Carsten
Carsten
I fixed it here: https://github.com/taxus13/wtte-rnn/tree/bugfix/float-fix-for-mkl However, some tests are failing: 1. test_discrete_padded_pipeline: different dtypes int64/int32 2. test_padded_between (same) 3. test_censoring_funs_no_time_discrete (AssertionError: not_censored failed) 4. test_censoring_funs_with_time_discrete (same)
I have the most recent pandas 0.23.1 It seems that master is ahead of development and I branched from master. Can you rebase develop on master?
Hi, thank you for your response! This is a histogram of my ttes, which is roughly Weibull distributed: ![hist_tte](https://user-images.githubusercontent.com/6933947/45042451-019f3380-b06b-11e8-9af1-933b5a4b4cf6.PNG) Pretraining leads to the following values: ```(before pretrain) alpha: 55.90673 beta...
Hi, thank you for your help! My only features were the event indicator (x==1 when tte==0) and the time (scaled from 0 to 1). * Today I tried the following:...
Awesome, thank you very much! May I buy you a beer or something? I fixed my data, now it looks like this: timestamp | event marker | tte ------------ |...