MStarmans91 / WORC

Workflow for Optimal Radiomics Classification
Other
66 stars 19 forks source link

classify job has failed #3

Closed josemanuel097 closed 6 years ago

josemanuel097 commented 6 years ago

Traceback (most recent call last): File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/WORC/resources/fastr_tools/predict/bin/TrainClassifier.py", line 64, in main() File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/WORC/resources/fastr_tools/predict/bin/TrainClassifier.py", line 60, in main fixedsplits=args.fs) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/trainclassifier.py", line 120, in trainclassifier load_features(feat_train, patientinfo_train, label_type) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/trainclassifier.py", line 276, in load_features label_type, modnames) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/IOparser/file_io.py", line 77, in load_data image_features) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/genetics/genetic_processing.py", line 179, in findmutationdata mutation_data_temp = load_mutation_status(patientinfo, mutation_type) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/genetics/genetic_processing.py", line 41, in load_mutation_status genetic_file) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/PREDICT/genetics/genetic_processing.py", line 79, in load_genetic_file data = np.loadtxt(input_file, np.str) File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/numpy/lib/npyio.py", line 1101, in loadtxt for x in read_data(_loadtxt_chunksize): File "/home/jose/anaconda3/envs/worc_pro/lib/python2.7/site-packages/numpy/lib/npyio.py", line 1025, in read_data % line_num) ValueError: Wrong number of columns at line 2

MStarmans91 commented 6 years ago

Looks like the file you provided in the labels_train source in WORC is not formatted correctly. It should be a text file, in which the first column is headed patient and contains the patientnames. The other columns should head the label name and contain the labels, e.g.:

Patient Label1 Label2 Pname1 1 0 Pname2 3 5 Pname3 0 1

Note: as the fields are separated by spaces, you cannot use spaces in the patient names!

I will implement a catch for this in PREDICT.

josemanuel097 commented 6 years ago

That fixed the issue. Thanks .