by

## Where communities thrive

• Join over 1.5M+ people
• Join over 100K+ communities
• Free without limits
##### Activity
Cameron Davidson-Pilon
@CamDavidsonPilon
1) Instead of one large matrix for the x_ variables (which may cause problems with autograd), I instead chose a list of small matrices.
2) the lik variable is now incrementing as we go.
3) I like BFGS as a first routine to use, feel free to try others though.
Sandu Ursu
@sursu
Thanks a lot @CamDavidsonPilon !! Really helpful!
Gareth Brown
@gabrown
@CamDavidsonPilon hmm, I get your point. I have looked at the Kaplan-Meier distribution and it seems to match for the example I provided, however, when I look at the dataset I am interested in, there is a bias after the first 12 months. Is there any assumption about the hazards? We have very spikey hazards, with high hazard once every 12 months, and through the rest of the year the hazard is low. Do you think that would effect the performance?
That is an example of the comparison, where the blue line is the Kaplan-Meier estimate and the red line is the cox regresstion
Cameron Davidson-Pilon
@CamDavidsonPilon
Sorry @gabrown, I'm not exactly sure. KMF estimate != CoxPH baseline, generally, so differences are expected.
Cameron Davidson-Pilon
@CamDavidsonPilon

@CamDavidsonPilon for what it's worth, a short snippet of a slightly misleading error involving pandas.DataFrame.apply that took me a day to debug

task: use Cox to predict event probability for censored items at the time of their current duration

import lifelines as ll
import numpy as np
import pandas as pd

df = pd.DataFrame(np.random.randint(0, 100, size=(10, 2)), columns=['regressor', 'duration'])
df['event'] = np.random.choice([True, False], 10)
display(df)

# uncomment to lose the bool and fix the TypeError
#df['event'] = df['event'].astype(int)

cf = ll.CoxPHFitter()
cf.fit(df, duration_col='duration', event_col='event')

# select only censored items
df = df[df['event'] == 0]

func = lambda row: cf.predict_survival_function(row[['regressor']], times=row['duration'])
df.apply(func, axis=1)

'misleading' cause it will say the regressor column is non-numerical...

Cameron Davidson-Pilon
@CamDavidsonPilon
absolutely no need to apologize, especially since it was i who ignored docstring regarding the event data type in the first place ;)
Cameron Davidson-Pilon
@CamDavidsonPilon
Minor lifelines release: https://github.com/CamDavidsonPilon/lifelines/releases/tag/v0.22.5
@CamDavidsonPilon i feel so appreciated ;) glad i could help
Cameron Davidson-Pilon
@CamDavidsonPilon
Alexander Dmitryuk
@dmitryuk
Hello, Is it possible to use lifelines to predict ~ queue times? In my example, employees checks client's documents, they don't work on weekends, at night, have a dinner and etc. I want to know if client uploaded the document, predict how long time to wait left.
For example, training data - table contains documents verification process
document_id|start_at|ends_at|duration(ends_at - start_at)
Cameron Davidson-Pilon
@CamDavidsonPilon
Hi @dmitryuk, sure that can be done. Queue times fit perfectly into survival analysis. Since you suggest that when the client uploaded the doc is important, I would suggest that you use that feature (mapped to a cyclic variable¹) in a regression model. Ex:
from lifelines import WeibullAFTFitter

df['start_time'] = df['start_time'].map(map_to_seconds)
df['sin_start_time'] = np.sin(2*np.pi*df['start_time']/seconds_in_day)
df['cos_start_time'] = np.cos(2*np.pi*df['start_time']/seconds_in_day)
df = df.drop('start_time', axis=1)

wf = WeibullAFTFitter().fit(df, "duration")

wf.predict_survival_function(df)
wf.predict_median(df)
Since you want how long left to wait, you probably want to use the conditional_after kwarg in the predict_* methods as well
Vilane.
@vgs549
@CamDavidsonPilon have you considered counterfactual analysis in lifelines?
Cameron Davidson-Pilon
@CamDavidsonPilon
@vgs549 mmm not much - are you thinking about casual inference techniques?
Alexander Dmitryuk
@dmitryuk
This way I prepared the data as
id(doc id)|start_from_week_seconds(seconds past from start of week after client uploaded doc)|duration(seconds spent to check the doc)
After code line executed wf = WeibullAFTFitter().fit(df, "duration") exception throw
"StatisticalWarning: The diagonal of the variancematrix has negative values. This could be a problem with WeibullFitter's fit to the data."
Could you help to understand what is wrong in the code?
Vilane.
@vgs549
@CamDavidsonPilon yes, causal inference.
Cameron Davidson-Pilon
@CamDavidsonPilon
@vgs549 I've thought some about it, however I've left most of the burden on the user to choose models and inference appropriately. I would suggest checking out the Zepid package for more causal inference assistance
@dmitryuk ah, ignore it, I need to suppress that. Also, make sure to drop the id col in your model
Cameron Davidson-Pilon
@CamDavidsonPilon
:wave: minor lifelines release. Better support for pickling! https://github.com/CamDavidsonPilon/lifelines/releases
Vilane.
@vgs549
@CamDavidsonPilon Thanks, I will have a look.
Niranjan Ravichandra
@nravic
Hello! I'm trying to predict failure of a few robots with a pretty substantial time-series dataset, and I've been looking at lifelines as a potential method for doing so. The time series data has a few instances of failure, and I'm trying to correlate a number of other variables we have data on (such as forward velocity, number of stationary hours, etc) with failure. In short, I'm trying to get a window in which to predict possible failure based on historical data. Should I be using survival regression for this?
Niranjan Ravichandra
@nravic
Also going off the survival regression chapter in the wiki, each of my observations are obtained daily. Does the fact that the duration in my data is just 1 matter?
Cameron Davidson-Pilon
@CamDavidsonPilon
@nravic I think you can use lifelines, but you're in the realm of recurrent events, which lifelines has only a little support for (there may be another package out there?). Since you have daily snapshots, you probably want to use time-varying regression: https://lifelines.readthedocs.io/en/latest/Time%20varying%20survival%20regression.html
Niranjan Ravichandra
@nravic
Great, thanks @CamDavidsonPilon ! I'll look into this and also see if there's anything around for recurrent events.
Niranjan Ravichandra
@nravic
@CamDavidsonPilon I have data granular down to the second too however. would that see a better use from lifelines or am I better off looking elsewhere?
d-seki
@d-seki
Thank you very much for creating this wonderful tool for statistics. Let me ask you a subtle question. What null hypothesis are you assuming for CoxTimeVaryingFitter? I guess it is for beta to be zero. Best,
Julian Späth
@julianspaeth
Hey, I have a question concerning the concordance_index. I want to use my predicted cumulative hazard functions to compute the concordance_index and use them as predicted_scores. Is it the right way to sum up the chf of each sample and take the negative of it to compute the concordance_index on the basis of the cumulative hazard functions?
Youyang
@zxclcsq
Hello. I'm trying to replicate the Weibull AFT model prediction section in the lifelines docs, but the return is all NANs from the predict_survival_function. Any thoughts on this? The code I used is :
from lifelines import WeibullAFTFitter

aft = WeibullAFTFitter()
aft.fit(rossi_dataset, duration_col='week', event_col='arrest')

X = rossi_dataset.loc[:10]

aft.predict_survival_function(X)
Cameron Davidson-Pilon
@CamDavidsonPilon
Ahh sorry about the delay folks! I don't check this daily, and gitter didn't end me emails
@d-seki yes that's right, NH is that beta == 0

@julianspaeth depends on the model. Recall that the c-index only depends on ranking of values. For the Cox model, the summing the cumulative hazard won't change the ranking, so it won't matter what you use. For an AFT model, it may change the ranking.

Alternatively, you can choose a point in time, and use the CHF at that

@zxclcsq not good! Looks like I broke something...
I'll investigate asap
Cameron Davidson-Pilon
@CamDavidsonPilon
@zxclcsq for now, you must specify the times argument in predict_survival_function
Cameron Davidson-Pilon
@CamDavidsonPilon
The fix is in master: CamDavidsonPilon/lifelines@085258e
hpham04
@hpham04
Hello everyone, i just tried to play with lifelines. I look into some examples but still do not understand. As far as I understand, after training we should have a way to save the model, then we can use this model immediately without re-training model. Can you please help to advise
hpham04
@hpham04
Cameron Davidson-Pilon
@CamDavidsonPilon
@hpham04 yup that is - let me know if you have other questions or that doesn't work.
Cameron Davidson-Pilon
@CamDavidsonPilon
Is anyone experiencing problems installing / upgrading lifelines? Let me know!
d-seki
@d-seki
@CamDavidsonPilon Thanks very much!
Cameron Davidson-Pilon
@CamDavidsonPilon
I got conda forge working again, so we should start to see simultaneous conda & pypi releases again
Cameron Davidson-Pilon
@CamDavidsonPilon
:wave: Also, new minor release with some useful bug fixes: https://github.com/CamDavidsonPilon/lifelines/releases/tag/v0.22.9
Bojan Kostic
@bkos
@CamDavidsonPilon I see there are estimators for cumulative hazard function, and it is as well in your mathematical links between entities diagram (nice one, BTW). What's the point (/advantage?) of introducing/estimating CHF in our survival analysis? It seems that all we need is hazard and survival functions, which have a direct transform. I can't explain the meaning of CHF, it doesn't bring anything, seems redundant... I'm reading about deep survival models (there's lots of papers and code lately) and they hardly mention it...
Cameron Davidson-Pilon
@CamDavidsonPilon
@bkos good question. A few points / advantages: i) The CHF is easier to estimate (less variance) than the hazard ii) The CHF, and the HF, are present in the likelihood equation for survival models, see equation (2.5) in https://cran.r-project.org/web/packages/flexsurv/vignettes/flexsurv.pdf iii) because of the "ease of differentiation" vs "hardness of integration", specifying the CHF and working out the HF is easier than the other way around, iv) it's 1-1 with the SF, that is, SF = exp(-CHF).
Bojan Kostic
@bkos
Thanks a lot, @CamDavidsonPilon! Is the equation you mentioned used in lifelines for some models? With it we don't lose any information, but it's different from the Cox partial likelihood, which includes only uncensored observations and softmax terms...