Measures for In-Sample Evaluation

By using the numerical value it could measure how the model is fitted to the data. 

There are two type of it: 

1- Mean Squared Error (MSE):

 find the between predict and actual value then square it and divided by the number of samples;

The Code

from sklearn.metrics import mean_squared_error

mean_squared_error(df['price'], Y_predict_simple_fit)

2-R-squared(R^2): [0,1]

It measure how close the data to the fitted regression line and it is the percentage of variation of the target variable (Y) that is explain by the linear model.

 

\[R^{2} = (1-\frac{MSE of regressionline}{MSE of teh average of the data})\]

The Code: 

X = df[['highway-mpg']]

Y = df['price']

lm.fit(X, Y) // if the result is negative so there are overfitting must be solve

Share on Google Plus

About Inas AL-Kamachy