Cleaning the Weight Column

The weight column contained many entries marked as '?', which I replaced with NaN. Over 98,000 records were missing weight information, making this column a candidate for exclusion in further analysis. However, I preserved it for now to observe any patterns in available ranges like [75-100] or [50-75]. Cleaning this column highlights the challenges of working with incomplete clinical data.

Source https://archive.ics.uci.edu/dataset/296/diabetes+130-us+hospitals+for+years+1999-2008