search

l-magnificence / Mime

Machine learning-based integration model with elegant performance
Other
57 stars 10 forks source link

When using the sample data, it can run successfully, but when using my own data, the gbm step does not produce results for a long time, and error occured #34

Closed yandouwahhh closed 1 month ago

yandouwahhh commented 1 month ago

微信图片_20240717144313

There seems to be a problem when it comes to gbm methods.It's not like a mistake because the data is too big

my data:

dim(list_train_vali_Data$Dataset1) [1] 112 20 dim(list_train_vali_Data$Dataset2) [1] 107 20 list_train_vali_Data$Dataset1[1:4,1:5] ID OS.time OS FKBP10 TPPP3 1 TCGA.A1.A0SK.01A 967 1 5.049623 4.615698 2 TCGA.A1.A0SP.01A 584 0 6.835768 4.319503 3 TCGA.A2.A04U.01A 2654 0 6.610821 3.443134 4 TCGA.A2.A0CM.01A 754 1 5.602947 2.746017 list_train_vali_Data$Dataset2[1:4,1:5] ID OS.time OS BGN CHPF 1 GSM1419942 1520 1 10.207883 7.977907 2 GSM1419943 1281 1 8.707468 6.584553 3 GSM1419944 1066 1 9.402426 6.861479 4 GSM1419945 1050 1 10.449300 6.938301

l-magnificence commented 1 month ago

If your environment don't support multicore and you run this process in the condition of 1 core, it may run for a long time. Besides we recommend gene set with more than 50 genes.

yandouwahhh commented 1 month ago

Thanks for your reply. I will try it.