No project description provided
Project description
qp_flexzboost
This package allows for efficient, lossless storage of Flexcode[^1][^2] conditional density estimates and leverages the machinery provided by qp.
The primary module in the package provides the FlexzboostGen
class, a subclass of the qp.Pdf_rows_gen
class.
An API to retrieve PDF, CDF, and PPF values in addition to supporting simple plotting of PDFs is provided.
While it is possible to use all of the standard scipy.rvs_continuous
methods to work with a qp.Ensemble
of CDEs stored as FlexzboostGen
objects, it is much more efficient to convert the FlexzboostGen
representation into a native qp
representation, such as qp.interp
.
FlexzboostGen
is not included as a part of qp
by default for the following reasons:
- It is not possible to convert from a native
qp
representation into aFlexzboostGen
representation becauseFlexzboostGen
stores the output of machine learned model. However, it is possible to convert fromFlexzboostGen
to any other nativeqp
representation. - The use case is very tightly coupled to
Flexcode
and currently supports one specific use case - efficient storage ofqp.Ensemble
objects produced as output from rail_flexzboost stages.
For more information and usage examples, please see the documentation and API reference available here: https://qp-flexzboost.readthedocs.io/en/latest/index.html
Attribution
This project was automatically generated using the LINCC Frameworks Python Project Template.
For more information about the project template see the documentation.
[^1]: Rafael Izbicki and Ann B. Lee, “Converting high-dimensional regression to high-dimensional conditional density estimation”, Electron. J. Statist. 11(2): 2800-2831 (2017). DOI: 10.1214/17-EJS1302
[^2]: Schmidt et al, “Evaluation of probabilistic photometric redshift estimation approaches for The Rubin Observatory Legacy Survey of Space and Time (LSST)“, MNRAS, 449(2): 1587-1606. https://doi.org/10.1093/mnras/staa2799
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file qp_flexzboost-0.1.1.tar.gz
.
File metadata
- Download URL: qp_flexzboost-0.1.1.tar.gz
- Upload date:
- Size: 42.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.16
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c19eefd5a8a7266c6ddafd79db19f9a963f58e836624e83a3973ba7ffc29649a |
|
MD5 | 09c21fc18d750afb35d3916a595b637c |
|
BLAKE2b-256 | 9aceb107b94259d4545a81ed3e049ec66d9e3ae465d6c4290bd5257e94c5a0a5 |
File details
Details for the file qp_flexzboost-0.1.1-py3-none-any.whl
.
File metadata
- Download URL: qp_flexzboost-0.1.1-py3-none-any.whl
- Upload date:
- Size: 12.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.16
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e6f60db648df5d5d65e7ad256834569186f9abf9cb560f44397d68d0c3364bec |
|
MD5 | f668b2befce299866cdd9c393663b4b1 |
|
BLAKE2b-256 | 292affe072503932d126ccf9e4029c2d6fc0607a6fec0d441556a0680ea7c51f |