MOBPY 1.0.1

MOB is a statistical approach to transform continuous variables into optimal and monotonic categorical variables.

Monotonic-Optimal-Binning

Python implementation (MOBPY)

MOB is a statistical approach to transform continuous variables into optimal and monotonic categorical variables. In this project, we have expanded the application to allow the users to merge the bins based on statistics or bin size. This is a Python-based project that enables the users to achieve monotone optimal binning results aligned with their expectations.

Installation

python3 -m pip install MOBPY

Usage

Example:

import pandas as pd
from MOBPY.MOB import MOB


if __name__ == '__main__' :
    # import the testing datasets
    df = pd.read_csv('/data/german_data_credit_cat.csv')
    
    # Original values in the column are [1,2], make it into 1 representing the positive term, and 0 for the other one.
    df['default'] = df['default'] - 1

    # run the MOB algorithm to discretize the variable 'Durationinmonth'.
    MOB_ALGO = MOB(data = df, var = 'Durationinmonth', response = 'default', exclude_value = None)
    # A must-do step is to set the binning constraints.
    MOB_ALGO.setBinningConstraints( max_bins = 6, min_bins = 3, 
                                    max_samples = 0.4, min_samples = 0.05, 
                                    min_bads = 0.05, 
                                    init_pvalue = 0.4, 
                                    maximize_bins=True)
    # execute the MOB algorithm.
    SizeBinning = MOB_ALGO.runMOB(mergeMethod='Size') # Run under the bins size base.

    StatsBinning = MOB_ALGO.runMOB(mergeMethod='Stats') # Run under the statistical base. 
    

The runMOB method will return a pandas.DataFrame which shows the binning result of the variable and also the WoE summary information for each bin.

And after we receive the binning result dataframe, we can plot it by using MOBPY.plot.MOB_PLOT.plotBinsSummary to visualize the binning summary result.

from MOBPY.plot.MOB_PLOT import MOB_PLOT

# plot the bin summary data.
print('Bins Size Base')
MOB_PLOT.plotBinsSummary(monoOptBinTable = SizeBinning, var_name = 'Durationinmonth')

print('Statisitcal Base')
MOB_PLOT.plotBinsSummary(monoOptBinTable = StatsBinning, var_name = 'Durationinmonth')

Highlighted Features

User Preferences:

The MOB algorithm 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.
   

Typically, the 'Stats' (statistical-based) and 'Size' (bin size-based) methods yield identical results. However, when dealing with data under certain scenarios where the 'Size' method, employed by MOB, tends to prioritize maintaining the population of each bin within the maximum and minimum limits. In contrast, the 'Stats' method adheres to a more rigorous logic based on the results of hypothesis testing.

For example,

# run the MOB algorithm to discretize the variable 'Creditamount'.
MOB_ALGO = MOB(data = df, var = 'Creditamount', response = 'default', exclude_value = None) 
# Set Binning Constraints (Must-Do!)
MOB_ALGO.setBinningConstraints( max_bins = 6, min_bins = 3, 
                                max_samples = 0.4, min_samples = 0.05, 
                                min_bads = 0.05, 
                                init_pvalue = 0.4, 
                                maximize_bins=True)
# mergeMethod = 'Size' means to run MOB algorithm under bins size base
SizeBinning = MOB_ALGO.runMOB(mergeMethod='Size')
StatsBinning = MOB_ALGO.runMOB(mergeMethod='Stats')

# plot the bin summary data.
print('Bins Size Base')
MOB_PLOT.plotBinsSummary(monoOptBinTable = SizeBinning, var_name = 'Durationinmonth')
print('Statisitcal Base')
MOB_PLOT.plotBinsSummary(monoOptBinTable = StatsBinning, var_name = 'Durationinmonth')

SizeBinning	StatsBinning
runMOB(mergeMethod='Size') (bins size base)	runMOB(mergeMethod='Stats') (statistical base)

The left side image is the result generated by mergeMethod = 'Size' (bin size-based), and the right side is the result generated by mergeMethod = 'Stats' (statistical-based). We can see that the 'Size' method is designed to merge bins that fail to meet the minimum sample population requirement. This approach ensures that the number of bins remains within the specified limit, preventing it from exceeding the minimum bin limitation. By merging bins that fall short of the population threshold, the 'Size' method effectively maintains a balanced distribution of data across the bins..

Full Documentation

↪ Full API Reference

Environment

OS : macOS Ventura

IDE: Visual Studio Code 1.79.2 (Universal)

Language : Python 3.9.7 
    - pandas 1.3.4
    - numpy 1.20.3
    - scipy 1.7.1
    - matplotlib 3.7.1

Reference

• Testing Dataset : German Credit Risk from Kaggle

• Mironchyk, Pavel, and Viktor Tchistiakov. "Monotone optimal binning algorithm for credit risk modeling." Utr. Work. Pap (2017).

• GitHub Project : Monotone Optimal Binning (SAS 9.4 version)

Authors

1. Chen, Ta-Hung (Denny)
   
   • LinkedIn Profile : https://www.linkedin.com/in/dennychen-tahung/
   • E-Mail : [e-mail]
2. Tsai, Yu-Cheng (Darren)
   • LindedIn Profile : https://www.linkedin.com/in/darren-yucheng-tsai/
   • E-Mail :