Use the split test_size=0.2, random_state=42 with age_years → price_lakh, and train on the training part.
Store the root mean squared error on the test part, rounded to 2 decimals, in result. RMSE grows faster than MAE when a few predictions are far off.
import io
import pandas as pd
cars = pd.read_csv(io.StringIO("""car_id,age_years,km_driven_thousand,fuel,owners,price_lakh
1,5,32,Diesel,1,6.77
2,1,3,Petrol,1,8.59
3,2,11,Petrol,2,7.28
4,2,23,Petrol,1,7.17
5,4,37,Petrol,1,5.86
6,5,39,Diesel,1,6.68
7,6,74,Diesel,1,5.01
8,5,57,Diesel,1,6.00
9,7,68,Petrol,1,4.04
10,7,77,Diesel,2,4.41
11,3,37,Petrol,1,6.29
12,7,59,Petrol,3,4.12
13,1,11,Petrol,2,7.47
14,2,18,Petrol,1,7.34
15,11,113,Petrol,3,1.12
16,6,75,Diesel,1,5.24
17,7,77,Diesel,2,4.72
18,10,128,Petrol,1,2.01
19,1,3,Petrol,1,7.74
20,11,143,Diesel,2,2.17
21,8,95,Petrol,2,3.41
22,8,96,Petrol,1,3.27
23,3,46,Diesel,2,6.90
24,3,30,Petrol,1,7.01
25,1,17,Diesel,1,8.77
26,1,15,Petrol,1,8.07
27,11,101,Petrol,1,1.94
28,6,78,Petrol,1,4.17
29,11,136,Diesel,2,1.79
30,8,99,Petrol,2,3.11
31,5,56,Petrol,1,5.76
32,7,77,Petrol,1,4.60
33,5,60,Petrol,1,5.08
34,3,33,Diesel,1,7.18
35,2,29,Petrol,1,7.59
36,7,94,Diesel,1,4.62
37,6,57,Diesel,1,5.47
38,6,54,Diesel,1,5.88
39,3,38,Petrol,1,7.21
40,9,114,Petrol,2,2.84
41,9,125,Petrol,3,2.14
42,9,94,Petrol,1,2.47
43,11,97,Diesel,1,2.99
44,1,15,Diesel,1,9.08
45,10,90,Diesel,3,2.82
46,11,112,Petrol,2,1.03
47,4,44,Petrol,1,6.53
48,4,52,Petrol,1,6.23
49,2,19,Diesel,1,8.23
50,8,87,Diesel,1,4.03
51,2,34,Petrol,1,7.31
52,6,85,Diesel,2,5.18
53,8,87,Petrol,3,2.80
54,5,66,Diesel,1,6.06
55,11,104,Petrol,2,0.90
56,7,69,Petrol,1,4.79
57,9,126,Petrol,2,1.95
58,10,108,Petrol,1,2.34
59,5,67,Petrol,2,5.40
60,4,40,Petrol,2,6.04"""))Store your final answer in a variable named result.
Each hint gives a little more help. Try on your own first.
Run your code to see the output here.