MOBPY Release - Version 1.1.1

BUG FIXES :

MOB image :

• Fix the brackets for the interval display since we cannot contain inf/-inf.

PAVA image :

• Fix the interval display to show -inf as the minimum interval start Value
• Fix the brackets for the interval display since we cannot contain inf/-inf.

MOBPY Release - Version 1.1.0

New Features:

1. PAVA Implementation:

• Implemented the Pool Adjacent Violators Algorithm (PAVA), providing an extension on flexible statistic metric of response variable for forming the monotonic trend.
• Introduced the applyPAVA() method, allowing users to apply the PAVA result to their data and return a pandas series of the interval information assignment.
• Visualize the Cumulative Sum Diagram (CSD) and Greatest Convex Minorant (GCM) chart using the new MOB_PLOT.plotPAVACsd method.

2. Enhanced MOB Integration:

• Users can now apply the MOB algorithm's results directly to their data using the new applyMOB() method.

Fixes:

1. MOB Plot Enhancements:

• The MOB Plot now displays missing data and exclusive data on the chart, providing better insights and context to the users.

Optimizations:

1. MOB Algorithm:

• Adjusted column names and modified result display in binsummary, presenting a clearer summary columns as: [intervalStart | intervalEnd) | ..... for more precise information.
• MOB result now sets the index name to the corresponding var argument for improved clarity and usability.

2. MOB_PLOT:

• Refactored the plotBinsSummary method to remove the var_name argument, simplifying the plotting process.
• The x-axis representation now uses intervals for better visualization.
• The background color of the figure has been set to white, enhancing readability and aesthetics.

MOBPY Release - Version 1.0.1

Highlights of Version 1.0.1:

• Bug fixes, including resolving issues with exclude values entered as a list.

• Applied adjusted weight of evidence (WOE) handling for zero positive or negative events.

• Added function annotations for improved code readability.

Release Notes - MOBPY v1.0.0

We are excited to announce the release of MOBPY v1.0.0, introducing the initial implementation of the Monotone Optimal Binning (MOB) algorithm. This version focuses on providing basic functionality for working with numerical variables.

Key Features:

• Monotone Optimal Binning (MOB) algorithm implementation.
• Support for binning numerical variables.

User Preferences:
The MOB algorithm in MOBPY v1.0.0 offers two user preference settings (mergeMethod argument):

1. Size: This setting allows you to optimize the sample size of each bin within specified maximum and minimum limits while ensuring that the minimum number of bins constraint is maintained.

2. Stats: With this setting, the algorithm applies a stricter approach based on hypothesis testing results.

We are committed to further improving MOBPY and expanding its capabilities to handle additional data types and user preferences in future releases.

For more information, including detailed usage instructions and examples, please refer to the documentation provided.

Note: This release only supports the handling of numerical variables.

Full Changelog: https://github.com/ChenTaHung/Monotonic-Optimal-Binning/commits/v1.0.0