Logistic regression and linear regression

Same point:
Both are generalized linear models GLM (generalized linear models)

Different points:
1. Linear regression requires that the dependent variable (assuming y) is a continuous numeric variable, while the logistic regression requires that the dependent variable is a discrete type variable, such as the most common two classification problem, 1 represents a positive sample, and 0 represents a negative sample
2. Linear regression requires the self-variable to obey the normal distribution, and the distribution of the logistic regression to the variable is not required
3. Linear regression requires that the independent variable has a linear relationship with the dependent variable, and logistic regression does not require
4. Linear regression is the direct analysis of the relationship between the dependent variable and the independent variable, and the logistic regression is the relationship between the probability and the independent variable that the dependent variable takes a certain value.

The main difference is the 1th