Depending on the type of input and output variables, predicting the task given different names: input and output variables are continuous variables to predict problem is called regression output variables to predict problems finite number of discrete variables called classification, input variables and output variables are called variable sequence prediction problem question mark. Here realization of the principles of linear regression algorithm and code to make a summary.
Principle 1 of the linear regression
Regression relationships between the input variables and the predicted output variables, especially when changes in the value of the input variable changes, the value of output variables of the consequent. Regression model is a function representing the mapping between the input variables to the output variable, equivalent learning function fitting in regression: selecting a function curve fit so well known and well data predict unknown data.