Polynomial linear regression using Sklearn is tedious as one has to explicitly code its features. This can get challenging when one has to iteratively build higher-degree polynomial models.
NumPy's ๐ฉ๐จ๐ฅ๐ฒ๐๐ข๐ญ() method is an excellent alternative to this. Here, you can specify the degree of the polynomial as a parameter. As a result, it automatically creates the corresponding polynomial features.
The downside is that you cannot add custom features such as trigonometric/logarithmic. In other words, you are restricted to only polynomial features. But if that is not your requirement, NumPy's ๐ฉ๐จ๐ฅ๐ฒ๐๐ข๐ญ() method can be a better approach.
Read more here: https://numpy.org/doc/stable/reference/generated/numpy.polyfit.html
P.S. I post these daily tips on LinkedIn as well. You can read them here:ย https://www.linkedin.com/in/avi-chawla/recent-activity/shares