How to find the related columns between column?

Suppose I have a data frame with columns car_id,number_car,bike_id,number_bike.

df =
Product_id   Category order_id   order   customer_id  customer Name 
 pd01         car      or01      service   cus01       Jack
 pd02         bike     or02      repair    cus02       Swan
 pd03         car      or3       repair    cus03       Tom
 pd04         car      or04      cleaning  cus04       ram

Where we can make out that Product_id has a relation with Category, order_id has a relation with order and customer_id has a relation with customer name. But I am just curious about finding this by using nltk or any other way. Is it possible to find the relation between the columns using nltk word2vec? Just like sending a sentence as a list can we send the column as a list?

If not possible by nltk or is there any other way of doing this in data science, or any other method not related to data science. What is the best way to do it?

Basically, I am trying to find the dimensional tables without any human interference