lydiaaboukhamis / lab-cleaning-categorical-data

Lab | Cleaning categorical data

For this lab, we will be using the dataset in the Customer Analysis Business Case. This dataset can be found in files_for_lab folder. In this lab we will explore categorical data.

Instructions

1. Import the necessary libraries if you are starting a new notebook.
2. Load the continuous and discrete variables into continuous_df and discrete_df variables.
3. Plot a correlation matrix, what can you see?
4. Create a function to plot every discrete variables. Do the same with continuous variables (be careful, you may change the plot type to another one better suited for continuous data).
5. What can you see in the plots?
6. Look for outliers in the continuous variables we have found. Hint: There was a good plot to do that.
7. Have you found outliers? If you have, what should we do with them?
8. Check nan values per column.
9. Define a function that differentiate between continuous and discrete variables. Hint: Number of unique values might be useful. Store continuous data into a continuous variable and do the same for discrete and categorical.
10. for the categorical data, check if there is some kind of text in a variable so we would need to clean it. Hint: Use the same method you used in step 7. Depending on the implementation, decide what to do with the variables you get.
11. Get categorical features.
12. What should we do with the customer id column?