search

nliulab / AutoScore

AutoScore: An Interpretable Machine Learning-Based Automatic Clinical Score Generator
31 stars 4 forks source link

it does not work when i use "AutoScore_parsimony_Survival" function #9

Open gbjx opened 10 months ago

gbjx commented 10 months ago

hello, i have a question, it does not work when i use "AutoScore_parsimony_Survival" function， it tells me that "Error in AUC.uno(Surv.rsp.new, Surv.rsp.new, lpnew = score, times = km_time) : NA/NaN/Inf in foreign function call (arg 9) In addition: Warning messages: 1: In AutoScore_parsimony_Survival(train_set = train_set, validation_set = validation_set, : WARNING: the n_max (12) is larger the number of all variables (10). We Automatically revise the n_max to 10 2: In assign_score(validation_set_2, score_table) : NAs introduced by coercion 3: In compute_auc_val_survival(train_set_1, validation_set_1, variable_list, : NA in the validation_set_3: 4578", but at the begining, check_data_survival(sample_data_survival)，it tells me that "Data type check passed. No NA in data. ". the data and code in the following. thanks. seerautoscore.zip

gbjx commented 10 months ago

I have found the reason for does not work, the colname can not "N", it may be known as "NA".

nliulab commented 10 months ago

Thank you for the updates.