Auto Feature Selection and Evaluation using Bregman Divergence & ItakuraSaitoSelector
Project description
Dependencies
Make sure you have install the sklearn
sklearn version == 1.0.1
Feature Selection using Bregman divergence & Itakura Saito
What is Bregman Divergence & Itakura Saito
In statistics, divergence is a function that finds and measures differences using the distance between two probability distributions. Bregman divergence is one of many divergences. It can be calculated with the squared Euclidean distance:
###Steps to apply auto_feat_selection
#import
from auto_feat_select_rupakbob import auto_feat_selection
#grid_feat_search(dataframe,'taget_column_name', max_divergence(default = 0,max = 10)accepted divergence with the target column)
index 0 = BregmanDivergenceSelector, index 1 = ItakuraSaitoSelector
cols_BregmanDivergenceSelector = auto_feat_selection.grid_feat_search(df,'target',5)[0]
cols_ItakuraSaitoSelector = auto_feat_selection.grid_feat_search(df,'target',5)[1]
Evaluate if the selected features improves the model
###Currently supports Logistic Regression base model with goal to evaluate feature performance
#evaluate_grid_feat_search(dataframe,'taget_column_name')
auto_feat_selection.evaluate_grid_feat_search(df,cols_BregmanDivergenceSelector,target ='target')
auto_feat_selection.evaluate_grid_feat_search(df,cols_ItakuraSaitoSelector,target ='target')
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
Hashes for auto_feat_selection-0.0.8.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | b6ea1bfba30b61170f77593bb89c9a4db54884c917ef9800a5dde8b5489dec14 |
|
MD5 | 5f283fde187fdd9bec43a01ed43734ee |
|
BLAKE2b-256 | 97ab63c2494246c027df8bc9f519a3c91ba6e9f6af6b66418f7c7676b6f6a18d |
Hashes for auto_feat_selection-0.0.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bcd023207f96e9413f0723036b5e840544be4be8fd8a71b715dfd529f196c6a0 |
|
MD5 | b843ea4c14738f23513e34f558c1def6 |
|
BLAKE2b-256 | 0ef9258bae42ecb85157835f77cd67af0a9103b95b9e812936da66c71808be31 |