<aside> 📚

My Notebook in Github in first:

https://github.com/DataScienceMyLove/homeworks-ml-zoomcamp-2025/blob/main/02-linear_regression/homework-2.ipynb

</aside>

<aside> 📚

The questions are framed in white font.

</aside>

<aside> 💡

The key ideas to keep in mind in yellow.

</aside>

<aside> 📚

Question 1

There's one column with missing values. What is it?

</aside>

<aside> 💡

• Importance of EDA for looking at the distribution of the fuel_efficiency: our target
• Search for the missing values
• Investigate for knowing the measures of central tendency and dispersion (mode, median, mean) of the features
• Spot the duplicates if necessary </aside>

<aside> 📚

Question 2

What's the median (50% percentile) for variable 'horsepower'?

</aside>

<aside> 💡

• One of the measure to use to understand a feature and its distrib: always have in mind the others (mode, mean, standard deviation,range of values and quartiles)

Prepare and split the dataset

• Shuffle the dataset with a seed number for keeping the order and retrieve your index
• Split your data in train/val/test sets, with 60%/20%/20% distribution for the 1st part of the process.
• Never forget to delete the target column of the Xtrain,Xval & Xtest
• Make functions with fixed data (of the final dataset for training: columns/categories) to prepare the data
• No transformations made on the entire dataset: beware to data leakage </aside>

<aside> 📚

Question 3

• We need to deal with missing values for the column from Q1.
• We have two options: fill it with 0 or with the mean of this variable.
• Try both options. For each, train a linear regression model without regularization using the code from the lessons.
• For computing the mean, use the training only!
• Use the validation dataset to evaluate the models and compare the RMSE of each option.
• Round the RMSE scores to 2 decimal digits using round(score, 2)

Which option gives better RMSE?

</aside>