a difference in the official evaluation environment, such as the structure of the hidden test data or resource limits. Could you please provide us with any additional logs (specifically the stderr or stdout from our container's execution) to help us troubleshoot the issue? Thank you for your time and assistance. Best Regards, Kai, on behalf of Metformin-121

Created by Hsuan-Kai Wang DoingWell
Hi @DoingWell , Thanks for providing the extra context regarding your model. Similar to your team's other submission (https://www.synapse.org/Synapse:syn66496696/discussion/threadId=12473), the error received for subID 9760510 was: ``` start Load input data Load feature preprocessor Build feature matrix (shape = (542673, 3)) Traceback (most recent call last) /home/user/run_model.py:102 in main 99 print('Build feature matrix (shape = {})'.format(X.shape)) 100 101 # ---- Apply preprocessing ---- 102 X_imp = imputer.transform(X) 103 X_scaled = scaler.transform(X_imp) 104 print('Apply preprocessing') 105 locals adata = AnnData object with n_obs n_vars = 542673 36601 backed at '/input/data.h5ad' obs: 'library_prep', 'Donor ID', 'Method', 'Sex', 'Age at Death', 'Race (choice=White)', 'Race (choice=Black/ African American)', 'Race (choice=Asian)', 'Race (choice=American Indian/ Alaska Native)', 'Race (choice=Native Hawaiian or Pacific Islander)', 'Race (choice=Unknown or unreported)', 'Race (choice=Other)', 'Hispanic/Latino', 'Years of education', 'PMI', 'APOE Genotype', 'Class', 'Subclass', 'Supertype' var: 'gene_ids', 'feature_types', 'genome' uns: 'log1p' layers: 'UMIs' adata_path = '/input/data.h5ad' feat_names = [ 'Age at Death', 'Years of education', 'PMI', 'percent 6e10 positive area', 'percent AT8 positive area', 'percent NeuN positive area', 'percent GFAP positive area', 'percent aSyn positive area', 'percent pTDP43 positive area' ] imputer = SimpleImputer(strategy='median') input_dir = '/input' obs_feats = ['Age at Death', 'Years of education', 'PMI'] output_dir = '/output' parts = [ array([[96. , 14. , 10.3], [96. , 14. , 10.3], [96. , 14. , 10.3], ..., [97. , 14. , 4.8], [97. , 14. , 4.8], [97. , 14. , 4.8]], shape=(542673, 3)) ] preproc = { 'imputer': SimpleImputer(strategy='median'), 'scaler': StandardScaler(), 'feat_names': [ 'Age at Death', 'Years of education', 'PMI', 'percent 6e10 positive area', 'percent AT8 positive area', 'percent NeuN positive area', 'percent GFAP positive area', 'percent aSyn positive area', 'percent pTDP43 positive area' ] } ... [truncated] ValueError: X has 3 features, but SimpleImputer is expecting 9 features as input. ``` Hope this helps!

Submission Error - "Container did not generate predictions.csv" (ID: 9760510) page is loading…