Description

On the scatterplot of rating vs salary, you may have noticed that the relationship between these two variables seems to be different from linear and looks like a polynomial function. Let's try to raise the rating by several degrees and see whether it improves the score.

Objectives

1. Read the data. For downloading the dataset refer to Stage 1;
2. Load the data with pandas.read_csv;
3. Make X a DataFrame with a predictor rating and y a series with a target salary;
4. Raise predictor to the power of $2$.
5. Split the predictors and target into training and test sets. Use test_size=0.3 and random_state=100 parameters — they guarantee that the results will be as expected;
6. Fit the linear model of salary on rating, make predictions and calculate the MAPE;
7. Repeat steps 2–5 for the power of 3 and 4;
8. Print the best MAPE obtained by fitting and running the models described above. The MAPE is a float number rounded to five decimal places.

Example

Example 1: program output

1.23456