HyperAI

Non-ordinal Attribute

Unordered propertiesRefers to the situation where attributes cannot be arranged in order.

For example, if the color attributes are [red, yellow, blue], they cannot be simply converted to [1, 2, 3] during processing.There is no obvious "order" relationship between the original attributes, such as size, distance, etc. If it is converted to [1, 2, 3], this "order" relationship will be introduced invisibly when calculating the distance.

Attributes like this are often called unordered attributes, and they can usually be converted into vector processing, such as converting them into the three attributes {[ 1 , 0, 0 ],[ 0 , 1, 0 ],[ 0 , 0 , 1 ]}.

References

【1】https://blog.csdn.net/weixin_35732969/article/details/81120512?utm_source=copy