Different results in course video and run lecture Jupyter file

With the same scaled_inputs both in video (2:20:42) and the lecture Jupyter file
scaled_inputs =
array([[-1.43876426, -0.45332 , -0.90861367],
[-1.50996545, 0.5096211 , -0.07876719],
[-0.79795355, 0.38330685, 1.58092576],
…,
[-1.50996545, 1.0148781 , -0.90861367],
[-1.29636188, -0.79781341, -0.90861367],
[ 1.55168573, -0.26138796, -0.90861367]]),
why the weights in video (2:21:42) are different from the results obtained by running the lecture Jupyter file? The latter are

feature weight
0 age 256.856353
1 bmi 339.193454
2 children 475.500545
3 smoker_code 23848.534542
4 sex_code -131.314359
5 northeast 587.009235
6 northwest 234.045336
7 southeast -448.012814
8 southwest -373.041756
9 1 -12525.547811

In particular, the weights for the four regions (NE, NW, SE, SW) are all the same in the video (2:21:46) while for those obtained by running the lecture Jupyter file have different values. Can someone confirm this and explain why the results are different? Thanks!