pycox

pycox copied to clipboard

Calculating Estimated Population Survival Curve

4

Hi Pycox Community! I am working on a project applying survival analysis to the dwell times of insects and have found the PyCox package quite useful. I have mostly been...

puckybreg

Softmax layer and residual connections in DeepHitSingle model

1

Hi, I am following this DeepHit tutorial for a single event - [https://github.com/havakv/pycox/blob/master/examples/deephit.ipynb](url) In the model architecture, the "**_MLPVanilla_**" class inserts 2 hidden, linear layers. It seems like you don't...

Anivader

ValueError: cannot convert float NaN to integer

1

The below code form the examples notebook of CoxTime works when pandas=1.3.5 but fails otherwise ``` %%time log = model.fit(x_train, y_train, batch_size, epochs, callbacks, verbose, val_data=val.repeat(10).cat()) ``` ``` /opt/conda/lib/python3.10/site-packages/pycox/models/data.py:90, in...

Aniket99coder

is_monotonic should be update to is_monotonic_increasing

1

> \pycox\evaluation\eval_surv.py:36: FutureWarning: is_monotonic is deprecated and will be removed in a future version. Use is_monotonic_increasing instead.

JIN-Li-stats

I appreciate this library but the documentation for models is quite lackluster and the jupyter notebook is not enough to re-use this for other, more complex, use cases. Pretty frustrating...

KristofPusztai

I have been running my training notebook routinely when suddenly I received an error upon importing pycox: **initialization of _internal failed without raising an exception** Has anyone else encountered this...

afuentes09651

Issue in function cox_time.py

1

Since the release of pandas 2.0.0, the function iteritems is depreciated. (see https://pandas.pydata.org/docs/dev/whatsnew/v2.0.0.html). Because of this, the function cox_time.py doesn't work anymore, can this be updated? I cannot give a...

jensrobben

ValueError: cannot convert float NaN to integer

1

Hi, I encounter the problem with code in pycox.model.data.py, the function sample_alive_from_dates has bug that when we create samp samp = np.empty((dates.size, n_control), dtype=int) samp.fill(np.nan) howerer, this part always givens...

Serendipity-Sylvia

AttributeError: 'DeepHitSingle' object has no attribute 'state_dict'

1

I'm trying to save my model using tensor flow save and I get the following Error when I use state_dict. `mdl.state_dict()` I get the follwing `AttributeError: 'DeepHitSingle' object has no...

zachfreitas

How to use dropout in eval_

1

Hi, first of thank you so much for this great python package. I am wondering how to approach the MC dropout in deepsurv model, i.e., keep the dropout active when...

iuimaki