Implementing standard logistic regression from scratch

Logistic Regression is a generalized Linear Regression in which we do not output the weighted sum of inputs directly, but is passed through a function (sigmoid) that can map any real value between 0 and 1.

In the Logistic regression class; the hypothesis (sigmoid, net_input, probability functions), the cost function, gradient descent, train (fit, predict funtions) and accuracy were written.

The created model was tested on marks.txt data The numpy module was used for mathematical calculations The matplotlib module was used for plotting generated data The scipy module was used to compute the minimum value in relation to the gradient descent