Master Multi-Linear Regression & Prediction with scikit-learn in Python 🚀

In this video, I would like to explore performing multi regression and prediction using python scikit learn where my response is a numeric variable and feature variables are both numeric and categorical. The content is solely for educational purposes and is based on my personal experience.

Links:
Dataset - https://www.kaggle.com/datasets/zynicide/wine-reviews
Code - https://github.com/maddyhyc/Multiple-Linear-Regression-and-Prediction-with-scikit-learn-python-Part-1

See other links to sites that I used to hone my skills below. I may receive commission from them.
BE SURE TO CHECK THEM OUT!
Datacamp signup and learn for free - https://datacamp.pxf.io/c/3053810/1611872/13294
Datacamp student - https://datacamp.pxf.io/c/3053810/1611874/13294
Datacamp business - https://datacamp.pxf.io/c/3053810/1545190/13294
Canva - https://partner.canva.com/FwDbyMaddy

Timestamps:
00:00 Introduction
00:17 Ask ChatGPT
01:25 Coding starts - importing packages, read in and explore data, check missing values
02:37 Investigate country categorical variable, check counts, and values, create top 10 countries, data manipulation
04:19 Create Response and Feature variables using .loc call
05:10 Start preprocessing with OneHotEncoder and StandardScaler
05:35 Covert categorical country variable to binary variables, determining, binary columns
06:31 Normalize numeric points variable, how to interpret coefficient, reasons for normalizing numeric points
08:02 Split train/testing datasets, fit Linear Regression
08:33 Evaluate model's performance, coefficients, intercept
09:16 R-squared, and Residuals (for points and country model)
10:06 Investigate taster_name categorical variable
10:43 Preprocessing using OneHotEncoder and StandardScaler
11:12 Fitting linear regression, coefficients, intercept
11:21 R-squared, and Residuals (for points and taster_name model)
12:00 Compare models and closing final thoughts