View Code? Open in Web Editor
NEW
Logistic Regression technique in machine learning both theory and code in Python. Includes topics from Assumptions, Multi Class Classifications, Regularization (l1 and l2), Weight of Evidence and Information Value
logistic-regression-in-python's Introduction
Logistic-regression-in-python
01_LR_Introduction (Theory)
Predict categories based on MLE
02_Odd_LogOdd_OddRatio (Theory)
Probability : Something Happening / Everything that could Happen
Odds : Something Happening / Something Not Happening
Log(Odds) : To make Odds output symmetry
Indepth Logistic Output explained
04_Likelihood_Probability (Theory)
06_LR_Assumptions (Theory)
Assumption 1 - Appropriate outcome type (Must be categorical)
Assumption 2 - Linearity of independent variables and log odds
Assumption 3 - No strongly influential outliers
Assumption 4 - Absence of multicollinearity
Assumption 5 - Independence of observations
Assumption 6 - Sufficiently large sample size
07_LR_Assumptions (Python Code)
Python Code for Logistic Regression Assumptions
Akaike Information Criterion
Bayesian Information Criterion
Choose the lowest score
09_Logistic_Regression (Python Code)
Python Code for Logistic Regression
10_Multiclass_Classification (Theory)
One vs All (OvA) also known as One vs Rest (OvR)
One vs One (OnO)
11_Multi_Class_Classification (Python Code)
Python Code for Multi Class Classification
12_Regularization (Theory)
L1 Lasso
SSR + lamda * (slope)^2
Useless variable become 0
L2 Ridge
SSR + lamda * |slope|
Useless variable tends to become 0 but never = 0
Elastic Net : Combination of L1 & L2
13_LR_Regularization (Python Code)
Python Code of Regularization (L1 Lasso,L2 Ridge & Elastic Net)
Weight of Evidence : Predictive power of Independent Variables
Information Value : Technique to select important Variables
15_LR_WOE_IV (Python Code)
Python Code for WOE and IV
Logistic Regression Revision
17_LR_1_Interview_Questions (Theory)
Logistic Regression Interview quesion bank
18_LR_2_Interview_Questions (Theory)
Indepth Logistic Output explained
logistic-regression-in-python's People
Contributors
Watchers