Now, let's go through a few more examples, and for each example I'm going to show you another attribute of the same dataset and I'm going to ask you to identify what attribute type it is and also to identify the additional characteristics that we mentioned like beings spacial, or temporal, or hierarchical and so on. The first one is customer segment. This attribute contains four main values; consumer, corporate, home office, and small business. So what kind of attribute is this? Okay, that's another categorical attribute. The values of this attribute are four different categories and there's really no particular order that can be considered in these values. So, it's just a plain categorical attribute. The next one is these pair, province and region. There are a number of regions and a number of provinces within each region. What kind of attribute is this? So, these two attributes are clearly categorical attributes because they identify a number of categories but they also have the additional characteristics of being special because they describe geographical locations and they're are also hierarchical because I can build a hierarchy out of provinces and regions within each regions, there is a number of province. The next one is order ID, that's just a number that describes, actually keeps track of a unique- uses a unique number to identify an order. So, what kind of attribute is this? Okay, this attribute is ordinal and this is a typical example where students often make mistakes because they see a number within order ID and they believe that that's a quantitative attribute but it's not. So remember, not necessarily if you see a number then this attribute is quantitative, is quantitative only if it measure something. So in this case we have an ordinal attributes. Even more precisely, without adding more information, these attributes could have been considered categorical because we don't know if these numbers actually do represent an order. So the safest case is to assume that these are just a number of categories. But since I know the dataset and where it comes from, I know that these numbers are actually sequential and represent the sequence of orders. So it is an ordinal attribute. The next one is product container and the values within this product container's attribute are jumbo box, jumbo drum, large box, medium box, a small box, small pack, and wrap bag. So what kind of attribute is this? Okay. So here we have another example where the interpretation depends on how much we know about the data. So, for sure, this can be considered a categorical attribute. The doubt that you may have is whether this is also ordinal. So, in another way, is it possible to order the values of these categories meaningfully? Again, I think if it makes sense, if for instance if this product containers have different volumes and they can be ordered by their volume and it's useful to do that, then you can consider this attribute as ordinal. So, this gives you also a sense of the fact that the interpretation of a type of attribute, a given attribute is also depends on understanding at a deeper level the real meaning of these attributes and how they relate to the phenomena or objects that they describe in the world.