nannyml
nannyml copied to clipboard
NannyML
nannyml: post-deployment data science in python
**Describe the bug** Running the Quickstart results in an error **To Reproduce** Steps to reproduce the behavior: Runing: ``` import pandas as pd import nannyml as nml from IPython.display import...
It would be useful to exploit methodologies that allow the user to avoid the choice of the number of bins for estimating the Expected Calibration Error. From the literature, static...
* nannyml version: 0.4.1 * Python version: 3.7.12 * Operating System: Linux (Kaggle Kernel) ### Description Trying to run the code in the [Chunking data](https://nannyml.readthedocs.io/en/latest/how_it_works/chunking_data.html) section. It specifically gives error...
If it doesn't already exist in the NannyML package (I didn't find it), it would be nice to have a collection of bare-bones functions to predict performance using only a...
* nannyml version: 0.3.1 2a46c7aee39a898de17d8ae24b10d6888802eeb5 * Python version: 3.10 * Operating System: Fedora ### Description `doc8` package does not get installed ### What I Did Run tests after creating a...
**Describe the bug** When using chunk_count as a chunker option in realized performance dates are ignored in results and plots. **To Reproduce** The results are reproduced with the following code:...
**Describe the bug** The thresholds and confidence bands for some regression metrics can  What is wrong with the above plot? - The lower threshold for performance change is below...
**Describe the bug** When reviewing the estimated performance plot after running a DLE estimator, the RMSE is moving under the threshold. Whilst performance is actually better, it is still labeled...
**Motivation: describe the problem to be solved** Real world use cases have large data sets that can not fit in memory. Doing performance estimation on such datasets is not possible...
It would be nice if you'd allow bootstrapping (resampling with replacement) instead of non-overlapping chunks for the CBPE estimate. Ideally, something like this: https://stats.stackexchange.com/questions/96739/what-is-the-632-rule-in-bootstrapping
