Metadata-Version: 2.1
Name: lambda_or
Version: 0.0.2
Summary: Lambda Odds Ratio
Home-page: https://github.com/zeroknowledgediscovery/lambda_or
Download-URL: https://github.com/zeroknowledgediscovery/lambda_or/archive/0.0.2.tar.gz
Author: Ishanu Chattopadhyay
Author-email: zeroknowledgediscovery@gmail.com
License: LICENSE
Keywords: robust odds ratio,misclassification correction,machine learning,EHR databases
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
Classifier: Topic :: Software Development :: Libraries
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.9
Requires-Python: >=3.6
Description-Content-Type: text/x-rst
License-File: LICENSE

===============
Qbiome
===============

.. class:: no-web no-pdf

:Info: Draft link will be posted here
:Author: ZeD Lab <zed.createuky.net>
:Description: Robust Odds Ratio correcting label noise 
:Documentation: 


**Usage:**

.. code-block::

    from lambda_or import lambda_or, pq_from_two_gates

    tilde = np.array([[100, 50],[ 80, 70]], dtype=float)
    # Suppose selection-conditional rates from two-gate ROC:
    p_sel, q_sel = 0.92, 0.90
    res = lambda_or(tilde, p_sel, q_sel, n_val=2000)
    
    print(res.log_or, res.neglog10_p, res.z, res.se)
    print(res.counts)   # corrected a,b,c,d

