How to Use DeepSurv Exactly?

[koji1225shasha]

I am still quite new to Python, and am trying to apply my data to deepsurv. Would you mind sharing the exact code you wrote between the two paragraphs below? I appreciate your help.

Training DeepSurv can be done in a few lines. First, all you need to do is prepare the datasets to have the following keys:
{
'x': (n,d) observations (dtype = float32),
't': (n) event times (dtype = float32),
'e': (n) event indicators (dtype = int32)
}

Then prepare a dictionary of hyper-parameters. And it takes only two lines to train a network:
network = deepsurv.DeepSurv(**hyperparams)
log = network.train(train_data, valid_data, n_epochs=500)

[jaredleekatzman]

I just uploaded a simple notebook showing how to take a CSV file and create a dataset to use with DeepSurv.

Take a look at that and see if you understand it more. And then let me know if you have any other questions

[koji1225shasha]

Thank you so much for your comment. I can run mots of the codes without an issues. At the end, I cannot run the last two part of the codes as below:

KeyError Traceback (most recent call last)
in ()
1 # Print the final metrics
----> 2 print('Train C-Index:', metrics['c-index'][-1])

KeyError: 'c-index'

---

KeyError Traceback (most recent call last)
in ()
1 # Plot the training / validation curves
----> 2 viz.plot_log(metrics)

/Users/ksasaki1/AppData/Local/Programs/Python/Python36/Lib/site-packages/DeepSurv-master/deepsurv\viz.py in plot_log(log)
36 VALID_CI = 'valid_c-index'
37
---> 38 num_epochs = len(log[TRAIN_LOSS])
39
40 # Plots Negative Log Likelihood vs. Epoch

KeyError: 'loss'

P.S.
I have one favor. Could you share how we should add code for the treatment recommendation?

[nishan2204]

I'm getting the same error for last two lines of code, with loss as a KeyError.

Adding to messenger's point above, some code on how to obtain the personalized treatment recommendation would be appreciated. Sorry, I'm actually giving a literature review with your paper as part of a PoC for a project.